Merge branch 'master' into v3-definition

* ComfyAPI Core v0.0.2

* Respond to PR feedback

* Fix Python 3.9 errors

* Fix missing backward compatibility proxy

* Reorganize types a bit

The input types, input impls, and utility types are now all available in
the versioned API. See the change in `comfy_extras/nodes_video.py` for
an example of their usage.

* Remove the need for `--generate-api-stubs`

* Fix generated stubs differing by Python version

* Fix ruff formatting issues

comfy/ldm/wan/model.py

@@ -146,6 +146,15 @@ WAN_CROSSATTENTION_CLASSES = {
 }
 
 
+def repeat_e(e, x):
+    repeats = 1
+    if e.shape[1] > 1:
+        repeats = x.shape[1] // e.shape[1]
+    if repeats == 1:
+        return e
+    return torch.repeat_interleave(e, repeats, dim=1)
+
+
 class WanAttentionBlock(nn.Module):
 
     def __init__(self,
@@ -201,6 +210,7 @@ class WanAttentionBlock(nn.Module):
             freqs(Tensor): Rope freqs, shape [1024, C / num_heads / 2]
         """
         # assert e.dtype == torch.float32
+
         if e.ndim < 4:
             e = (comfy.model_management.cast_to(self.modulation, dtype=x.dtype, device=x.device) + e).chunk(6, dim=1)
         else:
@@ -209,15 +219,15 @@ class WanAttentionBlock(nn.Module):
 
         # self-attention
         y = self.self_attn(
-            self.norm1(x) * (1 + e[1]) + e[0],
+            self.norm1(x) * (1 + repeat_e(e[1], x)) + repeat_e(e[0], x),
             freqs)
 
-        x = x + y * e[2]
+        x = x + y * repeat_e(e[2], x)
 
         # cross-attention & ffn
         x = x + self.cross_attn(self.norm3(x), context, context_img_len=context_img_len)
-        y = self.ffn(self.norm2(x) * (1 + e[4]) + e[3])
-        x = x + y * e[5]
+        y = self.ffn(self.norm2(x) * (1 + repeat_e(e[4], x)) + repeat_e(e[3], x))
+        x = x + y * repeat_e(e[5], x)
         return x
 
 
@@ -331,7 +341,8 @@ class Head(nn.Module):
             e = (comfy.model_management.cast_to(self.modulation, dtype=x.dtype, device=x.device) + e.unsqueeze(1)).chunk(2, dim=1)
         else:
             e = (comfy.model_management.cast_to(self.modulation, dtype=x.dtype, device=x.device).unsqueeze(0) + e.unsqueeze(2)).unbind(2)
-        x = (self.head(self.norm(x) * (1 + e[1]) + e[0]))
+
+        x = (self.head(self.norm(x) * (1 + repeat_e(e[1], x)) + repeat_e(e[0], x)))
         return x
 
 

comfy/ldm/wan/vae2_2.py

@@ -136,7 +136,7 @@ class ResidualBlock(nn.Module):
             if in_dim != out_dim else nn.Identity())
 
     def forward(self, x, feat_cache=None, feat_idx=[0]):
-        h = self.shortcut(x)
+        old_x = x
         for layer in self.residual:
             if isinstance(layer, CausalConv3d) and feat_cache is not None:
                 idx = feat_idx[0]
@@ -156,7 +156,7 @@ class ResidualBlock(nn.Module):
                 feat_idx[0] += 1
             else:
                 x = layer(x)
-        return x + h
+        return x + self.shortcut(old_x)
 
 
 def patchify(x, patch_size):
@@ -327,7 +327,7 @@ class Down_ResidualBlock(nn.Module):
         self.downsamples = nn.Sequential(*downsamples)
 
     def forward(self, x, feat_cache=None, feat_idx=[0]):
-        x_copy = x.clone()
+        x_copy = x
         for module in self.downsamples:
             x = module(x, feat_cache, feat_idx)
 
@@ -369,7 +369,7 @@ class Up_ResidualBlock(nn.Module):
         self.upsamples = nn.Sequential(*upsamples)
 
     def forward(self, x, feat_cache=None, feat_idx=[0], first_chunk=False):
-        x_main = x.clone()
+        x_main = x
         for module in self.upsamples:
             x_main = module(x_main, feat_cache, feat_idx)
         if self.avg_shortcut is not None:

comfy/model_base.py

@@ -1202,7 +1202,7 @@ class WAN22(BaseModel):
     def process_timestep(self, timestep, x, denoise_mask=None, **kwargs):
         if denoise_mask is None:
             return timestep
-        temp_ts = (torch.mean(denoise_mask[:, :, :, ::2, ::2], dim=1, keepdim=True) * timestep.view([timestep.shape[0]] + [1] * (denoise_mask.ndim - 1))).reshape(timestep.shape[0], -1)
+        temp_ts = (torch.mean(denoise_mask[:, :, :, :, :], dim=(1, 3, 4), keepdim=True) * timestep.view([timestep.shape[0]] + [1] * (denoise_mask.ndim - 1))).reshape(timestep.shape[0], -1)
         return temp_ts
 
     def scale_latent_inpaint(self, sigma, noise, latent_image, **kwargs):

comfy/model_management.py

@@ -529,6 +529,8 @@ WINDOWS = any(platform.win32_ver())
 EXTRA_RESERVED_VRAM = 400 * 1024 * 1024
 if WINDOWS:
     EXTRA_RESERVED_VRAM = 600 * 1024 * 1024 #Windows is higher because of the shared vram issue
+    if total_vram > (15 * 1024):  # more extra reserved vram on 16GB+ cards
+        EXTRA_RESERVED_VRAM += 100 * 1024 * 1024
 
 if args.reserve_vram is not None:
     EXTRA_RESERVED_VRAM = args.reserve_vram * 1024 * 1024 * 1024

comfy_api/generate_api_stubs.py

@@ -0,0 +1,86 @@
+#!/usr/bin/env python3
+"""
+Script to generate .pyi stub files for the synchronous API wrappers.
+This allows generating stubs without running the full ComfyUI application.
+"""
+
+import os
+import sys
+import logging
+import importlib
+
+# Add ComfyUI to path so we can import modules
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from comfy_api.internal.async_to_sync import AsyncToSyncConverter
+from comfy_api.version_list import supported_versions
+
+
+def generate_stubs_for_module(module_name: str) -> None:
+    """Generate stub files for a specific module that exports ComfyAPI and ComfyAPISync."""
+    try:
+        # Import the module
+        module = importlib.import_module(module_name)
+
+        # Check if module has ComfyAPISync (the sync wrapper)
+        if hasattr(module, "ComfyAPISync"):
+            # Module already has a sync class
+            api_class = getattr(module, "ComfyAPI", None)
+            sync_class = getattr(module, "ComfyAPISync")
+
+            if api_class:
+                # Generate the stub file
+                AsyncToSyncConverter.generate_stub_file(api_class, sync_class)
+                logging.info(f"Generated stub file for {module_name}")
+            else:
+                logging.warning(
+                    f"Module {module_name} has ComfyAPISync but no ComfyAPI"
+                )
+
+        elif hasattr(module, "ComfyAPI"):
+            # Module only has async API, need to create sync wrapper first
+            from comfy_api.internal.async_to_sync import create_sync_class
+
+            api_class = getattr(module, "ComfyAPI")
+            sync_class = create_sync_class(api_class)
+
+            # Generate the stub file
+            AsyncToSyncConverter.generate_stub_file(api_class, sync_class)
+            logging.info(f"Generated stub file for {module_name}")
+        else:
+            logging.warning(
+                f"Module {module_name} does not export ComfyAPI or ComfyAPISync"
+            )
+
+    except Exception as e:
+        logging.error(f"Failed to generate stub for {module_name}: {e}")
+        import traceback
+
+        traceback.print_exc()
+
+
+def main():
+    """Main function to generate all API stub files."""
+    logging.basicConfig(level=logging.INFO)
+
+    logging.info("Starting stub generation...")
+
+    # Dynamically get module names from supported_versions
+    api_modules = []
+    for api_class in supported_versions:
+        # Extract module name from the class
+        module_name = api_class.__module__
+        if module_name not in api_modules:
+            api_modules.append(module_name)
+
+    logging.info(f"Found {len(api_modules)} API modules: {api_modules}")
+
+    # Generate stubs for each module
+    for module_name in api_modules:
+        generate_stubs_for_module(module_name)
+
+    logging.info("Stub generation complete!")
+
+
+if __name__ == "__main__":
+    main()

comfy_api/input/__init__.py

@@ -1,8 +1,16 @@
-from .basic_types import ImageInput, AudioInput
-from .video_types import VideoInput
+# This file only exists for backwards compatibility.
+from comfy_api.latest._input import (
+    ImageInput,
+    AudioInput,
+    MaskInput,
+    LatentInput,
+    VideoInput,
+)
 
 __all__ = [
     "ImageInput",
     "AudioInput",
+    "MaskInput",
+    "LatentInput",
     "VideoInput",
 ]

comfy_api/input/basic_types.py

@@ -1,20 +1,14 @@
-import torch
-from typing import TypedDict
-
-ImageInput = torch.Tensor
-"""
-An image in format [B, H, W, C] where B is the batch size, C is the number of channels,
-"""
-
-class AudioInput(TypedDict):
-    """
-    TypedDict representing audio input.
-    """
-
-    waveform: torch.Tensor
-    """
-    Tensor in the format [B, C, T] where B is the batch size, C is the number of channels,
-    """
-
-    sample_rate: int
+# This file only exists for backwards compatibility.
+from comfy_api.latest._input.basic_types import (
+    ImageInput,
+    AudioInput,
+    MaskInput,
+    LatentInput,
+)
 
+__all__ = [
+    "ImageInput",
+    "AudioInput",
+    "MaskInput",
+    "LatentInput",
+]

comfy_api/input/video_types.py

@@ -1,85 +1,6 @@
-from __future__ import annotations
-from abc import ABC, abstractmethod
-from typing import Optional, Union
-import io
-import av
-from comfy_api.util import VideoContainer, VideoCodec, VideoComponents
+# This file only exists for backwards compatibility.
+from comfy_api.latest._input.video_types import VideoInput
 
-class VideoInput(ABC):
-    """
-    Abstract base class for video input types.
-    """
-
-    @abstractmethod
-    def get_components(self) -> VideoComponents:
-        """
-        Abstract method to get the video components (images, audio, and frame rate).
-
-        Returns:
-            VideoComponents containing images, audio, and frame rate
-        """
-        pass
-
-    @abstractmethod
-    def save_to(
-        self,
-        path: str,
-        format: VideoContainer = VideoContainer.AUTO,
-        codec: VideoCodec = VideoCodec.AUTO,
-        metadata: Optional[dict] = None
-    ):
-        """
-        Abstract method to save the video input to a file.
-        """
-        pass
-
-    def get_stream_source(self) -> Union[str, io.BytesIO]:
-        """
-        Get a streamable source for the video. This allows processing without
-        loading the entire video into memory.
-
-        Returns:
-            Either a file path (str) or a BytesIO object that can be opened with av.
-
-        Default implementation creates a BytesIO buffer, but subclasses should
-        override this for better performance when possible.
-        """
-        buffer = io.BytesIO()
-        self.save_to(buffer)
-        buffer.seek(0)
-        return buffer
-
-    # Provide a default implementation, but subclasses can provide optimized versions
-    # if possible.
-    def get_dimensions(self) -> tuple[int, int]:
-        """
-        Returns the dimensions of the video input.
-
-        Returns:
-            Tuple of (width, height)
-        """
-        components = self.get_components()
-        return components.images.shape[2], components.images.shape[1]
-
-    def get_duration(self) -> float:
-        """
-        Returns the duration of the video in seconds.
-
-        Returns:
-            Duration in seconds
-        """
-        components = self.get_components()
-        frame_count = components.images.shape[0]
-        return float(frame_count / components.frame_rate)
-
-    def get_container_format(self) -> str:
-        """
-        Returns the container format of the video (e.g., 'mp4', 'mov', 'avi').
-
-        Returns:
-            Container format as string
-        """
-        # Default implementation - subclasses should override for better performance
-        source = self.get_stream_source()
-        with av.open(source, mode="r") as container:
-            return container.format.name
+__all__ = [
+    "VideoInput",
+]

comfy_api/input_impl/__init__.py

@@ -1,7 +1,7 @@
-from .video_types import VideoFromFile, VideoFromComponents
+# This file only exists for backwards compatibility.
+from comfy_api.latest._input_impl import VideoFromFile, VideoFromComponents
 
 __all__ = [
-    # Implementations
     "VideoFromFile",
     "VideoFromComponents",
 ]

comfy_api/input_impl/video_types.py

@@ -1,324 +1,2 @@
-from __future__ import annotations
-from av.container import InputContainer
-from av.subtitles.stream import SubtitleStream
-from fractions import Fraction
-from typing import Optional
-from comfy_api.input import AudioInput
-import av
-import io
-import json
-import numpy as np
-import torch
-from comfy_api.input import VideoInput
-from comfy_api.util import VideoContainer, VideoCodec, VideoComponents
-
-
-def container_to_output_format(container_format: str | None) -> str | None:
-    """
-    A container's `format` may be a comma-separated list of formats.
-    E.g., iso container's `format` may be `mov,mp4,m4a,3gp,3g2,mj2`.
-    However, writing to a file/stream with `av.open` requires a single format,
-    or `None` to auto-detect.
-    """
-    if not container_format:
-        return None  # Auto-detect
-
-    if "," not in container_format:
-        return container_format
-
-    formats = container_format.split(",")
-    return formats[0]
-
-
-def get_open_write_kwargs(
-    dest: str | io.BytesIO, container_format: str, to_format: str | None
-) -> dict:
-    """Get kwargs for writing a `VideoFromFile` to a file/stream with `av.open`"""
-    open_kwargs = {
-        "mode": "w",
-        # If isobmff, preserve custom metadata tags (workflow, prompt, extra_pnginfo)
-        "options": {"movflags": "use_metadata_tags"},
-    }
-
-    is_write_to_buffer = isinstance(dest, io.BytesIO)
-    if is_write_to_buffer:
-        # Set output format explicitly, since it cannot be inferred from file extension
-        if to_format == VideoContainer.AUTO:
-            to_format = container_format.lower()
-        elif isinstance(to_format, str):
-            to_format = to_format.lower()
-        open_kwargs["format"] = container_to_output_format(to_format)
-
-    return open_kwargs
-
-
-class VideoFromFile(VideoInput):
-    """
-    Class representing video input from a file.
-    """
-
-    def __init__(self, file: str | io.BytesIO):
-        """
-        Initialize the VideoFromFile object based off of either a path on disk or a BytesIO object
-        containing the file contents.
-        """
-        self.__file = file
-
-    def get_stream_source(self) -> str | io.BytesIO:
-        """
-        Return the underlying file source for efficient streaming.
-        This avoids unnecessary memory copies when the source is already a file path.
-        """
-        if isinstance(self.__file, io.BytesIO):
-            self.__file.seek(0)
-        return self.__file
-
-    def get_dimensions(self) -> tuple[int, int]:
-        """
-        Returns the dimensions of the video input.
-
-        Returns:
-            Tuple of (width, height)
-        """
-        if isinstance(self.__file, io.BytesIO):
-            self.__file.seek(0)  # Reset the BytesIO object to the beginning
-        with av.open(self.__file, mode='r') as container:
-            for stream in container.streams:
-                if stream.type == 'video':
-                    assert isinstance(stream, av.VideoStream)
-                    return stream.width, stream.height
-        raise ValueError(f"No video stream found in file '{self.__file}'")
-
-    def get_duration(self) -> float:
-        """
-        Returns the duration of the video in seconds.
-
-        Returns:
-            Duration in seconds
-        """
-        if isinstance(self.__file, io.BytesIO):
-            self.__file.seek(0)
-        with av.open(self.__file, mode="r") as container:
-            if container.duration is not None:
-                return float(container.duration / av.time_base)
-
-            # Fallback: calculate from frame count and frame rate
-            video_stream = next(
-                (s for s in container.streams if s.type == "video"), None
-            )
-            if video_stream and video_stream.frames and video_stream.average_rate:
-                return float(video_stream.frames / video_stream.average_rate)
-
-            # Last resort: decode frames to count them
-            if video_stream and video_stream.average_rate:
-                frame_count = 0
-                container.seek(0)
-                for packet in container.demux(video_stream):
-                    for _ in packet.decode():
-                        frame_count += 1
-                if frame_count > 0:
-                    return float(frame_count / video_stream.average_rate)
-
-        raise ValueError(f"Could not determine duration for file '{self.__file}'")
-
-    def get_container_format(self) -> str:
-        """
-        Returns the container format of the video (e.g., 'mp4', 'mov', 'avi').
-
-        Returns:
-            Container format as string
-        """
-        if isinstance(self.__file, io.BytesIO):
-            self.__file.seek(0)
-        with av.open(self.__file, mode='r') as container:
-            return container.format.name
-
-    def get_components_internal(self, container: InputContainer) -> VideoComponents:
-        # Get video frames
-        frames = []
-        for frame in container.decode(video=0):
-            img = frame.to_ndarray(format='rgb24')  # shape: (H, W, 3)
-            img = torch.from_numpy(img) / 255.0  # shape: (H, W, 3)
-            frames.append(img)
-
-        images = torch.stack(frames) if len(frames) > 0 else torch.zeros(0, 3, 0, 0)
-
-        # Get frame rate
-        video_stream = next(s for s in container.streams if s.type == 'video')
-        frame_rate = Fraction(video_stream.average_rate) if video_stream and video_stream.average_rate else Fraction(1)
-
-        # Get audio if available
-        audio = None
-        try:
-            container.seek(0)  # Reset the container to the beginning
-            for stream in container.streams:
-                if stream.type != 'audio':
-                    continue
-                assert isinstance(stream, av.AudioStream)
-                audio_frames = []
-                for packet in container.demux(stream):
-                    for frame in packet.decode():
-                        assert isinstance(frame, av.AudioFrame)
-                        audio_frames.append(frame.to_ndarray())  # shape: (channels, samples)
-                if len(audio_frames) > 0:
-                    audio_data = np.concatenate(audio_frames, axis=1)  # shape: (channels, total_samples)
-                    audio_tensor = torch.from_numpy(audio_data).unsqueeze(0)  # shape: (1, channels, total_samples)
-                    audio = AudioInput({
-                        "waveform": audio_tensor,
-                        "sample_rate": int(stream.sample_rate) if stream.sample_rate else 1,
-                    })
-        except StopIteration:
-            pass  # No audio stream
-
-        metadata = container.metadata
-        return VideoComponents(images=images, audio=audio, frame_rate=frame_rate, metadata=metadata)
-
-    def get_components(self) -> VideoComponents:
-        if isinstance(self.__file, io.BytesIO):
-            self.__file.seek(0)  # Reset the BytesIO object to the beginning
-        with av.open(self.__file, mode='r') as container:
-            return self.get_components_internal(container)
-        raise ValueError(f"No video stream found in file '{self.__file}'")
-
-    def save_to(
-        self,
-        path: str | io.BytesIO,
-        format: VideoContainer = VideoContainer.AUTO,
-        codec: VideoCodec = VideoCodec.AUTO,
-        metadata: Optional[dict] = None
-    ):
-        if isinstance(self.__file, io.BytesIO):
-            self.__file.seek(0)  # Reset the BytesIO object to the beginning
-        with av.open(self.__file, mode='r') as container:
-            container_format = container.format.name
-            video_encoding = container.streams.video[0].codec.name if len(container.streams.video) > 0 else None
-            reuse_streams = True
-            if format != VideoContainer.AUTO and format not in container_format.split(","):
-                reuse_streams = False
-            if codec != VideoCodec.AUTO and codec != video_encoding and video_encoding is not None:
-                reuse_streams = False
-
-            if not reuse_streams:
-                components = self.get_components_internal(container)
-                video = VideoFromComponents(components)
-                return video.save_to(
-                    path,
-                    format=format,
-                    codec=codec,
-                    metadata=metadata
-                )
-
-            streams = container.streams
-
-            open_kwargs = get_open_write_kwargs(path, container_format, format)
-            with av.open(path, **open_kwargs) as output_container:
-                # Copy over the original metadata
-                for key, value in container.metadata.items():
-                    if metadata is None or key not in metadata:
-                        output_container.metadata[key] = value
-
-                # Add our new metadata
-                if metadata is not None:
-                    for key, value in metadata.items():
-                        if isinstance(value, str):
-                            output_container.metadata[key] = value
-                        else:
-                            output_container.metadata[key] = json.dumps(value)
-
-                # Add streams to the new container
-                stream_map = {}
-                for stream in streams:
-                    if isinstance(stream, (av.VideoStream, av.AudioStream, SubtitleStream)):
-                        out_stream = output_container.add_stream_from_template(template=stream, opaque=True)
-                        stream_map[stream] = out_stream
-
-                # Write packets to the new container
-                for packet in container.demux():
-                    if packet.stream in stream_map and packet.dts is not None:
-                        packet.stream = stream_map[packet.stream]
-                        output_container.mux(packet)
-
-class VideoFromComponents(VideoInput):
-    """
-    Class representing video input from tensors.
-    """
-
-    def __init__(self, components: VideoComponents):
-        self.__components = components
-
-    def get_components(self) -> VideoComponents:
-        return VideoComponents(
-            images=self.__components.images,
-            audio=self.__components.audio,
-            frame_rate=self.__components.frame_rate
-        )
-
-    def save_to(
-        self,
-        path: str,
-        format: VideoContainer = VideoContainer.AUTO,
-        codec: VideoCodec = VideoCodec.AUTO,
-        metadata: Optional[dict] = None
-    ):
-        if format != VideoContainer.AUTO and format != VideoContainer.MP4:
-            raise ValueError("Only MP4 format is supported for now")
-        if codec != VideoCodec.AUTO and codec != VideoCodec.H264:
-            raise ValueError("Only H264 codec is supported for now")
-        with av.open(path, mode='w', options={'movflags': 'use_metadata_tags'}) as output:
-            # Add metadata before writing any streams
-            if metadata is not None:
-                for key, value in metadata.items():
-                    output.metadata[key] = json.dumps(value)
-
-            frame_rate = Fraction(round(self.__components.frame_rate * 1000), 1000)
-            # Create a video stream
-            video_stream = output.add_stream('h264', rate=frame_rate)
-            video_stream.width = self.__components.images.shape[2]
-            video_stream.height = self.__components.images.shape[1]
-            video_stream.pix_fmt = 'yuv420p'
-
-            # Create an audio stream
-            audio_sample_rate = 1
-            audio_stream: Optional[av.AudioStream] = None
-            if self.__components.audio:
-                audio_sample_rate = int(self.__components.audio['sample_rate'])
-                audio_stream = output.add_stream('aac', rate=audio_sample_rate)
-                audio_stream.sample_rate = audio_sample_rate
-                audio_stream.format = 'fltp'
-
-            # Encode video
-            for i, frame in enumerate(self.__components.images):
-                img = (frame * 255).clamp(0, 255).byte().cpu().numpy() # shape: (H, W, 3)
-                frame = av.VideoFrame.from_ndarray(img, format='rgb24')
-                frame = frame.reformat(format='yuv420p')  # Convert to YUV420P as required by h264
-                packet = video_stream.encode(frame)
-                output.mux(packet)
-
-            # Flush video
-            packet = video_stream.encode(None)
-            output.mux(packet)
-
-            if audio_stream and self.__components.audio:
-                # Encode audio
-                samples_per_frame = int(audio_sample_rate / frame_rate)
-                num_frames = self.__components.audio['waveform'].shape[2] // samples_per_frame
-                for i in range(num_frames):
-                    start = i * samples_per_frame
-                    end = start + samples_per_frame
-                    # TODO(Feature) - Add support for stereo audio
-                    chunk = (
-                        self.__components.audio["waveform"][0, 0, start:end]
-                        .unsqueeze(0)
-                        .contiguous()
-                        .numpy()
-                    )
-                    audio_frame = av.AudioFrame.from_ndarray(chunk, format='fltp', layout='mono')
-                    audio_frame.sample_rate = audio_sample_rate
-                    audio_frame.pts = i * samples_per_frame
-                    for packet in audio_stream.encode(audio_frame):
-                        output.mux(packet)
-
-                # Flush audio
-                for packet in audio_stream.encode(None):
-                    output.mux(packet)
-
+# This file only exists for backwards compatibility.
+from comfy_api.latest._input_impl.video_types import *  # noqa: F403

comfy_api/internal/__init__.py

@@ -0,0 +1,150 @@
+# Internal infrastructure for ComfyAPI
+from .api_registry import (
+    ComfyAPIBase as ComfyAPIBase,
+    ComfyAPIWithVersion as ComfyAPIWithVersion,
+    register_versions as register_versions,
+    get_all_versions as get_all_versions,
+)
+
+import asyncio
+from dataclasses import asdict
+from typing import Callable, Optional
+
+
+def first_real_override(cls: type, name: str, *, base: type=None) -> Optional[Callable]:
+    """Return the *callable* override of `name` visible on `cls`, or None if every
+    implementation up to (and including) `base` is the placeholder defined on `base`.
+
+    If base is not provided, it will assume cls has a GET_BASE_CLASS
+    """
+    if base is None:
+        if not hasattr(cls, "GET_BASE_CLASS"):
+            raise ValueError("base is required if cls does not have a GET_BASE_CLASS; is this a valid ComfyNode subclass?")
+        base = cls.GET_BASE_CLASS()
+    base_attr = getattr(base, name, None)
+    if base_attr is None:
+        return None
+    base_func = base_attr.__func__
+    for c in cls.mro():                       # NodeB, NodeA, ComfyNode, object …
+        if c is base:                         # reached the placeholder – we're done
+            break
+        if name in c.__dict__:                # first class that *defines* the attr
+            func = getattr(c, name).__func__
+            if func is not base_func:         # real override
+                return getattr(cls, name)     # bound to *cls*
+    return None
+
+
+class _ComfyNodeInternal:
+    """Class that all V3-based APIs inherit from for ComfyNode.
+
+    This is intended to only be referenced within execution.py, as it has to handle all V3 APIs going forward."""
+    @classmethod
+    def GET_NODE_INFO_V1(cls):
+        ...
+
+
+class _NodeOutputInternal:
+    """Class that all V3-based APIs inherit from for NodeOutput.
+
+    This is intended to only be referenced within execution.py, as it has to handle all V3 APIs going forward."""
+    ...
+
+
+def as_pruned_dict(dataclass_obj):
+    '''Return dict of dataclass object with pruned None values.'''
+    return prune_dict(asdict(dataclass_obj))
+
+def prune_dict(d: dict):
+    return {k: v for k,v in d.items() if v is not None}
+
+
+def is_class(obj):
+    '''
+    Returns True if is a class type.
+    Returns False if is a class instance.
+    '''
+    return isinstance(obj, type)
+
+
+def copy_class(cls: type) -> type:
+    '''
+    Copy a class and its attributes.
+    '''
+    if cls is None:
+        return None
+    cls_dict = {
+            k: v for k, v in cls.__dict__.items()
+            if k not in ('__dict__', '__weakref__', '__module__', '__doc__')
+        }
+    # new class
+    new_cls = type(
+        cls.__name__,
+        (cls,),
+        cls_dict
+    )
+    # metadata preservation
+    new_cls.__module__ = cls.__module__
+    new_cls.__doc__ = cls.__doc__
+    return new_cls
+
+
+class classproperty(object):
+    def __init__(self, f):
+        self.f = f
+    def __get__(self, obj, owner):
+        return self.f(owner)
+
+
+# NOTE: this was ai generated and validated by hand
+def shallow_clone_class(cls, new_name=None):
+    '''
+    Shallow clone a class while preserving super() functionality.
+    '''
+    new_name = new_name or f"{cls.__name__}Clone"
+    # Include the original class in the bases to maintain proper inheritance
+    new_bases = (cls,) + cls.__bases__
+    return type(new_name, new_bases, dict(cls.__dict__))
+
+# NOTE: this was ai generated and validated by hand
+def lock_class(cls):
+    '''
+    Lock a class so that its top-levelattributes cannot be modified.
+    '''
+    # Locked instance __setattr__
+    def locked_instance_setattr(self, name, value):
+        raise AttributeError(
+            f"Cannot set attribute '{name}' on immutable instance of {type(self).__name__}"
+        )
+    # Locked metaclass
+    class LockedMeta(type(cls)):
+        def __setattr__(cls_, name, value):
+            raise AttributeError(
+                f"Cannot modify class attribute '{name}' on locked class '{cls_.__name__}'"
+            )
+    # Rebuild class with locked behavior
+    locked_dict = dict(cls.__dict__)
+    locked_dict['__setattr__'] = locked_instance_setattr
+
+    return LockedMeta(cls.__name__, cls.__bases__, locked_dict)
+
+
+def make_locked_method_func(type_obj, func, class_clone):
+    """
+    Returns a function that, when called with **inputs, will execute:
+    getattr(type_obj, func).__func__(lock_class(class_clone), **inputs)
+
+    Supports both synchronous and asynchronous methods.
+    """
+    locked_class = lock_class(class_clone)
+    method = getattr(type_obj, func).__func__
+
+    # Check if the original method is async
+    if asyncio.iscoroutinefunction(method):
+        async def wrapped_async_func(**inputs):
+            return await method(locked_class, **inputs)
+        return wrapped_async_func
+    else:
+        def wrapped_func(**inputs):
+            return method(locked_class, **inputs)
+        return wrapped_func

comfy_api/internal/api_registry.py

@@ -0,0 +1,39 @@
+from typing import Type, List, NamedTuple
+from comfy_api.internal.singleton import ProxiedSingleton
+from packaging import version as packaging_version
+
+
+class ComfyAPIBase(ProxiedSingleton):
+    def __init__(self):
+        pass
+
+
+class ComfyAPIWithVersion(NamedTuple):
+    version: str
+    api_class: Type[ComfyAPIBase]
+
+
+def parse_version(version_str: str) -> packaging_version.Version:
+    """
+    Parses a version string into a packaging_version.Version object.
+    Raises ValueError if the version string is invalid.
+    """
+    if version_str == "latest":
+        return packaging_version.parse("9999999.9999999.9999999")
+    return packaging_version.parse(version_str)
+
+
+registered_versions: List[ComfyAPIWithVersion] = []
+
+
+def register_versions(versions: List[ComfyAPIWithVersion]):
+    versions.sort(key=lambda x: parse_version(x.version))
+    global registered_versions
+    registered_versions = versions
+
+
+def get_all_versions() -> List[ComfyAPIWithVersion]:
+    """
+    Returns a list of all registered ComfyAPI versions.
+    """
+    return registered_versions

comfy_api/internal/async_to_sync.py

@@ -0,0 +1,987 @@
+import asyncio
+import concurrent.futures
+import contextvars
+import functools
+import inspect
+import logging
+import os
+import textwrap
+import threading
+from enum import Enum
+from typing import Optional, Type, get_origin, get_args
+
+
+class TypeTracker:
+    """Tracks types discovered during stub generation for automatic import generation."""
+
+    def __init__(self):
+        self.discovered_types = {}  # type_name -> (module, qualname)
+        self.builtin_types = {
+            "Any",
+            "Dict",
+            "List",
+            "Optional",
+            "Tuple",
+            "Union",
+            "Set",
+            "Sequence",
+            "cast",
+            "NamedTuple",
+            "str",
+            "int",
+            "float",
+            "bool",
+            "None",
+            "bytes",
+            "object",
+            "type",
+            "dict",
+            "list",
+            "tuple",
+            "set",
+        }
+        self.already_imported = (
+            set()
+        )  # Track types already imported to avoid duplicates
+
+    def track_type(self, annotation):
+        """Track a type annotation and record its module/import info."""
+        if annotation is None or annotation is type(None):
+            return
+
+        # Skip builtins and typing module types we already import
+        type_name = getattr(annotation, "__name__", None)
+        if type_name and (
+            type_name in self.builtin_types or type_name in self.already_imported
+        ):
+            return
+
+        # Get module and qualname
+        module = getattr(annotation, "__module__", None)
+        qualname = getattr(annotation, "__qualname__", type_name or "")
+
+        # Skip types from typing module (they're already imported)
+        if module == "typing":
+            return
+
+        # Skip UnionType and GenericAlias from types module as they're handled specially
+        if module == "types" and type_name in ("UnionType", "GenericAlias"):
+            return
+
+        if module and module not in ["builtins", "__main__"]:
+            # Store the type info
+            if type_name:
+                self.discovered_types[type_name] = (module, qualname)
+
+    def get_imports(self, main_module_name: str) -> list[str]:
+        """Generate import statements for all discovered types."""
+        imports = []
+        imports_by_module = {}
+
+        for type_name, (module, qualname) in sorted(self.discovered_types.items()):
+            # Skip types from the main module (they're already imported)
+            if main_module_name and module == main_module_name:
+                continue
+
+            if module not in imports_by_module:
+                imports_by_module[module] = []
+            if type_name not in imports_by_module[module]:  # Avoid duplicates
+                imports_by_module[module].append(type_name)
+
+        # Generate import statements
+        for module, types in sorted(imports_by_module.items()):
+            if len(types) == 1:
+                imports.append(f"from {module} import {types[0]}")
+            else:
+                imports.append(f"from {module} import {', '.join(sorted(set(types)))}")
+
+        return imports
+
+
+class AsyncToSyncConverter:
+    """
+    Provides utilities to convert async classes to sync classes with proper type hints.
+    """
+
+    _thread_pool: Optional[concurrent.futures.ThreadPoolExecutor] = None
+    _thread_pool_lock = threading.Lock()
+    _thread_pool_initialized = False
+
+    @classmethod
+    def get_thread_pool(cls, max_workers=None) -> concurrent.futures.ThreadPoolExecutor:
+        """Get or create the shared thread pool with proper thread-safe initialization."""
+        # Fast path - check if already initialized without acquiring lock
+        if cls._thread_pool_initialized:
+            assert cls._thread_pool is not None, "Thread pool should be initialized"
+            return cls._thread_pool
+
+        # Slow path - acquire lock and create pool if needed
+        with cls._thread_pool_lock:
+            if not cls._thread_pool_initialized:
+                cls._thread_pool = concurrent.futures.ThreadPoolExecutor(
+                    max_workers=max_workers, thread_name_prefix="async_to_sync_"
+                )
+                cls._thread_pool_initialized = True
+
+        # This should never be None at this point, but add assertion for type checker
+        assert cls._thread_pool is not None
+        return cls._thread_pool
+
+    @classmethod
+    def run_async_in_thread(cls, coro_func, *args, **kwargs):
+        """
+        Run an async function in a separate thread from the thread pool.
+        Blocks until the async function completes.
+        Properly propagates contextvars between threads and manages event loops.
+        """
+        # Capture current context - this includes all context variables
+        context = contextvars.copy_context()
+
+        # Store the result and any exception that occurs
+        result_container: dict = {"result": None, "exception": None}
+
+        # Function that runs in the thread pool
+        def run_in_thread():
+            # Create new event loop for this thread
+            loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(loop)
+
+            try:
+                # Create the coroutine within the context
+                async def run_with_context():
+                    # The coroutine function might access context variables
+                    return await coro_func(*args, **kwargs)
+
+                # Run the coroutine with the captured context
+                # This ensures all context variables are available in the async function
+                result = context.run(loop.run_until_complete, run_with_context())
+                result_container["result"] = result
+            except Exception as e:
+                # Store the exception to re-raise in the calling thread
+                result_container["exception"] = e
+            finally:
+                # Ensure event loop is properly closed to prevent warnings
+                try:
+                    # Cancel any remaining tasks
+                    pending = asyncio.all_tasks(loop)
+                    for task in pending:
+                        task.cancel()
+
+                    # Run the loop briefly to handle cancellations
+                    if pending:
+                        loop.run_until_complete(
+                            asyncio.gather(*pending, return_exceptions=True)
+                        )
+                except Exception:
+                    pass  # Ignore errors during cleanup
+
+                # Close the event loop
+                loop.close()
+
+                # Clear the event loop from the thread
+                asyncio.set_event_loop(None)
+
+        # Submit to thread pool and wait for result
+        thread_pool = cls.get_thread_pool()
+        future = thread_pool.submit(run_in_thread)
+        future.result()  # Wait for completion
+
+        # Re-raise any exception that occurred in the thread
+        if result_container["exception"] is not None:
+            raise result_container["exception"]
+
+        return result_container["result"]
+
+    @classmethod
+    def create_sync_class(cls, async_class: Type, thread_pool_size=10) -> Type:
+        """
+        Creates a new class with synchronous versions of all async methods.
+
+        Args:
+            async_class: The async class to convert
+            thread_pool_size: Size of thread pool to use
+
+        Returns:
+            A new class with sync versions of all async methods
+        """
+        sync_class_name = "ComfyAPISyncStub"
+        cls.get_thread_pool(thread_pool_size)
+
+        # Create a proper class with docstrings and proper base classes
+        sync_class_dict = {
+            "__doc__": async_class.__doc__,
+            "__module__": async_class.__module__,
+            "__qualname__": sync_class_name,
+            "__orig_class__": async_class,  # Store original class for typing references
+        }
+
+        # Create __init__ method
+        def __init__(self, *args, **kwargs):
+            self._async_instance = async_class(*args, **kwargs)
+
+            # Handle annotated class attributes (like execution: Execution)
+            # Get all annotations from the class hierarchy
+            all_annotations = {}
+            for base_class in reversed(inspect.getmro(async_class)):
+                if hasattr(base_class, "__annotations__"):
+                    all_annotations.update(base_class.__annotations__)
+
+            # For each annotated attribute, check if it needs to be created or wrapped
+            for attr_name, attr_type in all_annotations.items():
+                if hasattr(self._async_instance, attr_name):
+                    # Attribute exists on the instance
+                    attr = getattr(self._async_instance, attr_name)
+                    # Check if this attribute needs a sync wrapper
+                    if hasattr(attr, "__class__"):
+                        from comfy_api.internal.singleton import ProxiedSingleton
+
+                        if isinstance(attr, ProxiedSingleton):
+                            # Create a sync version of this attribute
+                            try:
+                                sync_attr_class = cls.create_sync_class(attr.__class__)
+                                # Create instance of the sync wrapper with the async instance
+                                sync_attr = object.__new__(sync_attr_class)  # type: ignore
+                                sync_attr._async_instance = attr
+                                setattr(self, attr_name, sync_attr)
+                            except Exception:
+                                # If we can't create a sync version, keep the original
+                                setattr(self, attr_name, attr)
+                        else:
+                            # Not async, just copy the reference
+                            setattr(self, attr_name, attr)
+                else:
+                    # Attribute doesn't exist, but is annotated - create it
+                    # This handles cases like execution: Execution
+                    if isinstance(attr_type, type):
+                        # Check if the type is defined as an inner class
+                        if hasattr(async_class, attr_type.__name__):
+                            inner_class = getattr(async_class, attr_type.__name__)
+                            from comfy_api.internal.singleton import ProxiedSingleton
+
+                            # Create an instance of the inner class
+                            try:
+                                # For ProxiedSingleton classes, get or create the singleton instance
+                                if issubclass(inner_class, ProxiedSingleton):
+                                    async_instance = inner_class.get_instance()
+                                else:
+                                    async_instance = inner_class()
+
+                                # Create sync wrapper
+                                sync_attr_class = cls.create_sync_class(inner_class)
+                                sync_attr = object.__new__(sync_attr_class)  # type: ignore
+                                sync_attr._async_instance = async_instance
+                                setattr(self, attr_name, sync_attr)
+                                # Also set on the async instance for consistency
+                                setattr(self._async_instance, attr_name, async_instance)
+                            except Exception as e:
+                                logging.warning(
+                                    f"Failed to create instance for {attr_name}: {e}"
+                                )
+
+            # Handle other instance attributes that might not be annotated
+            for name, attr in inspect.getmembers(self._async_instance):
+                if name.startswith("_") or hasattr(self, name):
+                    continue
+
+                # If attribute is an instance of a class, and that class is defined in the original class
+                # we need to check if it needs a sync wrapper
+                if isinstance(attr, object) and not isinstance(
+                    attr, (str, int, float, bool, list, dict, tuple)
+                ):
+                    from comfy_api.internal.singleton import ProxiedSingleton
+
+                    if isinstance(attr, ProxiedSingleton):
+                        # Create a sync version of this nested class
+                        try:
+                            sync_attr_class = cls.create_sync_class(attr.__class__)
+                            # Create instance of the sync wrapper with the async instance
+                            sync_attr = object.__new__(sync_attr_class)  # type: ignore
+                            sync_attr._async_instance = attr
+                            setattr(self, name, sync_attr)
+                        except Exception:
+                            # If we can't create a sync version, keep the original
+                            setattr(self, name, attr)
+
+        sync_class_dict["__init__"] = __init__
+
+        # Process methods from the async class
+        for name, method in inspect.getmembers(
+            async_class, predicate=inspect.isfunction
+        ):
+            if name.startswith("_"):
+                continue
+
+            # Extract the actual return type from a coroutine
+            if inspect.iscoroutinefunction(method):
+                # Create sync version of async method with proper signature
+                @functools.wraps(method)
+                def sync_method(self, *args, _method_name=name, **kwargs):
+                    async_method = getattr(self._async_instance, _method_name)
+                    return AsyncToSyncConverter.run_async_in_thread(
+                        async_method, *args, **kwargs
+                    )
+
+                # Add to the class dict
+                sync_class_dict[name] = sync_method
+            else:
+                # For regular methods, create a proxy method
+                @functools.wraps(method)
+                def proxy_method(self, *args, _method_name=name, **kwargs):
+                    method = getattr(self._async_instance, _method_name)
+                    return method(*args, **kwargs)
+
+                # Add to the class dict
+                sync_class_dict[name] = proxy_method
+
+        # Handle property access
+        for name, prop in inspect.getmembers(
+            async_class, lambda x: isinstance(x, property)
+        ):
+
+            def make_property(name, prop_obj):
+                def getter(self):
+                    value = getattr(self._async_instance, name)
+                    if inspect.iscoroutinefunction(value):
+
+                        def sync_fn(*args, **kwargs):
+                            return AsyncToSyncConverter.run_async_in_thread(
+                                value, *args, **kwargs
+                            )
+
+                        return sync_fn
+                    return value
+
+                def setter(self, value):
+                    setattr(self._async_instance, name, value)
+
+                return property(getter, setter if prop_obj.fset else None)
+
+            sync_class_dict[name] = make_property(name, prop)
+
+        # Create the class
+        sync_class = type(sync_class_name, (object,), sync_class_dict)
+
+        return sync_class
+
+    @classmethod
+    def _format_type_annotation(
+        cls, annotation, type_tracker: Optional[TypeTracker] = None
+    ) -> str:
+        """Convert a type annotation to its string representation for stub files."""
+        if (
+            annotation is inspect.Parameter.empty
+            or annotation is inspect.Signature.empty
+        ):
+            return "Any"
+
+        # Handle None type
+        if annotation is type(None):
+            return "None"
+
+        # Track the type if we have a tracker
+        if type_tracker:
+            type_tracker.track_type(annotation)
+
+        # Try using typing.get_origin/get_args for Python 3.8+
+        try:
+            origin = get_origin(annotation)
+            args = get_args(annotation)
+
+            if origin is not None:
+                # Track the origin type
+                if type_tracker:
+                    type_tracker.track_type(origin)
+
+                # Get the origin name
+                origin_name = getattr(origin, "__name__", str(origin))
+                if "." in origin_name:
+                    origin_name = origin_name.split(".")[-1]
+
+                # Special handling for types.UnionType (Python 3.10+ pipe operator)
+                # Convert to old-style Union for compatibility
+                if str(origin) == "<class 'types.UnionType'>" or origin_name == "UnionType":
+                    origin_name = "Union"
+
+                # Format arguments recursively
+                if args:
+                    formatted_args = []
+                    for arg in args:
+                        # Track each type in the union
+                        if type_tracker:
+                            type_tracker.track_type(arg)
+                        formatted_args.append(cls._format_type_annotation(arg, type_tracker))
+                    return f"{origin_name}[{', '.join(formatted_args)}]"
+                else:
+                    return origin_name
+        except (AttributeError, TypeError):
+            # Fallback for older Python versions or non-generic types
+            pass
+
+        # Handle generic types the old way for compatibility
+        if hasattr(annotation, "__origin__") and hasattr(annotation, "__args__"):
+            origin = annotation.__origin__
+            origin_name = (
+                origin.__name__
+                if hasattr(origin, "__name__")
+                else str(origin).split("'")[1]
+            )
+
+            # Format each type argument
+            args = []
+            for arg in annotation.__args__:
+                args.append(cls._format_type_annotation(arg, type_tracker))
+
+            return f"{origin_name}[{', '.join(args)}]"
+
+        # Handle regular types with __name__
+        if hasattr(annotation, "__name__"):
+            return annotation.__name__
+
+        # Handle special module types (like types from typing module)
+        if hasattr(annotation, "__module__") and hasattr(annotation, "__qualname__"):
+            # For types like typing.Literal, typing.TypedDict, etc.
+            return annotation.__qualname__
+
+        # Last resort: string conversion with cleanup
+        type_str = str(annotation)
+
+        # Clean up common patterns more robustly
+        if type_str.startswith("<class '") and type_str.endswith("'>"):
+            type_str = type_str[8:-2]  # Remove "<class '" and "'>"
+
+        # Remove module prefixes for common modules
+        for prefix in ["typing.", "builtins.", "types."]:
+            if type_str.startswith(prefix):
+                type_str = type_str[len(prefix) :]
+
+        # Handle special cases
+        if type_str in ("_empty", "inspect._empty"):
+            return "None"
+
+        # Fix NoneType (this should rarely be needed now)
+        if type_str == "NoneType":
+            return "None"
+
+        return type_str
+
+    @classmethod
+    def _extract_coroutine_return_type(cls, annotation):
+        """Extract the actual return type from a Coroutine annotation."""
+        if hasattr(annotation, "__args__") and len(annotation.__args__) > 2:
+            # Coroutine[Any, Any, ReturnType] -> extract ReturnType
+            return annotation.__args__[2]
+        return annotation
+
+    @classmethod
+    def _format_parameter_default(cls, default_value) -> str:
+        """Format a parameter's default value for stub files."""
+        if default_value is inspect.Parameter.empty:
+            return ""
+        elif default_value is None:
+            return " = None"
+        elif isinstance(default_value, bool):
+            return f" = {default_value}"
+        elif default_value == {}:
+            return " = {}"
+        elif default_value == []:
+            return " = []"
+        else:
+            return f" = {default_value}"
+
+    @classmethod
+    def _format_method_parameters(
+        cls,
+        sig: inspect.Signature,
+        skip_self: bool = True,
+        type_hints: Optional[dict] = None,
+        type_tracker: Optional[TypeTracker] = None,
+    ) -> str:
+        """Format method parameters for stub files."""
+        params = []
+        if type_hints is None:
+            type_hints = {}
+
+        for i, (param_name, param) in enumerate(sig.parameters.items()):
+            if i == 0 and param_name == "self" and skip_self:
+                params.append("self")
+            else:
+                # Get type annotation from type hints if available, otherwise from signature
+                annotation = type_hints.get(param_name, param.annotation)
+                type_str = cls._format_type_annotation(annotation, type_tracker)
+
+                # Get default value
+                default_str = cls._format_parameter_default(param.default)
+
+                # Combine parameter parts
+                if annotation is inspect.Parameter.empty:
+                    params.append(f"{param_name}: Any{default_str}")
+                else:
+                    params.append(f"{param_name}: {type_str}{default_str}")
+
+        return ", ".join(params)
+
+    @classmethod
+    def _generate_method_signature(
+        cls,
+        method_name: str,
+        method,
+        is_async: bool = False,
+        type_tracker: Optional[TypeTracker] = None,
+    ) -> str:
+        """Generate a complete method signature for stub files."""
+        sig = inspect.signature(method)
+
+        # Try to get evaluated type hints to resolve string annotations
+        try:
+            from typing import get_type_hints
+            type_hints = get_type_hints(method)
+        except Exception:
+            # Fallback to empty dict if we can't get type hints
+            type_hints = {}
+
+        # For async methods, extract the actual return type
+        return_annotation = type_hints.get('return', sig.return_annotation)
+        if is_async and inspect.iscoroutinefunction(method):
+            return_annotation = cls._extract_coroutine_return_type(return_annotation)
+
+        # Format parameters with type hints
+        params_str = cls._format_method_parameters(sig, type_hints=type_hints, type_tracker=type_tracker)
+
+        # Format return type
+        return_type = cls._format_type_annotation(return_annotation, type_tracker)
+        if return_annotation is inspect.Signature.empty:
+            return_type = "None"
+
+        return f"def {method_name}({params_str}) -> {return_type}: ..."
+
+    @classmethod
+    def _generate_imports(
+        cls, async_class: Type, type_tracker: TypeTracker
+    ) -> list[str]:
+        """Generate import statements for the stub file."""
+        imports = []
+
+        # Add standard typing imports
+        imports.append(
+            "from typing import Any, Dict, List, Optional, Tuple, Union, Set, Sequence, cast, NamedTuple"
+        )
+
+        # Add imports from the original module
+        if async_class.__module__ != "builtins":
+            module = inspect.getmodule(async_class)
+            additional_types = []
+
+            if module:
+                # Check if module has __all__ defined
+                module_all = getattr(module, "__all__", None)
+
+                for name, obj in sorted(inspect.getmembers(module)):
+                    if isinstance(obj, type):
+                        # Skip if __all__ is defined and this name isn't in it
+                        # unless it's already been tracked as used in type annotations
+                        if module_all is not None and name not in module_all:
+                            # Check if this type was actually used in annotations
+                            if name not in type_tracker.discovered_types:
+                                continue
+
+                        # Check for NamedTuple
+                        if issubclass(obj, tuple) and hasattr(obj, "_fields"):
+                            additional_types.append(name)
+                            # Mark as already imported
+                            type_tracker.already_imported.add(name)
+                        # Check for Enum
+                        elif issubclass(obj, Enum) and name != "Enum":
+                            additional_types.append(name)
+                            # Mark as already imported
+                            type_tracker.already_imported.add(name)
+
+            if additional_types:
+                type_imports = ", ".join([async_class.__name__] + additional_types)
+                imports.append(f"from {async_class.__module__} import {type_imports}")
+            else:
+                imports.append(
+                    f"from {async_class.__module__} import {async_class.__name__}"
+                )
+
+        # Add imports for all discovered types
+        # Pass the main module name to avoid duplicate imports
+        imports.extend(
+            type_tracker.get_imports(main_module_name=async_class.__module__)
+        )
+
+        # Add base module import if needed
+        if hasattr(inspect.getmodule(async_class), "__name__"):
+            module_name = inspect.getmodule(async_class).__name__
+            if "." in module_name:
+                base_module = module_name.split(".")[0]
+                # Only add if not already importing from it
+                if not any(imp.startswith(f"from {base_module}") for imp in imports):
+                    imports.append(f"import {base_module}")
+
+        return imports
+
+    @classmethod
+    def _get_class_attributes(cls, async_class: Type) -> list[tuple[str, Type]]:
+        """Extract class attributes that are classes themselves."""
+        class_attributes = []
+
+        # Look for class attributes that are classes
+        for name, attr in sorted(inspect.getmembers(async_class)):
+            if isinstance(attr, type) and not name.startswith("_"):
+                class_attributes.append((name, attr))
+            elif (
+                hasattr(async_class, "__annotations__")
+                and name in async_class.__annotations__
+            ):
+                annotation = async_class.__annotations__[name]
+                if isinstance(annotation, type):
+                    class_attributes.append((name, annotation))
+
+        return class_attributes
+
+    @classmethod
+    def _generate_inner_class_stub(
+        cls,
+        name: str,
+        attr: Type,
+        indent: str = "    ",
+        type_tracker: Optional[TypeTracker] = None,
+    ) -> list[str]:
+        """Generate stub for an inner class."""
+        stub_lines = []
+        stub_lines.append(f"{indent}class {name}Sync:")
+
+        # Add docstring if available
+        if hasattr(attr, "__doc__") and attr.__doc__:
+            stub_lines.extend(
+                cls._format_docstring_for_stub(attr.__doc__, f"{indent}    ")
+            )
+
+        # Add __init__ if it exists
+        if hasattr(attr, "__init__"):
+            try:
+                init_method = getattr(attr, "__init__")
+                init_sig = inspect.signature(init_method)
+
+                # Try to get type hints
+                try:
+                    from typing import get_type_hints
+                    init_hints = get_type_hints(init_method)
+                except Exception:
+                    init_hints = {}
+
+                # Format parameters
+                params_str = cls._format_method_parameters(
+                    init_sig, type_hints=init_hints, type_tracker=type_tracker
+                )
+                # Add __init__ docstring if available (before the method)
+                if hasattr(init_method, "__doc__") and init_method.__doc__:
+                    stub_lines.extend(
+                        cls._format_docstring_for_stub(
+                            init_method.__doc__, f"{indent}    "
+                        )
+                    )
+                stub_lines.append(
+                    f"{indent}    def __init__({params_str}) -> None: ..."
+                )
+            except (ValueError, TypeError):
+                stub_lines.append(
+                    f"{indent}    def __init__(self, *args, **kwargs) -> None: ..."
+                )
+
+        # Add methods to the inner class
+        has_methods = False
+        for method_name, method in sorted(
+            inspect.getmembers(attr, predicate=inspect.isfunction)
+        ):
+            if method_name.startswith("_"):
+                continue
+
+            has_methods = True
+            try:
+                # Add method docstring if available (before the method signature)
+                if method.__doc__:
+                    stub_lines.extend(
+                        cls._format_docstring_for_stub(method.__doc__, f"{indent}    ")
+                    )
+
+                method_sig = cls._generate_method_signature(
+                    method_name, method, is_async=True, type_tracker=type_tracker
+                )
+                stub_lines.append(f"{indent}    {method_sig}")
+            except (ValueError, TypeError):
+                stub_lines.append(
+                    f"{indent}    def {method_name}(self, *args, **kwargs): ..."
+                )
+
+        if not has_methods:
+            stub_lines.append(f"{indent}    pass")
+
+        return stub_lines
+
+    @classmethod
+    def _format_docstring_for_stub(
+        cls, docstring: str, indent: str = "    "
+    ) -> list[str]:
+        """Format a docstring for inclusion in a stub file with proper indentation."""
+        if not docstring:
+            return []
+
+        # First, dedent the docstring to remove any existing indentation
+        dedented = textwrap.dedent(docstring).strip()
+
+        # Split into lines
+        lines = dedented.split("\n")
+
+        # Build the properly indented docstring
+        result = []
+        result.append(f'{indent}"""')
+
+        for line in lines:
+            if line.strip():  # Non-empty line
+                result.append(f"{indent}{line}")
+            else:  # Empty line
+                result.append("")
+
+        result.append(f'{indent}"""')
+        return result
+
+    @classmethod
+    def _post_process_stub_content(cls, stub_content: list[str]) -> list[str]:
+        """Post-process stub content to fix any remaining issues."""
+        processed = []
+
+        for line in stub_content:
+            # Skip processing imports
+            if line.startswith(("from ", "import ")):
+                processed.append(line)
+                continue
+
+            # Fix method signatures missing return types
+            if (
+                line.strip().startswith("def ")
+                and line.strip().endswith(": ...")
+                and ") -> " not in line
+            ):
+                # Add -> None for methods without return annotation
+                line = line.replace(": ...", " -> None: ...")
+
+            processed.append(line)
+
+        return processed
+
+    @classmethod
+    def generate_stub_file(cls, async_class: Type, sync_class: Type) -> None:
+        """
+        Generate a .pyi stub file for the sync class to help IDEs with type checking.
+        """
+        try:
+            # Only generate stub if we can determine module path
+            if async_class.__module__ == "__main__":
+                return
+
+            module = inspect.getmodule(async_class)
+            if not module:
+                return
+
+            module_path = module.__file__
+            if not module_path:
+                return
+
+            # Create stub file path in a 'generated' subdirectory
+            module_dir = os.path.dirname(module_path)
+            stub_dir = os.path.join(module_dir, "generated")
+
+            # Ensure the generated directory exists
+            os.makedirs(stub_dir, exist_ok=True)
+
+            module_name = os.path.basename(module_path)
+            if module_name.endswith(".py"):
+                module_name = module_name[:-3]
+
+            sync_stub_path = os.path.join(stub_dir, f"{sync_class.__name__}.pyi")
+
+            # Create a type tracker for this stub generation
+            type_tracker = TypeTracker()
+
+            stub_content = []
+
+            # We'll generate imports after processing all methods to capture all types
+            # Leave a placeholder for imports
+            imports_placeholder_index = len(stub_content)
+            stub_content.append("")  # Will be replaced with imports later
+
+            # Class definition
+            stub_content.append(f"class {sync_class.__name__}:")
+
+            # Docstring
+            if async_class.__doc__:
+                stub_content.extend(
+                    cls._format_docstring_for_stub(async_class.__doc__, "    ")
+                )
+
+            # Generate __init__
+            try:
+                init_method = async_class.__init__
+                init_signature = inspect.signature(init_method)
+
+                # Try to get type hints for __init__
+                try:
+                    from typing import get_type_hints
+                    init_hints = get_type_hints(init_method)
+                except Exception:
+                    init_hints = {}
+
+                # Format parameters
+                params_str = cls._format_method_parameters(
+                    init_signature, type_hints=init_hints, type_tracker=type_tracker
+                )
+                # Add __init__ docstring if available (before the method)
+                if hasattr(init_method, "__doc__") and init_method.__doc__:
+                    stub_content.extend(
+                        cls._format_docstring_for_stub(init_method.__doc__, "    ")
+                    )
+                stub_content.append(f"    def __init__({params_str}) -> None: ...")
+            except (ValueError, TypeError):
+                stub_content.append(
+                    "    def __init__(self, *args, **kwargs) -> None: ..."
+                )
+
+            stub_content.append("")  # Add newline after __init__
+
+            # Get class attributes
+            class_attributes = cls._get_class_attributes(async_class)
+
+            # Generate inner classes
+            for name, attr in class_attributes:
+                inner_class_stub = cls._generate_inner_class_stub(
+                    name, attr, type_tracker=type_tracker
+                )
+                stub_content.extend(inner_class_stub)
+                stub_content.append("")  # Add newline after the inner class
+
+            # Add methods to the main class
+            processed_methods = set()  # Keep track of methods we've processed
+            for name, method in sorted(
+                inspect.getmembers(async_class, predicate=inspect.isfunction)
+            ):
+                if name.startswith("_") or name in processed_methods:
+                    continue
+
+                processed_methods.add(name)
+
+                try:
+                    method_sig = cls._generate_method_signature(
+                        name, method, is_async=True, type_tracker=type_tracker
+                    )
+
+                    # Add docstring if available (before the method signature for proper formatting)
+                    if method.__doc__:
+                        stub_content.extend(
+                            cls._format_docstring_for_stub(method.__doc__, "    ")
+                        )
+
+                    stub_content.append(f"    {method_sig}")
+
+                    stub_content.append("")  # Add newline after each method
+
+                except (ValueError, TypeError):
+                    # If we can't get the signature, just add a simple stub
+                    stub_content.append(f"    def {name}(self, *args, **kwargs): ...")
+                    stub_content.append("")  # Add newline
+
+            # Add properties
+            for name, prop in sorted(
+                inspect.getmembers(async_class, lambda x: isinstance(x, property))
+            ):
+                stub_content.append("    @property")
+                stub_content.append(f"    def {name}(self) -> Any: ...")
+                if prop.fset:
+                    stub_content.append(f"    @{name}.setter")
+                    stub_content.append(
+                        f"    def {name}(self, value: Any) -> None: ..."
+                    )
+                stub_content.append("")  # Add newline after each property
+
+            # Add placeholders for the nested class instances
+            # Check the actual attribute names from class annotations and attributes
+            attribute_mappings = {}
+
+            # First check annotations for typed attributes (including from parent classes)
+            # Collect all annotations from the class hierarchy
+            all_annotations = {}
+            for base_class in reversed(inspect.getmro(async_class)):
+                if hasattr(base_class, "__annotations__"):
+                    all_annotations.update(base_class.__annotations__)
+
+            for attr_name, attr_type in sorted(all_annotations.items()):
+                for class_name, class_type in class_attributes:
+                    # If the class type matches the annotated type
+                    if (
+                        attr_type == class_type
+                        or (hasattr(attr_type, "__name__") and attr_type.__name__ == class_name)
+                        or (isinstance(attr_type, str) and attr_type == class_name)
+                    ):
+                        attribute_mappings[class_name] = attr_name
+
+            # Remove the extra checking - annotations should be sufficient
+
+            # Add the attribute declarations with proper names
+            for class_name, class_type in class_attributes:
+                # Check if there's a mapping from annotation
+                attr_name = attribute_mappings.get(class_name, class_name)
+                # Use the annotation name if it exists, even if the attribute doesn't exist yet
+                # This is because the attribute might be created at runtime
+                stub_content.append(f"    {attr_name}: {class_name}Sync")
+
+            stub_content.append("")  # Add a final newline
+
+            # Now generate imports with all discovered types
+            imports = cls._generate_imports(async_class, type_tracker)
+
+            # Deduplicate imports while preserving order
+            seen = set()
+            unique_imports = []
+            for imp in imports:
+                if imp not in seen:
+                    seen.add(imp)
+                    unique_imports.append(imp)
+                else:
+                    logging.warning(f"Duplicate import detected: {imp}")
+
+            # Replace the placeholder with actual imports
+            stub_content[imports_placeholder_index : imports_placeholder_index + 1] = (
+                unique_imports
+            )
+
+            # Post-process stub content
+            stub_content = cls._post_process_stub_content(stub_content)
+
+            # Write stub file
+            with open(sync_stub_path, "w") as f:
+                f.write("\n".join(stub_content))
+
+            logging.info(f"Generated stub file: {sync_stub_path}")
+
+        except Exception as e:
+            # If stub generation fails, log the error but don't break the main functionality
+            logging.error(
+                f"Error generating stub file for {sync_class.__name__}: {str(e)}"
+            )
+            import traceback
+
+            logging.error(traceback.format_exc())
+
+
+def create_sync_class(async_class: Type, thread_pool_size=10) -> Type:
+    """
+    Creates a sync version of an async class
+
+    Args:
+        async_class: The async class to convert
+        thread_pool_size: Size of thread pool to use
+
+    Returns:
+        A new class with sync versions of all async methods
+    """
+    return AsyncToSyncConverter.create_sync_class(async_class, thread_pool_size)

comfy_api/internal/singleton.py

@@ -0,0 +1,33 @@
+from typing import Type, TypeVar
+
+class SingletonMetaclass(type):
+    T = TypeVar("T", bound="SingletonMetaclass")
+    _instances = {}
+
+    def __call__(cls, *args, **kwargs):
+        if cls not in cls._instances:
+            cls._instances[cls] = super(SingletonMetaclass, cls).__call__(
+                *args, **kwargs
+            )
+        return cls._instances[cls]
+
+    def inject_instance(cls: Type[T], instance: T) -> None:
+        assert cls not in SingletonMetaclass._instances, (
+            "Cannot inject instance after first instantiation"
+        )
+        SingletonMetaclass._instances[cls] = instance
+
+    def get_instance(cls: Type[T], *args, **kwargs) -> T:
+        """
+        Gets the singleton instance of the class, creating it if it doesn't exist.
+        """
+        if cls not in SingletonMetaclass._instances:
+            SingletonMetaclass._instances[cls] = super(
+                SingletonMetaclass, cls
+            ).__call__(*args, **kwargs)
+        return cls._instances[cls]
+
+
+class ProxiedSingleton(object, metaclass=SingletonMetaclass):
+    def __init__(self):
+        super().__init__()

comfy_api/latest/__init__.py

@@ -0,0 +1,109 @@
+from __future__ import annotations
+
+from typing import Type, TYPE_CHECKING
+from comfy_api.internal import ComfyAPIBase
+from comfy_api.internal.singleton import ProxiedSingleton
+from comfy_api.internal.async_to_sync import create_sync_class
+from comfy_api.latest._input import ImageInput, AudioInput, MaskInput, LatentInput, VideoInput
+from comfy_api.latest._input_impl import VideoFromFile, VideoFromComponents
+from comfy_api.latest._util import VideoCodec, VideoContainer, VideoComponents
+from comfy_api.latest._io import _IO as io  #noqa: F401
+from comfy_api.latest._ui import _UI as ui  #noqa: F401
+from comfy_api.latest._resources import _RESOURCES as resources  #noqa: F401
+from comfy_execution.utils import get_executing_context
+from comfy_execution.progress import get_progress_state, PreviewImageTuple
+from PIL import Image
+from comfy.cli_args import args
+import numpy as np
+
+
+class ComfyAPI_latest(ComfyAPIBase):
+    VERSION = "latest"
+    STABLE = False
+
+    class Execution(ProxiedSingleton):
+        async def set_progress(
+            self,
+            value: float,
+            max_value: float,
+            node_id: str | None = None,
+            preview_image: Image.Image | ImageInput | None = None,
+            ignore_size_limit: bool = False,
+        ) -> None:
+            """
+            Update the progress bar displayed in the ComfyUI interface.
+
+            This function allows custom nodes and API calls to report their progress
+            back to the user interface, providing visual feedback during long operations.
+
+            Migration from previous API: comfy.utils.PROGRESS_BAR_HOOK
+            """
+            executing_context = get_executing_context()
+            if node_id is None and executing_context is not None:
+                node_id = executing_context.node_id
+            if node_id is None:
+                raise ValueError("node_id must be provided if not in executing context")
+
+            # Convert preview_image to PreviewImageTuple if needed
+            to_display: PreviewImageTuple | Image.Image | ImageInput | None = preview_image
+            if to_display is not None:
+                # First convert to PIL Image if needed
+                if isinstance(to_display, ImageInput):
+                    # Convert ImageInput (torch.Tensor) to PIL Image
+                    # Handle tensor shape [B, H, W, C] -> get first image if batch
+                    tensor = to_display
+                    if len(tensor.shape) == 4:
+                        tensor = tensor[0]
+
+                    # Convert to numpy array and scale to 0-255
+                    image_np = (tensor.cpu().numpy() * 255).astype(np.uint8)
+                    to_display = Image.fromarray(image_np)
+
+                if isinstance(to_display, Image.Image):
+                    # Detect image format from PIL Image
+                    image_format = to_display.format if to_display.format else "JPEG"
+                    # Use None for preview_size if ignore_size_limit is True
+                    preview_size = None if ignore_size_limit else args.preview_size
+                    to_display = (image_format, to_display, preview_size)
+
+            get_progress_state().update_progress(
+                node_id=node_id,
+                value=value,
+                max_value=max_value,
+                image=to_display,
+            )
+
+    execution: Execution
+
+class Input:
+    Image = ImageInput
+    Audio = AudioInput
+    Mask = MaskInput
+    Latent = LatentInput
+    Video = VideoInput
+
+class InputImpl:
+    VideoFromFile = VideoFromFile
+    VideoFromComponents = VideoFromComponents
+
+class Types:
+    VideoCodec = VideoCodec
+    VideoContainer = VideoContainer
+    VideoComponents = VideoComponents
+
+ComfyAPI = ComfyAPI_latest
+
+# Create a synchronous version of the API
+if TYPE_CHECKING:
+    import comfy_api.latest.generated.ComfyAPISyncStub  # type: ignore
+
+    ComfyAPISync: Type[comfy_api.latest.generated.ComfyAPISyncStub.ComfyAPISyncStub]
+ComfyAPISync = create_sync_class(ComfyAPI_latest)
+
+__all__ = [
+    "ComfyAPI",
+    "ComfyAPISync",
+    "Input",
+    "InputImpl",
+    "Types",
+]

comfy_api/latest/_input/__init__.py

@@ -0,0 +1,10 @@
+from .basic_types import ImageInput, AudioInput, MaskInput, LatentInput
+from .video_types import VideoInput
+
+__all__ = [
+    "ImageInput",
+    "AudioInput",
+    "VideoInput",
+    "MaskInput",
+    "LatentInput",
+]

comfy_api/latest/_input/basic_types.py

@@ -0,0 +1,42 @@
+import torch
+from typing import TypedDict, List, Optional
+
+ImageInput = torch.Tensor
+"""
+An image in format [B, H, W, C] where B is the batch size, C is the number of channels,
+"""
+
+MaskInput = torch.Tensor
+"""
+A mask in format [B, H, W] where B is the batch size
+"""
+
+class AudioInput(TypedDict):
+    """
+    TypedDict representing audio input.
+    """
+
+    waveform: torch.Tensor
+    """
+    Tensor in the format [B, C, T] where B is the batch size, C is the number of channels,
+    """
+
+    sample_rate: int
+
+class LatentInput(TypedDict):
+    """
+    TypedDict representing latent input.
+    """
+
+    samples: torch.Tensor
+    """
+    Tensor in the format [B, C, H, W] where B is the batch size, C is the number of channels,
+    H is the height, and W is the width.
+    """
+
+    noise_mask: Optional[MaskInput]
+    """
+    Optional noise mask tensor in the same format as samples.
+    """
+
+    batch_index: Optional[List[int]]

comfy_api/latest/_input/video_types.py

@@ -0,0 +1,85 @@
+from __future__ import annotations
+from abc import ABC, abstractmethod
+from typing import Optional, Union
+import io
+import av
+from comfy_api.util import VideoContainer, VideoCodec, VideoComponents
+
+class VideoInput(ABC):
+    """
+    Abstract base class for video input types.
+    """
+
+    @abstractmethod
+    def get_components(self) -> VideoComponents:
+        """
+        Abstract method to get the video components (images, audio, and frame rate).
+
+        Returns:
+            VideoComponents containing images, audio, and frame rate
+        """
+        pass
+
+    @abstractmethod
+    def save_to(
+        self,
+        path: str,
+        format: VideoContainer = VideoContainer.AUTO,
+        codec: VideoCodec = VideoCodec.AUTO,
+        metadata: Optional[dict] = None
+    ):
+        """
+        Abstract method to save the video input to a file.
+        """
+        pass
+
+    def get_stream_source(self) -> Union[str, io.BytesIO]:
+        """
+        Get a streamable source for the video. This allows processing without
+        loading the entire video into memory.
+
+        Returns:
+            Either a file path (str) or a BytesIO object that can be opened with av.
+
+        Default implementation creates a BytesIO buffer, but subclasses should
+        override this for better performance when possible.
+        """
+        buffer = io.BytesIO()
+        self.save_to(buffer)
+        buffer.seek(0)
+        return buffer
+
+    # Provide a default implementation, but subclasses can provide optimized versions
+    # if possible.
+    def get_dimensions(self) -> tuple[int, int]:
+        """
+        Returns the dimensions of the video input.
+
+        Returns:
+            Tuple of (width, height)
+        """
+        components = self.get_components()
+        return components.images.shape[2], components.images.shape[1]
+
+    def get_duration(self) -> float:
+        """
+        Returns the duration of the video in seconds.
+
+        Returns:
+            Duration in seconds
+        """
+        components = self.get_components()
+        frame_count = components.images.shape[0]
+        return float(frame_count / components.frame_rate)
+
+    def get_container_format(self) -> str:
+        """
+        Returns the container format of the video (e.g., 'mp4', 'mov', 'avi').
+
+        Returns:
+            Container format as string
+        """
+        # Default implementation - subclasses should override for better performance
+        source = self.get_stream_source()
+        with av.open(source, mode="r") as container:
+            return container.format.name

comfy_api/latest/_input_impl/__init__.py

@@ -0,0 +1,7 @@
+from .video_types import VideoFromFile, VideoFromComponents
+
+__all__ = [
+    # Implementations
+    "VideoFromFile",
+    "VideoFromComponents",
+]

comfy_api/latest/_input_impl/video_types.py

@@ -0,0 +1,324 @@
+from __future__ import annotations
+from av.container import InputContainer
+from av.subtitles.stream import SubtitleStream
+from fractions import Fraction
+from typing import Optional
+from comfy_api.latest._input import AudioInput, VideoInput
+import av
+import io
+import json
+import numpy as np
+import torch
+from comfy_api.latest._util import VideoContainer, VideoCodec, VideoComponents
+
+
+def container_to_output_format(container_format: str | None) -> str | None:
+    """
+    A container's `format` may be a comma-separated list of formats.
+    E.g., iso container's `format` may be `mov,mp4,m4a,3gp,3g2,mj2`.
+    However, writing to a file/stream with `av.open` requires a single format,
+    or `None` to auto-detect.
+    """
+    if not container_format:
+        return None  # Auto-detect
+
+    if "," not in container_format:
+        return container_format
+
+    formats = container_format.split(",")
+    return formats[0]
+
+
+def get_open_write_kwargs(
+    dest: str | io.BytesIO, container_format: str, to_format: str | None
+) -> dict:
+    """Get kwargs for writing a `VideoFromFile` to a file/stream with `av.open`"""
+    open_kwargs = {
+        "mode": "w",
+        # If isobmff, preserve custom metadata tags (workflow, prompt, extra_pnginfo)
+        "options": {"movflags": "use_metadata_tags"},
+    }
+
+    is_write_to_buffer = isinstance(dest, io.BytesIO)
+    if is_write_to_buffer:
+        # Set output format explicitly, since it cannot be inferred from file extension
+        if to_format == VideoContainer.AUTO:
+            to_format = container_format.lower()
+        elif isinstance(to_format, str):
+            to_format = to_format.lower()
+        open_kwargs["format"] = container_to_output_format(to_format)
+
+    return open_kwargs
+
+
+class VideoFromFile(VideoInput):
+    """
+    Class representing video input from a file.
+    """
+
+    def __init__(self, file: str | io.BytesIO):
+        """
+        Initialize the VideoFromFile object based off of either a path on disk or a BytesIO object
+        containing the file contents.
+        """
+        self.__file = file
+
+    def get_stream_source(self) -> str | io.BytesIO:
+        """
+        Return the underlying file source for efficient streaming.
+        This avoids unnecessary memory copies when the source is already a file path.
+        """
+        if isinstance(self.__file, io.BytesIO):
+            self.__file.seek(0)
+        return self.__file
+
+    def get_dimensions(self) -> tuple[int, int]:
+        """
+        Returns the dimensions of the video input.
+
+        Returns:
+            Tuple of (width, height)
+        """
+        if isinstance(self.__file, io.BytesIO):
+            self.__file.seek(0)  # Reset the BytesIO object to the beginning
+        with av.open(self.__file, mode='r') as container:
+            for stream in container.streams:
+                if stream.type == 'video':
+                    assert isinstance(stream, av.VideoStream)
+                    return stream.width, stream.height
+        raise ValueError(f"No video stream found in file '{self.__file}'")
+
+    def get_duration(self) -> float:
+        """
+        Returns the duration of the video in seconds.
+
+        Returns:
+            Duration in seconds
+        """
+        if isinstance(self.__file, io.BytesIO):
+            self.__file.seek(0)
+        with av.open(self.__file, mode="r") as container:
+            if container.duration is not None:
+                return float(container.duration / av.time_base)
+
+            # Fallback: calculate from frame count and frame rate
+            video_stream = next(
+                (s for s in container.streams if s.type == "video"), None
+            )
+            if video_stream and video_stream.frames and video_stream.average_rate:
+                return float(video_stream.frames / video_stream.average_rate)
+
+            # Last resort: decode frames to count them
+            if video_stream and video_stream.average_rate:
+                frame_count = 0
+                container.seek(0)
+                for packet in container.demux(video_stream):
+                    for _ in packet.decode():
+                        frame_count += 1
+                if frame_count > 0:
+                    return float(frame_count / video_stream.average_rate)
+
+        raise ValueError(f"Could not determine duration for file '{self.__file}'")
+
+    def get_container_format(self) -> str:
+        """
+        Returns the container format of the video (e.g., 'mp4', 'mov', 'avi').
+
+        Returns:
+            Container format as string
+        """
+        if isinstance(self.__file, io.BytesIO):
+            self.__file.seek(0)
+        with av.open(self.__file, mode='r') as container:
+            return container.format.name
+
+    def get_components_internal(self, container: InputContainer) -> VideoComponents:
+        # Get video frames
+        frames = []
+        for frame in container.decode(video=0):
+            img = frame.to_ndarray(format='rgb24')  # shape: (H, W, 3)
+            img = torch.from_numpy(img) / 255.0  # shape: (H, W, 3)
+            frames.append(img)
+
+        images = torch.stack(frames) if len(frames) > 0 else torch.zeros(0, 3, 0, 0)
+
+        # Get frame rate
+        video_stream = next(s for s in container.streams if s.type == 'video')
+        frame_rate = Fraction(video_stream.average_rate) if video_stream and video_stream.average_rate else Fraction(1)
+
+        # Get audio if available
+        audio = None
+        try:
+            container.seek(0)  # Reset the container to the beginning
+            for stream in container.streams:
+                if stream.type != 'audio':
+                    continue
+                assert isinstance(stream, av.AudioStream)
+                audio_frames = []
+                for packet in container.demux(stream):
+                    for frame in packet.decode():
+                        assert isinstance(frame, av.AudioFrame)
+                        audio_frames.append(frame.to_ndarray())  # shape: (channels, samples)
+                if len(audio_frames) > 0:
+                    audio_data = np.concatenate(audio_frames, axis=1)  # shape: (channels, total_samples)
+                    audio_tensor = torch.from_numpy(audio_data).unsqueeze(0)  # shape: (1, channels, total_samples)
+                    audio = AudioInput({
+                        "waveform": audio_tensor,
+                        "sample_rate": int(stream.sample_rate) if stream.sample_rate else 1,
+                    })
+        except StopIteration:
+            pass  # No audio stream
+
+        metadata = container.metadata
+        return VideoComponents(images=images, audio=audio, frame_rate=frame_rate, metadata=metadata)
+
+    def get_components(self) -> VideoComponents:
+        if isinstance(self.__file, io.BytesIO):
+            self.__file.seek(0)  # Reset the BytesIO object to the beginning
+        with av.open(self.__file, mode='r') as container:
+            return self.get_components_internal(container)
+        raise ValueError(f"No video stream found in file '{self.__file}'")
+
+    def save_to(
+        self,
+        path: str | io.BytesIO,
+        format: VideoContainer = VideoContainer.AUTO,
+        codec: VideoCodec = VideoCodec.AUTO,
+        metadata: Optional[dict] = None
+    ):
+        if isinstance(self.__file, io.BytesIO):
+            self.__file.seek(0)  # Reset the BytesIO object to the beginning
+        with av.open(self.__file, mode='r') as container:
+            container_format = container.format.name
+            video_encoding = container.streams.video[0].codec.name if len(container.streams.video) > 0 else None
+            reuse_streams = True
+            if format != VideoContainer.AUTO and format not in container_format.split(","):
+                reuse_streams = False
+            if codec != VideoCodec.AUTO and codec != video_encoding and video_encoding is not None:
+                reuse_streams = False
+
+            if not reuse_streams:
+                components = self.get_components_internal(container)
+                video = VideoFromComponents(components)
+                return video.save_to(
+                    path,
+                    format=format,
+                    codec=codec,
+                    metadata=metadata
+                )
+
+            streams = container.streams
+
+            open_kwargs = get_open_write_kwargs(path, container_format, format)
+            with av.open(path, **open_kwargs) as output_container:
+                # Copy over the original metadata
+                for key, value in container.metadata.items():
+                    if metadata is None or key not in metadata:
+                        output_container.metadata[key] = value
+
+                # Add our new metadata
+                if metadata is not None:
+                    for key, value in metadata.items():
+                        if isinstance(value, str):
+                            output_container.metadata[key] = value
+                        else:
+                            output_container.metadata[key] = json.dumps(value)
+
+                # Add streams to the new container
+                stream_map = {}
+                for stream in streams:
+                    if isinstance(stream, (av.VideoStream, av.AudioStream, SubtitleStream)):
+                        out_stream = output_container.add_stream_from_template(template=stream, opaque=True)
+                        stream_map[stream] = out_stream
+
+                # Write packets to the new container
+                for packet in container.demux():
+                    if packet.stream in stream_map and packet.dts is not None:
+                        packet.stream = stream_map[packet.stream]
+                        output_container.mux(packet)
+
+class VideoFromComponents(VideoInput):
+    """
+    Class representing video input from tensors.
+    """
+
+    def __init__(self, components: VideoComponents):
+        self.__components = components
+
+    def get_components(self) -> VideoComponents:
+        return VideoComponents(
+            images=self.__components.images,
+            audio=self.__components.audio,
+            frame_rate=self.__components.frame_rate
+        )
+
+    def save_to(
+        self,
+        path: str,
+        format: VideoContainer = VideoContainer.AUTO,
+        codec: VideoCodec = VideoCodec.AUTO,
+        metadata: Optional[dict] = None
+    ):
+        if format != VideoContainer.AUTO and format != VideoContainer.MP4:
+            raise ValueError("Only MP4 format is supported for now")
+        if codec != VideoCodec.AUTO and codec != VideoCodec.H264:
+            raise ValueError("Only H264 codec is supported for now")
+        with av.open(path, mode='w', options={'movflags': 'use_metadata_tags'}) as output:
+            # Add metadata before writing any streams
+            if metadata is not None:
+                for key, value in metadata.items():
+                    output.metadata[key] = json.dumps(value)
+
+            frame_rate = Fraction(round(self.__components.frame_rate * 1000), 1000)
+            # Create a video stream
+            video_stream = output.add_stream('h264', rate=frame_rate)
+            video_stream.width = self.__components.images.shape[2]
+            video_stream.height = self.__components.images.shape[1]
+            video_stream.pix_fmt = 'yuv420p'
+
+            # Create an audio stream
+            audio_sample_rate = 1
+            audio_stream: Optional[av.AudioStream] = None
+            if self.__components.audio:
+                audio_sample_rate = int(self.__components.audio['sample_rate'])
+                audio_stream = output.add_stream('aac', rate=audio_sample_rate)
+                audio_stream.sample_rate = audio_sample_rate
+                audio_stream.format = 'fltp'
+
+            # Encode video
+            for i, frame in enumerate(self.__components.images):
+                img = (frame * 255).clamp(0, 255).byte().cpu().numpy() # shape: (H, W, 3)
+                frame = av.VideoFrame.from_ndarray(img, format='rgb24')
+                frame = frame.reformat(format='yuv420p')  # Convert to YUV420P as required by h264
+                packet = video_stream.encode(frame)
+                output.mux(packet)
+
+            # Flush video
+            packet = video_stream.encode(None)
+            output.mux(packet)
+
+            if audio_stream and self.__components.audio:
+                # Encode audio
+                samples_per_frame = int(audio_sample_rate / frame_rate)
+                num_frames = self.__components.audio['waveform'].shape[2] // samples_per_frame
+                for i in range(num_frames):
+                    start = i * samples_per_frame
+                    end = start + samples_per_frame
+                    # TODO(Feature) - Add support for stereo audio
+                    chunk = (
+                        self.__components.audio["waveform"][0, 0, start:end]
+                        .unsqueeze(0)
+                        .contiguous()
+                        .numpy()
+                    )
+                    audio_frame = av.AudioFrame.from_ndarray(chunk, format='fltp', layout='mono')
+                    audio_frame.sample_rate = audio_sample_rate
+                    audio_frame.pts = i * samples_per_frame
+                    for packet in audio_stream.encode(audio_frame):
+                        output.mux(packet)
+
+                # Flush audio
+                for packet in audio_stream.encode(None):
+                    output.mux(packet)
+
+

comfy_api/latest/_resources.py

@@ -0,0 +1,72 @@
+from __future__ import annotations
+import comfy.utils
+import folder_paths
+import logging
+from abc import ABC, abstractmethod
+from typing import Any
+import torch
+
+class ResourceKey(ABC):
+    Type = Any
+    def __init__(self):
+        ...
+
+class TorchDictFolderFilename(ResourceKey):
+    '''Key for requesting a torch file via file_name from a folder category.'''
+    Type = dict[str, torch.Tensor]
+    def __init__(self, folder_name: str, file_name: str):
+        self.folder_name = folder_name
+        self.file_name = file_name
+
+    def __hash__(self):
+        return hash((self.folder_name, self.file_name))
+
+    def __eq__(self, other: object) -> bool:
+        if not isinstance(other, TorchDictFolderFilename):
+            return False
+        return self.folder_name == other.folder_name and self.file_name == other.file_name
+
+    def __str__(self):
+        return f"{self.folder_name} -> {self.file_name}"
+
+class Resources(ABC):
+    def __init__(self):
+        ...
+
+    @abstractmethod
+    def get(self, key: ResourceKey, default: Any=...) -> Any:
+        pass
+
+class ResourcesLocal(Resources):
+    def __init__(self):
+        super().__init__()
+        self.local_resources: dict[ResourceKey, Any] = {}
+
+    def get(self, key: ResourceKey, default: Any=...) -> Any:
+        cached = self.local_resources.get(key, None)
+        if cached is not None:
+            logging.info(f"Using cached resource '{key}'")
+            return cached
+        logging.info(f"Loading resource '{key}'")
+        to_return = None
+        if isinstance(key, TorchDictFolderFilename):
+            if default is ...:
+                to_return = comfy.utils.load_torch_file(folder_paths.get_full_path_or_raise(key.folder_name, key.file_name), safe_load=True)
+            else:
+                full_path = folder_paths.get_full_path(key.folder_name, key.file_name)
+                if full_path is not None:
+                    to_return = comfy.utils.load_torch_file(full_path, safe_load=True)
+
+        if to_return is not None:
+            self.local_resources[key] = to_return
+            return to_return
+        if default is not ...:
+            return default
+        raise Exception(f"Unsupported resource key type: {type(key)}")
+
+
+class _RESOURCES:
+    ResourceKey = ResourceKey
+    TorchDictFolderFilename = TorchDictFolderFilename
+    Resources = Resources
+    ResourcesLocal = ResourcesLocal

comfy_api/latest/_ui.py

@@ -0,0 +1,505 @@
+from __future__ import annotations
+
+import json
+import os
+import random
+from io import BytesIO
+from typing import Type
+
+import av
+import numpy as np
+import torch
+import torchaudio
+from PIL import Image as PILImage
+from PIL.PngImagePlugin import PngInfo
+
+import folder_paths
+
+# used for image preview
+from comfy.cli_args import args
+from comfy_api.latest._io import ComfyNode, FolderType, Image, _UIOutput
+
+
+class SavedResult(dict):
+    def __init__(self, filename: str, subfolder: str, type: FolderType):
+        super().__init__(filename=filename, subfolder=subfolder,type=type.value)
+
+    @property
+    def filename(self) -> str:
+        return self["filename"]
+
+    @property
+    def subfolder(self) -> str:
+        return self["subfolder"]
+
+    @property
+    def type(self) -> FolderType:
+        return FolderType(self["type"])
+
+
+class SavedImages(_UIOutput):
+    """A UI output class to represent one or more saved images, potentially animated."""
+    def __init__(self, results: list[SavedResult], is_animated: bool = False):
+        super().__init__()
+        self.results = results
+        self.is_animated = is_animated
+
+    def as_dict(self) -> dict:
+        data = {"images": self.results}
+        if self.is_animated:
+            data["animated"] = (True,)
+        return data
+
+
+class SavedAudios(_UIOutput):
+    """UI wrapper around one or more audio files on disk (FLAC / MP3 / Opus)."""
+    def __init__(self, results: list[SavedResult]):
+        super().__init__()
+        self.results = results
+
+    def as_dict(self) -> dict:
+        return {"audio": self.results}
+
+
+def _get_directory_by_folder_type(folder_type: FolderType) -> str:
+    if folder_type == FolderType.input:
+        return folder_paths.get_input_directory()
+    if folder_type == FolderType.output:
+        return folder_paths.get_output_directory()
+    return folder_paths.get_temp_directory()
+
+
+class ImageSaveHelper:
+    """A helper class with static methods to handle image saving and metadata."""
+
+    @staticmethod
+    def _convert_tensor_to_pil(image_tensor: torch.Tensor) -> PILImage.Image:
+        """Converts a single torch tensor to a PIL Image."""
+        return PILImage.fromarray(np.clip(255.0 * image_tensor.cpu().numpy(), 0, 255).astype(np.uint8))
+
+    @staticmethod
+    def _create_png_metadata(cls: Type[ComfyNode] | None) -> PngInfo | None:
+        """Creates a PngInfo object with prompt and extra_pnginfo."""
+        if args.disable_metadata or cls is None or not cls.hidden:
+            return None
+        metadata = PngInfo()
+        if cls.hidden.prompt:
+            metadata.add_text("prompt", json.dumps(cls.hidden.prompt))
+        if cls.hidden.extra_pnginfo:
+            for x in cls.hidden.extra_pnginfo:
+                metadata.add_text(x, json.dumps(cls.hidden.extra_pnginfo[x]))
+        return metadata
+
+    @staticmethod
+    def _create_animated_png_metadata(cls: Type[ComfyNode] | None) -> PngInfo | None:
+        """Creates a PngInfo object with prompt and extra_pnginfo for animated PNGs (APNG)."""
+        if args.disable_metadata or cls is None or not cls.hidden:
+            return None
+        metadata = PngInfo()
+        if cls.hidden.prompt:
+            metadata.add(
+                b"comf",
+                "prompt".encode("latin-1", "strict")
+                + b"\0"
+                + json.dumps(cls.hidden.prompt).encode("latin-1", "strict"),
+                after_idat=True,
+            )
+        if cls.hidden.extra_pnginfo:
+            for x in cls.hidden.extra_pnginfo:
+                metadata.add(
+                    b"comf",
+                    x.encode("latin-1", "strict")
+                    + b"\0"
+                    + json.dumps(cls.hidden.extra_pnginfo[x]).encode("latin-1", "strict"),
+                    after_idat=True,
+                )
+        return metadata
+
+    @staticmethod
+    def _create_webp_metadata(pil_image: PILImage.Image, cls: Type[ComfyNode] | None) -> PILImage.Exif:
+        """Creates EXIF metadata bytes for WebP images."""
+        exif_data = pil_image.getexif()
+        if args.disable_metadata or cls is None or cls.hidden is None:
+            return exif_data
+        if cls.hidden.prompt is not None:
+            exif_data[0x0110] = "prompt:{}".format(json.dumps(cls.hidden.prompt))  # EXIF 0x0110 = Model
+        if cls.hidden.extra_pnginfo is not None:
+            inital_exif_tag = 0x010F  # EXIF 0x010f = Make
+            for key, value in cls.hidden.extra_pnginfo.items():
+                exif_data[inital_exif_tag] = "{}:{}".format(key, json.dumps(value))
+                inital_exif_tag -= 1
+        return exif_data
+
+    @staticmethod
+    def save_images(
+        images, filename_prefix: str, folder_type: FolderType, cls: Type[ComfyNode] | None, compress_level = 4,
+    ) -> list[SavedResult]:
+        """Saves a batch of images as individual PNG files."""
+        full_output_folder, filename, counter, subfolder, _ = folder_paths.get_save_image_path(
+            filename_prefix, _get_directory_by_folder_type(folder_type), images[0].shape[1], images[0].shape[0]
+        )
+        results = []
+        metadata = ImageSaveHelper._create_png_metadata(cls)
+        for batch_number, image_tensor in enumerate(images):
+            img = ImageSaveHelper._convert_tensor_to_pil(image_tensor)
+            filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
+            file = f"{filename_with_batch_num}_{counter:05}_.png"
+            img.save(os.path.join(full_output_folder, file), pnginfo=metadata, compress_level=compress_level)
+            results.append(SavedResult(file, subfolder, folder_type))
+            counter += 1
+        return results
+
+    @staticmethod
+    def get_save_images_ui(images, filename_prefix: str, cls: Type[ComfyNode] | None, compress_level=4) -> SavedImages:
+        """Saves a batch of images and returns a UI object for the node output."""
+        return SavedImages(
+                ImageSaveHelper.save_images(
+                images,
+                filename_prefix=filename_prefix,
+                folder_type=FolderType.output,
+                cls=cls,
+                compress_level=compress_level,
+            )
+        )
+
+    @staticmethod
+    def save_animated_png(
+        images, filename_prefix: str, folder_type: FolderType, cls: Type[ComfyNode] | None, fps: float, compress_level: int
+    ) -> SavedResult:
+        """Saves a batch of images as a single animated PNG."""
+        full_output_folder, filename, counter, subfolder, _ = folder_paths.get_save_image_path(
+            filename_prefix, _get_directory_by_folder_type(folder_type), images[0].shape[1], images[0].shape[0]
+        )
+        pil_images = [ImageSaveHelper._convert_tensor_to_pil(img) for img in images]
+        metadata = ImageSaveHelper._create_animated_png_metadata(cls)
+        file = f"{filename}_{counter:05}_.png"
+        save_path = os.path.join(full_output_folder, file)
+        pil_images[0].save(
+            save_path,
+            pnginfo=metadata,
+            compress_level=compress_level,
+            save_all=True,
+            duration=int(1000.0 / fps),
+            append_images=pil_images[1:],
+        )
+        return SavedResult(file, subfolder, folder_type)
+
+    @staticmethod
+    def get_save_animated_png_ui(
+        images, filename_prefix: str, cls: Type[ComfyNode] | None, fps: float, compress_level: int
+    ) -> SavedImages:
+        """Saves an animated PNG and returns a UI object for the node output."""
+        result = ImageSaveHelper.save_animated_png(
+            images,
+            filename_prefix=filename_prefix,
+            folder_type=FolderType.output,
+            cls=cls,
+            fps=fps,
+            compress_level=compress_level,
+        )
+        return SavedImages([result], is_animated=len(images) > 1)
+
+    @staticmethod
+    def save_animated_webp(
+        images,
+        filename_prefix: str,
+        folder_type: FolderType,
+        cls: Type[ComfyNode] | None,
+        fps: float,
+        lossless: bool,
+        quality: int,
+        method: int,
+    ) -> SavedResult:
+        """Saves a batch of images as a single animated WebP."""
+        full_output_folder, filename, counter, subfolder, _ = folder_paths.get_save_image_path(
+            filename_prefix, _get_directory_by_folder_type(folder_type), images[0].shape[1], images[0].shape[0]
+        )
+        pil_images = [ImageSaveHelper._convert_tensor_to_pil(img) for img in images]
+        pil_exif = ImageSaveHelper._create_webp_metadata(pil_images[0], cls)
+        file = f"{filename}_{counter:05}_.webp"
+        pil_images[0].save(
+            os.path.join(full_output_folder, file),
+            save_all=True,
+            duration=int(1000.0 / fps),
+            append_images=pil_images[1:],
+            exif=pil_exif,
+            lossless=lossless,
+            quality=quality,
+            method=method,
+        )
+        return SavedResult(file, subfolder, folder_type)
+
+    @staticmethod
+    def get_save_animated_webp_ui(
+        images,
+        filename_prefix: str,
+        cls: Type[ComfyNode] | None,
+        fps: float,
+        lossless: bool,
+        quality: int,
+        method: int,
+    ) -> SavedImages:
+        """Saves an animated WebP and returns a UI object for the node output."""
+        result = ImageSaveHelper.save_animated_webp(
+            images,
+            filename_prefix=filename_prefix,
+            folder_type=FolderType.output,
+            cls=cls,
+            fps=fps,
+            lossless=lossless,
+            quality=quality,
+            method=method,
+        )
+        return SavedImages([result], is_animated=len(images) > 1)
+
+
+class AudioSaveHelper:
+    """A helper class with static methods to handle audio saving and metadata."""
+    _OPUS_RATES = [8000, 12000, 16000, 24000, 48000]
+
+    @staticmethod
+    def save_audio(
+        audio: dict,
+        filename_prefix: str,
+        folder_type: FolderType,
+        cls: Type[ComfyNode] | None,
+        format: str = "flac",
+        quality: str = "128k",
+    ) -> list[SavedResult]:
+        full_output_folder, filename, counter, subfolder, _ = folder_paths.get_save_image_path(
+            filename_prefix, _get_directory_by_folder_type(folder_type)
+        )
+
+        metadata = {}
+        if not args.disable_metadata and cls is not None:
+            if cls.hidden.prompt is not None:
+                metadata["prompt"] = json.dumps(cls.hidden.prompt)
+            if cls.hidden.extra_pnginfo is not None:
+                for x in cls.hidden.extra_pnginfo:
+                    metadata[x] = json.dumps(cls.hidden.extra_pnginfo[x])
+
+        results = []
+        for batch_number, waveform in enumerate(audio["waveform"].cpu()):
+            filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
+            file = f"{filename_with_batch_num}_{counter:05}_.{format}"
+            output_path = os.path.join(full_output_folder, file)
+
+            # Use original sample rate initially
+            sample_rate = audio["sample_rate"]
+
+            # Handle Opus sample rate requirements
+            if format == "opus":
+                if sample_rate > 48000:
+                    sample_rate = 48000
+                elif sample_rate not in AudioSaveHelper._OPUS_RATES:
+                    # Find the next highest supported rate
+                    for rate in sorted(AudioSaveHelper._OPUS_RATES):
+                        if rate > sample_rate:
+                            sample_rate = rate
+                            break
+                    if sample_rate not in AudioSaveHelper._OPUS_RATES:  # Fallback if still not supported
+                        sample_rate = 48000
+
+                # Resample if necessary
+                if sample_rate != audio["sample_rate"]:
+                    waveform = torchaudio.functional.resample(waveform, audio["sample_rate"], sample_rate)
+
+            # Create output with specified format
+            output_buffer = BytesIO()
+            output_container = av.open(output_buffer, mode="w", format=format)
+
+            # Set metadata on the container
+            for key, value in metadata.items():
+                output_container.metadata[key] = value
+
+            # Set up the output stream with appropriate properties
+            if format == "opus":
+                out_stream = output_container.add_stream("libopus", rate=sample_rate)
+                if quality == "64k":
+                    out_stream.bit_rate = 64000
+                elif quality == "96k":
+                    out_stream.bit_rate = 96000
+                elif quality == "128k":
+                    out_stream.bit_rate = 128000
+                elif quality == "192k":
+                    out_stream.bit_rate = 192000
+                elif quality == "320k":
+                    out_stream.bit_rate = 320000
+            elif format == "mp3":
+                out_stream = output_container.add_stream("libmp3lame", rate=sample_rate)
+                if quality == "V0":
+                    # TODO i would really love to support V3 and V5 but there doesn't seem to be a way to set the qscale level, the property below is a bool
+                    out_stream.codec_context.qscale = 1
+                elif quality == "128k":
+                    out_stream.bit_rate = 128000
+                elif quality == "320k":
+                    out_stream.bit_rate = 320000
+            else:  # format == "flac":
+                out_stream = output_container.add_stream("flac", rate=sample_rate)
+
+            frame = av.AudioFrame.from_ndarray(
+                waveform.movedim(0, 1).reshape(1, -1).float().numpy(),
+                format="flt",
+                layout="mono" if waveform.shape[0] == 1 else "stereo",
+            )
+            frame.sample_rate = sample_rate
+            frame.pts = 0
+            output_container.mux(out_stream.encode(frame))
+
+            # Flush encoder
+            output_container.mux(out_stream.encode(None))
+
+            # Close containers
+            output_container.close()
+
+            # Write the output to file
+            output_buffer.seek(0)
+            with open(output_path, "wb") as f:
+                f.write(output_buffer.getbuffer())
+
+            results.append(SavedResult(file, subfolder, folder_type))
+            counter += 1
+
+        return results
+
+    @staticmethod
+    def get_save_audio_ui(
+        audio, filename_prefix: str, cls: Type[ComfyNode] | None, format: str = "flac", quality: str = "128k",
+    ) -> SavedAudios:
+        """Save and instantly wrap for UI."""
+        return SavedAudios(
+            AudioSaveHelper.save_audio(
+                audio,
+                filename_prefix=filename_prefix,
+                folder_type=FolderType.output,
+                cls=cls,
+                format=format,
+                quality=quality,
+            )
+        )
+
+
+class PreviewImage(_UIOutput):
+    def __init__(self, image: Image.Type, animated: bool = False, cls: Type[ComfyNode] = None, **kwargs):
+        self.values = ImageSaveHelper.save_images(
+            image,
+            filename_prefix="ComfyUI_temp_" + ''.join(random.choice("abcdefghijklmnopqrstupvxyz") for _ in range(5)),
+            folder_type=FolderType.temp,
+            cls=cls,
+            compress_level=1,
+        )
+        self.animated = animated
+
+    def as_dict(self):
+        return {
+            "images": self.values,
+            "animated": (self.animated,)
+        }
+
+
+class PreviewMask(PreviewImage):
+    def __init__(self, mask: PreviewMask.Type, animated: bool=False, cls: ComfyNode=None, **kwargs):
+        preview = mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])).movedim(1, -1).expand(-1, -1, -1, 3)
+        super().__init__(preview, animated, cls, **kwargs)
+
+
+# class UILatent(_UIOutput):
+#     def __init__(self, values: list[SavedResult | dict], **kwargs):
+#         output_dir = folder_paths.get_temp_directory()
+#         type = "temp"
+#         prefix_append = "_temp_" + ''.join(random.choice("abcdefghijklmnopqrstupvxyz") for x in range(5))
+#         compress_level = 1
+#         filename_prefix = "ComfyUI"
+
+
+#         full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir)
+
+#         # support save metadata for latent sharing
+#         prompt_info = ""
+#         if prompt is not None:
+#             prompt_info = json.dumps(prompt)
+
+#         metadata = None
+#         if not args.disable_metadata:
+#             metadata = {"prompt": prompt_info}
+#             if extra_pnginfo is not None:
+#                 for x in extra_pnginfo:
+#                     metadata[x] = json.dumps(extra_pnginfo[x])
+
+#         file = f"{filename}_{counter:05}_.latent"
+
+#         results: list[FileLocator] = []
+#         results.append({
+#             "filename": file,
+#             "subfolder": subfolder,
+#             "type": "output"
+#         })
+
+#         file = os.path.join(full_output_folder, file)
+
+#         output = {}
+#         output["latent_tensor"] = samples["samples"].contiguous()
+#         output["latent_format_version_0"] = torch.tensor([])
+
+#         comfy.utils.save_torch_file(output, file, metadata=metadata)
+
+#         self.values = values
+
+#     def as_dict(self):
+#         return {
+#             "latents": self.values,
+#         }
+
+
+class PreviewAudio(_UIOutput):
+    def __init__(self, audio: dict, cls: Type[ComfyNode] = None, **kwargs):
+        self.values = AudioSaveHelper.save_audio(
+            audio,
+            filename_prefix="ComfyUI_temp_" + "".join(random.choice("abcdefghijklmnopqrstuvwxyz") for _ in range(5)),
+            folder_type=FolderType.temp,
+            cls=cls,
+            format="flac",
+            quality="128k",
+        )
+
+    def as_dict(self) -> dict:
+        return {"audio": self.values}
+
+
+class PreviewVideo(_UIOutput):
+    def __init__(self, values: list[SavedResult | dict], **kwargs):
+        self.values = values
+
+    def as_dict(self):
+        return {"images": self.values, "animated": (True,)}
+
+
+class PreviewUI3D(_UIOutput):
+    def __init__(self, model_file, camera_info, **kwargs):
+        self.model_file = model_file
+        self.camera_info = camera_info
+
+    def as_dict(self):
+        return {"result": [self.model_file, self.camera_info]}
+
+
+class PreviewText(_UIOutput):
+    def __init__(self, value: str, **kwargs):
+        self.value = value
+
+    def as_dict(self):
+        return {"text": (self.value,)}
+
+
+class _UI:
+    SavedResult = SavedResult
+    SavedImages = SavedImages
+    SavedAudios = SavedAudios
+    ImageSaveHelper = ImageSaveHelper
+    AudioSaveHelper = AudioSaveHelper
+    PreviewImage = PreviewImage
+    PreviewMask = PreviewMask
+    PreviewAudio = PreviewAudio
+    PreviewVideo = PreviewVideo
+    PreviewUI3D = PreviewUI3D
+    PreviewText = PreviewText

comfy_api/latest/_util/__init__.py

@@ -0,0 +1,8 @@
+from .video_types import VideoContainer, VideoCodec, VideoComponents
+
+__all__ = [
+    # Utility Types
+    "VideoContainer",
+    "VideoCodec",
+    "VideoComponents",
+]

comfy_api/latest/_util/video_types.py

@@ -0,0 +1,52 @@
+from __future__ import annotations
+from dataclasses import dataclass
+from enum import Enum
+from fractions import Fraction
+from typing import Optional
+from comfy_api.latest._input import ImageInput, AudioInput
+
+class VideoCodec(str, Enum):
+    AUTO = "auto"
+    H264 = "h264"
+
+    @classmethod
+    def as_input(cls) -> list[str]:
+        """
+        Returns a list of codec names that can be used as node input.
+        """
+        return [member.value for member in cls]
+
+class VideoContainer(str, Enum):
+    AUTO = "auto"
+    MP4 = "mp4"
+
+    @classmethod
+    def as_input(cls) -> list[str]:
+        """
+        Returns a list of container names that can be used as node input.
+        """
+        return [member.value for member in cls]
+
+    @classmethod
+    def get_extension(cls, value) -> str:
+        """
+        Returns the file extension for the container.
+        """
+        if isinstance(value, str):
+            value = cls(value)
+        if value == VideoContainer.MP4 or value == VideoContainer.AUTO:
+            return "mp4"
+        return ""
+
+@dataclass
+class VideoComponents:
+    """
+    Dataclass representing the components of a video.
+    """
+
+    images: ImageInput
+    frame_rate: Fraction
+    audio: Optional[AudioInput] = None
+    metadata: Optional[dict] = None
+
+

comfy_api/latest/generated/ComfyAPISyncStub.pyi

@@ -0,0 +1,20 @@
+from typing import Any, Dict, List, Optional, Tuple, Union, Set, Sequence, cast, NamedTuple
+from comfy_api.latest import ComfyAPI_latest
+from PIL.Image import Image
+from torch import Tensor
+class ComfyAPISyncStub:
+    def __init__(self) -> None: ...
+
+    class ExecutionSync:
+        def __init__(self) -> None: ...
+        """
+        Update the progress bar displayed in the ComfyUI interface.
+
+        This function allows custom nodes and API calls to report their progress
+        back to the user interface, providing visual feedback during long operations.
+
+        Migration from previous API: comfy.utils.PROGRESS_BAR_HOOK
+        """
+        def set_progress(self, value: float, max_value: float, node_id: Union[str, None] = None, preview_image: Union[Image, Tensor, None] = None, ignore_size_limit: bool = False) -> None: ...
+
+    execution: ExecutionSync

comfy_api/util.py

@@ -0,0 +1,8 @@
+# This file only exists for backwards compatibility.
+from comfy_api.latest._util import VideoCodec, VideoContainer, VideoComponents
+
+__all__ = [
+    "VideoCodec",
+    "VideoContainer",
+    "VideoComponents",
+]

comfy_api/util/__init__.py

@@ -1,7 +1,7 @@
-from .video_types import VideoContainer, VideoCodec, VideoComponents
+# This file only exists for backwards compatibility.
+from comfy_api.latest._util import VideoContainer, VideoCodec, VideoComponents
 
 __all__ = [
-    # Utility Types
     "VideoContainer",
     "VideoCodec",
     "VideoComponents",

comfy_api/util/video_types.py

@@ -1,51 +1,12 @@
-from __future__ import annotations
-from dataclasses import dataclass
-from enum import Enum
-from fractions import Fraction
-from typing import Optional
-from comfy_api.input import ImageInput, AudioInput
-
-class VideoCodec(str, Enum):
-    AUTO = "auto"
-    H264 = "h264"
-
-    @classmethod
-    def as_input(cls) -> list[str]:
-        """
-        Returns a list of codec names that can be used as node input.
-        """
-        return [member.value for member in cls]
-
-class VideoContainer(str, Enum):
-    AUTO = "auto"
-    MP4 = "mp4"
-
-    @classmethod
-    def as_input(cls) -> list[str]:
-        """
-        Returns a list of container names that can be used as node input.
-        """
-        return [member.value for member in cls]
-
-    @classmethod
-    def get_extension(cls, value) -> str:
-        """
-        Returns the file extension for the container.
-        """
-        if isinstance(value, str):
-            value = cls(value)
-        if value == VideoContainer.MP4 or value == VideoContainer.AUTO:
-            return "mp4"
-        return ""
-
-@dataclass
-class VideoComponents:
-    """
-    Dataclass representing the components of a video.
-    """
-
-    images: ImageInput
-    frame_rate: Fraction
-    audio: Optional[AudioInput] = None
-    metadata: Optional[dict] = None
+# This file only exists for backwards compatibility.
+from comfy_api.latest._util.video_types import (
+    VideoContainer,
+    VideoCodec,
+    VideoComponents,
+)
 
+__all__ = [
+    "VideoContainer",
+    "VideoCodec",
+    "VideoComponents",
+]

comfy_api/v0_0_1/__init__.py

@@ -0,0 +1,42 @@
+from comfy_api.v0_0_2 import (
+    ComfyAPIAdapter_v0_0_2,
+    Input as Input_v0_0_2,
+    InputImpl as InputImpl_v0_0_2,
+    Types as Types_v0_0_2,
+)
+from typing import Type, TYPE_CHECKING
+from comfy_api.internal.async_to_sync import create_sync_class
+
+
+# This version only exists to serve as a template for future version adapters.
+# There is no reason anyone should ever use it.
+class ComfyAPIAdapter_v0_0_1(ComfyAPIAdapter_v0_0_2):
+    VERSION = "0.0.1"
+    STABLE = True
+
+class Input(Input_v0_0_2):
+    pass
+
+class InputImpl(InputImpl_v0_0_2):
+    pass
+
+class Types(Types_v0_0_2):
+    pass
+
+ComfyAPI = ComfyAPIAdapter_v0_0_1
+
+# Create a synchronous version of the API
+if TYPE_CHECKING:
+    from comfy_api.v0_0_1.generated.ComfyAPISyncStub import ComfyAPISyncStub  # type: ignore
+
+    ComfyAPISync: Type[ComfyAPISyncStub]
+
+ComfyAPISync = create_sync_class(ComfyAPIAdapter_v0_0_1)
+
+__all__ = [
+    "ComfyAPI",
+    "ComfyAPISync",
+    "Input",
+    "InputImpl",
+    "Types",
+]

comfy_api/v0_0_1/generated/ComfyAPISyncStub.pyi

@@ -0,0 +1,20 @@
+from typing import Any, Dict, List, Optional, Tuple, Union, Set, Sequence, cast, NamedTuple
+from comfy_api.v0_0_1 import ComfyAPIAdapter_v0_0_1
+from PIL.Image import Image
+from torch import Tensor
+class ComfyAPISyncStub:
+    def __init__(self) -> None: ...
+
+    class ExecutionSync:
+        def __init__(self) -> None: ...
+        """
+        Update the progress bar displayed in the ComfyUI interface.
+
+        This function allows custom nodes and API calls to report their progress
+        back to the user interface, providing visual feedback during long operations.
+
+        Migration from previous API: comfy.utils.PROGRESS_BAR_HOOK
+        """
+        def set_progress(self, value: float, max_value: float, node_id: Union[str, None] = None, preview_image: Union[Image, Tensor, None] = None, ignore_size_limit: bool = False) -> None: ...
+
+    execution: ExecutionSync

comfy_api/v0_0_2/__init__.py

@@ -0,0 +1,44 @@
+from comfy_api.latest import (
+    ComfyAPI_latest,
+    Input as Input_latest,
+    InputImpl as InputImpl_latest,
+    Types as Types_latest,
+)
+from typing import Type, TYPE_CHECKING
+from comfy_api.internal.async_to_sync import create_sync_class
+from comfy_api.latest import io, ui, resources  #noqa: F401
+
+
+class ComfyAPIAdapter_v0_0_2(ComfyAPI_latest):
+    VERSION = "0.0.2"
+    STABLE = False
+
+
+class Input(Input_latest):
+    pass
+
+
+class InputImpl(InputImpl_latest):
+    pass
+
+
+class Types(Types_latest):
+    pass
+
+
+ComfyAPI = ComfyAPIAdapter_v0_0_2
+
+# Create a synchronous version of the API
+if TYPE_CHECKING:
+    from comfy_api.v0_0_2.generated.ComfyAPISyncStub import ComfyAPISyncStub  # type: ignore
+
+    ComfyAPISync: Type[ComfyAPISyncStub]
+ComfyAPISync = create_sync_class(ComfyAPIAdapter_v0_0_2)
+
+__all__ = [
+    "ComfyAPI",
+    "ComfyAPISync",
+    "Input",
+    "InputImpl",
+    "Types",
+]

comfy_api/v0_0_2/generated/ComfyAPISyncStub.pyi

@@ -0,0 +1,20 @@
+from typing import Any, Dict, List, Optional, Tuple, Union, Set, Sequence, cast, NamedTuple
+from comfy_api.v0_0_2 import ComfyAPIAdapter_v0_0_2
+from PIL.Image import Image
+from torch import Tensor
+class ComfyAPISyncStub:
+    def __init__(self) -> None: ...
+
+    class ExecutionSync:
+        def __init__(self) -> None: ...
+        """
+        Update the progress bar displayed in the ComfyUI interface.
+
+        This function allows custom nodes and API calls to report their progress
+        back to the user interface, providing visual feedback during long operations.
+
+        Migration from previous API: comfy.utils.PROGRESS_BAR_HOOK
+        """
+        def set_progress(self, value: float, max_value: float, node_id: Union[str, None] = None, preview_image: Union[Image, Tensor, None] = None, ignore_size_limit: bool = False) -> None: ...
+
+    execution: ExecutionSync

comfy_api/version_list.py

@@ -0,0 +1,12 @@
+from comfy_api.latest import ComfyAPI_latest
+from comfy_api.v0_0_2 import ComfyAPIAdapter_v0_0_2
+from comfy_api.v0_0_1 import ComfyAPIAdapter_v0_0_1
+from comfy_api.internal import ComfyAPIBase
+from typing import List, Type
+
+supported_versions: List[Type[ComfyAPIBase]] = [
+    ComfyAPI_latest,
+    ComfyAPIAdapter_v0_0_2,
+    ComfyAPIAdapter_v0_0_1,
+]
+

comfy_api_nodes/apis/request_logger.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import os
 import datetime
 import json

comfy_api_nodes/nodes_gemini.py

@@ -2,6 +2,8 @@
 API Nodes for Gemini Multimodal LLM Usage via Remote API
 See: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference
 """
+from __future__ import annotations
+
 
 import os
 from enum import Enum

comfy_execution/progress.py

@@ -1,4 +1,6 @@
-from typing import TypedDict, Dict, Optional
+from __future__ import annotations
+
+from typing import TypedDict, Dict, Optional, Tuple
 from typing_extensions import override
 from PIL import Image
 from enum import Enum
@@ -10,6 +12,7 @@ if TYPE_CHECKING:
 from protocol import BinaryEventTypes
 from comfy_api import feature_flags
 
+PreviewImageTuple = Tuple[str, Image.Image, Optional[int]]
 
 class NodeState(Enum):
     Pending = "pending"
@@ -52,7 +55,7 @@ class ProgressHandler(ABC):
         max_value: float,
         state: NodeProgressState,
         prompt_id: str,
-        image: Optional[Image.Image] = None,
+        image: PreviewImageTuple | None = None,
     ):
         """Called when a node's progress is updated"""
         pass
@@ -103,7 +106,7 @@ class CLIProgressHandler(ProgressHandler):
         max_value: float,
         state: NodeProgressState,
         prompt_id: str,
-        image: Optional[Image.Image] = None,
+        image: PreviewImageTuple | None = None,
     ):
         # Handle case where start_handler wasn't called
         if node_id not in self.progress_bars:
@@ -196,7 +199,7 @@ class WebUIProgressHandler(ProgressHandler):
         max_value: float,
         state: NodeProgressState,
         prompt_id: str,
-        image: Optional[Image.Image] = None,
+        image: PreviewImageTuple | None = None,
     ):
         # Send progress state of all nodes
         if self.registry:
@@ -231,7 +234,6 @@ class WebUIProgressHandler(ProgressHandler):
         if self.registry:
             self._send_progress_state(prompt_id, self.registry.nodes)
 
-
 class ProgressRegistry:
     """
     Registry that maintains node progress state and notifies registered handlers.
@@ -285,7 +287,7 @@ class ProgressRegistry:
                 handler.start_handler(node_id, entry, self.prompt_id)
 
     def update_progress(
-        self, node_id: str, value: float, max_value: float, image: Optional[Image.Image]
+        self, node_id: str, value: float, max_value: float, image: PreviewImageTuple | None = None
     ) -> None:
         """Update progress for a node"""
         entry = self.ensure_entry(node_id)
@@ -317,7 +319,7 @@ class ProgressRegistry:
             handler.reset()
 
 # Global registry instance
-global_progress_registry: ProgressRegistry = None
+global_progress_registry: ProgressRegistry | None = None
 
 def reset_progress_state(prompt_id: str, dynprompt: "DynamicPrompt") -> None:
     global global_progress_registry

comfy_extras/nodes_v1_test.py

@@ -0,0 +1,77 @@
+import torch
+from comfy.comfy_types.node_typing import ComfyNodeABC, IO
+import asyncio
+from comfy.utils import ProgressBar
+import time
+
+
+class TestNode(ComfyNodeABC):
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "image": (IO.IMAGE,),
+                "some_int": (IO.INT, {"display_name": "new_name",
+                                      "min": 0, "max": 127, "default": 42,
+                                      "tooltip": "My tooltip 😎", "display": "slider"}),
+                "combo": (IO.COMBO, {"options": ["a", "b", "c"], "tooltip": "This is a combo input"}),
+                "combo2": (IO.COMBO, {"options": ["a", "b", "c"], "multi_select": True, "tooltip": "This is a combo input"}),
+            },
+            "optional": {
+                "xyz": ("XYZ",),
+                "mask": (IO.MASK,),
+            }
+        }
+
+    RETURN_TYPES = (IO.INT, IO.IMAGE)
+    RETURN_NAMES = ("INT", "img🖼️")
+    OUTPUT_TOOLTIPS = (None, "This is an image")
+    FUNCTION = "do_thing"
+
+    OUTPUT_NODE = True
+
+    CATEGORY = "v3 nodes"
+
+    def do_thing(self, image: torch.Tensor, some_int: int, combo: str, combo2: list[str], xyz=None, mask: torch.Tensor=None):
+        return (some_int, image)
+
+
+class TestSleep(ComfyNodeABC):
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "value": (IO.ANY, {}),
+                "seconds": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 9999.0, "step": 0.01, "tooltip": "The amount of seconds to sleep."}),
+            },
+            "hidden": {
+                "unique_id": "UNIQUE_ID",
+            },
+        }
+    RETURN_TYPES = (IO.ANY,)
+    FUNCTION = "sleep"
+
+    CATEGORY = "_for_testing"
+
+    async def sleep(self, value, seconds, unique_id):
+        pbar = ProgressBar(seconds, node_id=unique_id)
+        start = time.time()
+        expiration = start + seconds
+        now = start
+        while now < expiration:
+            now = time.time()
+            pbar.update_absolute(now - start)
+            await asyncio.sleep(0.02)
+        return (value,)
+
+
+NODE_CLASS_MAPPINGS = {
+    "V1TestNode1": TestNode,
+    "V1TestSleep": TestSleep,
+}
+
+NODE_DISPLAY_NAME_MAPPINGS = {
+    "V1TestNode1": "V1 Test Node",
+    "V1TestSleep": "V1 Test Sleep",
+}

comfy_extras/nodes_v3_test.py

@@ -0,0 +1,285 @@
+import torch
+import time
+from comfy_api.latest import io, ui, resources, _io
+import logging  # noqa
+import folder_paths
+import comfy.utils
+import comfy.sd
+import asyncio
+
+@io.comfytype(io_type="XYZ")
+class XYZ(io.ComfyTypeIO):
+    Type = tuple[int,str]
+
+
+class V3TestNode(io.ComfyNode):
+    # NOTE: this is here just to test that state is not leaking
+    def __init__(self):
+        super().__init__()
+        self.hahajkunless = ";)"
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="V3_01_TestNode1",
+            display_name="V3 Test Node",
+            category="v3 nodes",
+            description="This is a funky V3 node test.",
+            inputs=[
+                io.Image.Input("image", display_name="new_image"),
+                XYZ.Input("xyz", optional=True),
+                io.Custom("JKL").Input("jkl", optional=True),
+                io.Mask.Input("mask", display_name="mask haha", optional=True),
+                io.Int.Input("some_int", display_name="new_name", min=0, max=127, default=42,
+                             tooltip="My tooltip 😎", display_mode=io.NumberDisplay.slider),
+                io.Combo.Input("combo", options=["a", "b", "c"], tooltip="This is a combo input"),
+                io.MultiCombo.Input("combo2", options=["a","b","c"]),
+                io.MultiType.Input(io.Int.Input("int_multitype", display_name="haha"), types=[io.Float]),
+                io.MultiType.Input("multitype", types=[io.Mask, io.Float, io.Int], optional=True),
+                # ComboInput("combo", image_upload=True, image_folder=FolderType.output,
+                #             remote=RemoteOptions(
+                #                 route="/internal/files/output",
+                #                 refresh_button=True,
+                #             ),
+                #             tooltip="This is a combo input"),
+                # IntegerInput("some_int", display_name="new_name", min=0, tooltip="My tooltip 😎", display=NumberDisplay.slider, ),
+                # ComboDynamicInput("mask", behavior=InputBehavior.optional),
+                # IntegerInput("some_int", display_name="new_name", min=0, tooltip="My tooltip 😎", display=NumberDisplay.slider,
+                #              dependent_inputs=[ComboDynamicInput("mask", behavior=InputBehavior.optional)],
+                #              dependent_values=[lambda my_value: IO.STRING if my_value < 5 else IO.NUMBER],
+                #              ),
+                # ["option1", "option2". "option3"]
+                # ComboDynamicInput["sdfgjhl", [ComboDynamicOptions("option1", [IntegerInput("some_int", display_name="new_name", min=0, tooltip="My tooltip 😎", display=NumberDisplay.slider, ImageInput(), MaskInput(), String()]),
+                #                              CombyDynamicOptons("option2", [])
+                #                                                   ]]
+            ],
+            outputs=[
+                io.Int.Output(),
+                io.Image.Output(display_name="img🖼️", tooltip="This is an image"),
+            ],
+            hidden=[
+                io.Hidden.prompt,
+                io.Hidden.auth_token_comfy_org,
+                io.Hidden.unique_id,
+            ],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def validate_inputs(cls, image: io.Image.Type, some_int: int, combo: io.Combo.Type, combo2: io.MultiCombo.Type, xyz: XYZ.Type=None, mask: io.Mask.Type=None, **kwargs):
+        if some_int < 0:
+            raise Exception("some_int must be greater than 0")
+        if combo == "c":
+            raise Exception("combo must be a or b")
+        return True
+
+    @classmethod
+    def execute(cls, image: io.Image.Type, some_int: int, combo: io.Combo.Type, combo2: io.MultiCombo.Type, xyz: XYZ.Type=None, mask: io.Mask.Type=None, **kwargs):
+        if hasattr(cls, "hahajkunless"):
+            raise Exception("The 'cls' variable leaked instance state between runs!")
+        if hasattr(cls, "doohickey"):
+            raise Exception("The 'cls' variable leaked state on class properties between runs!")
+        try:
+            cls.doohickey = "LOLJK"
+        except AttributeError:
+            pass
+        return io.NodeOutput(some_int, image, ui=ui.PreviewImage(image, cls=cls))
+
+
+class V3LoraLoader(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="V3_LoraLoader",
+            display_name="V3 LoRA Loader",
+            category="v3 nodes",
+            description="LoRAs are used to modify diffusion and CLIP models, altering the way in which latents are denoised such as applying styles. Multiple LoRA nodes can be linked together.",
+            inputs=[
+                io.Model.Input("model", tooltip="The diffusion model the LoRA will be applied to."),
+                io.Clip.Input("clip", tooltip="The CLIP model the LoRA will be applied to."),
+                io.Combo.Input(
+                    "lora_name",
+                    options=folder_paths.get_filename_list("loras"),
+                    tooltip="The name of the LoRA."
+                ),
+                io.Float.Input(
+                    "strength_model",
+                    default=1.0,
+                    min=-100.0,
+                    max=100.0,
+                    step=0.01,
+                    tooltip="How strongly to modify the diffusion model. This value can be negative."
+                ),
+                io.Float.Input(
+                    "strength_clip",
+                    default=1.0,
+                    min=-100.0,
+                    max=100.0,
+                    step=0.01,
+                    tooltip="How strongly to modify the CLIP model. This value can be negative."
+                ),
+            ],
+            outputs=[
+                io.Model.Output(),
+                io.Clip.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model: io.Model.Type, clip: io.Clip.Type, lora_name: str, strength_model: float, strength_clip: float, **kwargs):
+        if strength_model == 0 and strength_clip == 0:
+            return io.NodeOutput(model, clip)
+
+        lora = cls.resources.get(resources.TorchDictFolderFilename("loras", lora_name))
+
+        model_lora, clip_lora = comfy.sd.load_lora_for_models(model, clip, lora, strength_model, strength_clip)
+        return io.NodeOutput(model_lora, clip_lora)
+
+
+class NInputsTest(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="V3_NInputsTest",
+            display_name="V3 N Inputs Test",
+            inputs=[
+                _io.AutogrowDynamic.Input("nmock", template_input=io.Image.Input("image"), min=1, max=3),
+                _io.AutogrowDynamic.Input("nmock2", template_input=io.Int.Input("int"), optional=True, min=1, max=4),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
+
+    @classmethod
+    def validate_inputs(cls, nmock, nmock2):
+        return True
+
+    @classmethod
+    def fingerprint_inputs(cls, nmock, nmock2):
+        return time.time()
+
+    @classmethod
+    def check_lazy_status(cls, **kwargs) -> list[str]:
+        need = [name for name in kwargs if kwargs[name] is None]
+        return need
+
+    @classmethod
+    def execute(cls, nmock, nmock2):
+        first_image = nmock[0]
+        all_images = []
+        for img in nmock:
+            if img.shape != first_image.shape:
+                img = img.movedim(-1,1)
+                img = comfy.utils.common_upscale(img, first_image.shape[2], first_image.shape[1], "lanczos", "center")
+                img = img.movedim(1,-1)
+            all_images.append(img)
+        combined_image = torch.cat(all_images, dim=0)
+        return io.NodeOutput(combined_image)
+
+
+class V3TestSleep(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="V3_TestSleep",
+            display_name="V3 Test Sleep",
+            category="_for_testing",
+            description="Test async sleep functionality.",
+            inputs=[
+                io.AnyType.Input("value", display_name="Value"),
+                io.Float.Input("seconds", display_name="Seconds", default=1.0, min=0.0, max=9999.0, step=0.01, tooltip="The amount of seconds to sleep."),
+            ],
+            outputs=[
+                io.AnyType.Output(),
+            ],
+            hidden=[
+                io.Hidden.unique_id,
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    async def execute(cls, value: io.AnyType.Type, seconds: io.Float.Type, **kwargs):
+        logging.info(f"V3TestSleep: {cls.hidden.unique_id}")
+        pbar = comfy.utils.ProgressBar(seconds, node_id=cls.hidden.unique_id)
+        start = time.time()
+        expiration = start + seconds
+        now = start
+        while now < expiration:
+            now = time.time()
+            pbar.update_absolute(now - start)
+            await asyncio.sleep(0.02)
+        return io.NodeOutput(value)
+
+
+class V3DummyStart(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="V3_DummyStart",
+            display_name="V3 Dummy Start",
+            category="v3 nodes",
+            description="This is a dummy start node.",
+            inputs=[],
+            outputs=[
+                io.Custom("XYZ").Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls):
+        return io.NodeOutput(None)
+
+
+class V3DummyEnd(io.ComfyNode):
+    COOL_VALUE = 123
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="V3_DummyEnd",
+            display_name="V3 Dummy End",
+            category="v3 nodes",
+            description="This is a dummy end node.",
+            inputs=[
+                io.Custom("XYZ").Input("xyz"),
+            ],
+            outputs=[],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def custom_action(cls):
+        return 456
+
+    @classmethod
+    def execute(cls, xyz: io.Custom("XYZ").Type):
+        logging.info(f"V3DummyEnd: {cls.COOL_VALUE}")
+        logging.info(f"V3DummyEnd: {cls.custom_action()}")
+        return
+
+
+class V3DummyEndInherit(V3DummyEnd):
+    @classmethod
+    def define_schema(cls):
+        schema = super().define_schema()
+        schema.node_id = "V3_DummyEndInherit"
+        schema.display_name = "V3 Dummy End Inherit"
+        return schema
+
+    @classmethod
+    def execute(cls, xyz: io.Custom("XYZ").Type):
+        logging.info(f"V3DummyEndInherit: {cls.COOL_VALUE}")
+        return super().execute(xyz)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    V3TestNode,
+    V3LoraLoader,
+    NInputsTest,
+    V3TestSleep,
+    V3DummyStart,
+    V3DummyEnd,
+    V3DummyEndInherit,
+]

comfy_extras/nodes_video.py

@@ -8,9 +8,7 @@ import json
 from typing import Optional, Literal
 from fractions import Fraction
 from comfy.comfy_types import IO, FileLocator, ComfyNodeABC
-from comfy_api.input import ImageInput, AudioInput, VideoInput
-from comfy_api.util import VideoContainer, VideoCodec, VideoComponents
-from comfy_api.input_impl import VideoFromFile, VideoFromComponents
+from comfy_api.latest import Input, InputImpl, Types
 from comfy.cli_args import args
 
 class SaveWEBM:
@@ -91,8 +89,8 @@ class SaveVideo(ComfyNodeABC):
             "required": {
                 "video": (IO.VIDEO, {"tooltip": "The video to save."}),
                 "filename_prefix": ("STRING", {"default": "video/ComfyUI", "tooltip": "The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes."}),
-                "format": (VideoContainer.as_input(), {"default": "auto", "tooltip": "The format to save the video as."}),
-                "codec": (VideoCodec.as_input(), {"default": "auto", "tooltip": "The codec to use for the video."}),
+                "format": (Types.VideoContainer.as_input(), {"default": "auto", "tooltip": "The format to save the video as."}),
+                "codec": (Types.VideoCodec.as_input(), {"default": "auto", "tooltip": "The codec to use for the video."}),
             },
             "hidden": {
                 "prompt": "PROMPT",
@@ -108,7 +106,7 @@ class SaveVideo(ComfyNodeABC):
     CATEGORY = "image/video"
     DESCRIPTION = "Saves the input images to your ComfyUI output directory."
 
-    def save_video(self, video: VideoInput, filename_prefix, format, codec, prompt=None, extra_pnginfo=None):
+    def save_video(self, video: Input.Video, filename_prefix, format, codec, prompt=None, extra_pnginfo=None):
         filename_prefix += self.prefix_append
         width, height = video.get_dimensions()
         full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(
@@ -127,7 +125,7 @@ class SaveVideo(ComfyNodeABC):
                 metadata["prompt"] = prompt
             if len(metadata) > 0:
                 saved_metadata = metadata
-        file = f"{filename}_{counter:05}_.{VideoContainer.get_extension(format)}"
+        file = f"{filename}_{counter:05}_.{Types.VideoContainer.get_extension(format)}"
         video.save_to(
             os.path.join(full_output_folder, file),
             format=format,
@@ -163,9 +161,9 @@ class CreateVideo(ComfyNodeABC):
     CATEGORY = "image/video"
     DESCRIPTION = "Create a video from images."
 
-    def create_video(self, images: ImageInput, fps: float, audio: Optional[AudioInput] = None):
-        return (VideoFromComponents(
-            VideoComponents(
+    def create_video(self, images: Input.Image, fps: float, audio: Optional[Input.Audio] = None):
+        return (InputImpl.VideoFromComponents(
+            Types.VideoComponents(
             images=images,
             audio=audio,
             frame_rate=Fraction(fps),
@@ -187,7 +185,7 @@ class GetVideoComponents(ComfyNodeABC):
     CATEGORY = "image/video"
     DESCRIPTION = "Extracts all components from a video: frames, audio, and framerate."
 
-    def get_components(self, video: VideoInput):
+    def get_components(self, video: Input.Video):
         components = video.get_components()
 
         return (components.images, components.audio, float(components.frame_rate))
@@ -208,7 +206,7 @@ class LoadVideo(ComfyNodeABC):
     FUNCTION = "load_video"
     def load_video(self, file):
         video_path = folder_paths.get_annotated_filepath(file)
-        return (VideoFromFile(video_path),)
+        return (InputImpl.VideoFromFile(video_path),)
 
     @classmethod
     def IS_CHANGED(cls, file):
@@ -239,3 +237,4 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "GetVideoComponents": "Get Video Components",
     "LoadVideo": "Load Video",
 }
+

comfy_extras/v3/nodes_ace.py

@@ -0,0 +1,57 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.model_management
+import node_helpers
+from comfy_api.latest import io
+
+
+class TextEncodeAceStepAudio(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="TextEncodeAceStepAudio_V3",
+            category="conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("tags", multiline=True, dynamic_prompts=True),
+                io.String.Input("lyrics", multiline=True, dynamic_prompts=True),
+                io.Float.Input("lyrics_strength", default=1.0, min=0.0, max=10.0, step=0.01),
+            ],
+            outputs=[io.Conditioning.Output()],
+        )
+
+    @classmethod
+    def execute(cls, clip, tags, lyrics, lyrics_strength) -> io.NodeOutput:
+        conditioning = clip.encode_from_tokens_scheduled(clip.tokenize(tags, lyrics=lyrics))
+        conditioning = node_helpers.conditioning_set_values(conditioning, {"lyrics_strength": lyrics_strength})
+        return io.NodeOutput(conditioning)
+
+
+class EmptyAceStepLatentAudio(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="EmptyAceStepLatentAudio_V3",
+            category="latent/audio",
+            inputs=[
+                io.Float.Input("seconds", default=120.0, min=1.0, max=1000.0, step=0.1),
+                io.Int.Input(
+                    "batch_size", default=1, min=1, max=4096, tooltip="The number of latent images in the batch."
+                ),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, seconds, batch_size) -> io.NodeOutput:
+        length = int(seconds * 44100 / 512 / 8)
+        latent = torch.zeros([batch_size, 8, 16, length], device=comfy.model_management.intermediate_device())
+        return io.NodeOutput({"samples": latent, "type": "audio"})
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    EmptyAceStepLatentAudio,
+    TextEncodeAceStepAudio,
+]

comfy_extras/v3/nodes_advanced_samplers.py

@@ -0,0 +1,128 @@
+import numpy as np
+import torch
+from tqdm.auto import trange
+
+import comfy.model_patcher
+import comfy.samplers
+import comfy.utils
+from comfy.k_diffusion.sampling import to_d
+from comfy_api.latest import io
+
+
+@torch.no_grad()
+def sample_lcm_upscale(
+    model, x, sigmas, extra_args=None, callback=None, disable=None, total_upscale=2.0, upscale_method="bislerp", upscale_steps=None
+):
+    extra_args = {} if extra_args is None else extra_args
+
+    if upscale_steps is None:
+        upscale_steps = max(len(sigmas) // 2 + 1, 2)
+    else:
+        upscale_steps += 1
+        upscale_steps = min(upscale_steps, len(sigmas) + 1)
+
+    upscales = np.linspace(1.0, total_upscale, upscale_steps)[1:]
+
+    orig_shape = x.size()
+    s_in = x.new_ones([x.shape[0]])
+    for i in trange(len(sigmas) - 1, disable=disable):
+        denoised = model(x, sigmas[i] * s_in, **extra_args)
+        if callback is not None:
+            callback({"x": x, "i": i, "sigma": sigmas[i], "sigma_hat": sigmas[i], "denoised": denoised})
+
+        x = denoised
+        if i < len(upscales):
+            x = comfy.utils.common_upscale(
+                x, round(orig_shape[-1] * upscales[i]), round(orig_shape[-2] * upscales[i]), upscale_method, "disabled"
+            )
+
+        if sigmas[i + 1] > 0:
+            x += sigmas[i + 1] * torch.randn_like(x)
+    return x
+
+
+class SamplerLCMUpscale(io.ComfyNode):
+    UPSCALE_METHODS = ["bislerp", "nearest-exact", "bilinear", "area", "bicubic"]
+
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="SamplerLCMUpscale_V3",
+            category="sampling/custom_sampling/samplers",
+            inputs=[
+                io.Float.Input("scale_ratio", default=1.0, min=0.1, max=20.0, step=0.01),
+                io.Int.Input("scale_steps", default=-1, min=-1, max=1000, step=1),
+                io.Combo.Input("upscale_method", options=cls.UPSCALE_METHODS),
+            ],
+            outputs=[io.Sampler.Output()],
+        )
+
+    @classmethod
+    def execute(cls, scale_ratio, scale_steps, upscale_method) -> io.NodeOutput:
+        if scale_steps < 0:
+            scale_steps = None
+        sampler = comfy.samplers.KSAMPLER(
+            sample_lcm_upscale,
+            extra_options={
+                "total_upscale": scale_ratio,
+                "upscale_steps": scale_steps,
+                "upscale_method": upscale_method,
+            },
+        )
+        return io.NodeOutput(sampler)
+
+
+@torch.no_grad()
+def sample_euler_pp(model, x, sigmas, extra_args=None, callback=None, disable=None):
+    extra_args = {} if extra_args is None else extra_args
+
+    temp = [0]
+
+    def post_cfg_function(args):
+        temp[0] = args["uncond_denoised"]
+        return args["denoised"]
+
+    model_options = extra_args.get("model_options", {}).copy()
+    extra_args["model_options"] = comfy.model_patcher.set_model_options_post_cfg_function(
+        model_options, post_cfg_function, disable_cfg1_optimization=True
+    )
+
+    s_in = x.new_ones([x.shape[0]])
+    for i in trange(len(sigmas) - 1, disable=disable):
+        sigma_hat = sigmas[i]
+        denoised = model(x, sigma_hat * s_in, **extra_args)
+        d = to_d(x - denoised + temp[0], sigmas[i], denoised)
+        if callback is not None:
+            callback({"x": x, "i": i, "sigma": sigmas[i], "sigma_hat": sigma_hat, "denoised": denoised})
+        dt = sigmas[i + 1] - sigma_hat
+        x = x + d * dt
+    return x
+
+
+class SamplerEulerCFGpp(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="SamplerEulerCFGpp_V3",
+            display_name="SamplerEulerCFG++ _V3",
+            category="_for_testing",
+            inputs=[
+                io.Combo.Input("version", options=["regular", "alternative"]),
+            ],
+            outputs=[io.Sampler.Output()],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, version) -> io.NodeOutput:
+        if version == "alternative":
+            sampler = comfy.samplers.KSAMPLER(sample_euler_pp)
+        else:
+            sampler = comfy.samplers.ksampler("euler_cfg_pp")
+        return io.NodeOutput(sampler)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    SamplerEulerCFGpp,
+    SamplerLCMUpscale,
+]

comfy_extras/v3/nodes_align_your_steps.py

@@ -0,0 +1,84 @@
+# from: https://research.nvidia.com/labs/toronto-ai/AlignYourSteps/howto.html
+
+import numpy as np
+import torch
+
+from comfy_api.latest import io
+
+
+def loglinear_interp(t_steps, num_steps):
+    """Performs log-linear interpolation of a given array of decreasing numbers."""
+    xs = np.linspace(0, 1, len(t_steps))
+    ys = np.log(t_steps[::-1])
+
+    new_xs = np.linspace(0, 1, num_steps)
+    new_ys = np.interp(new_xs, xs, ys)
+
+    return np.exp(new_ys)[::-1].copy()
+
+
+NOISE_LEVELS = {
+    "SD1": [
+        14.6146412293,
+        6.4745760956,
+        3.8636745985,
+        2.6946151520,
+        1.8841921177,
+        1.3943805092,
+        0.9642583904,
+        0.6523686016,
+        0.3977456272,
+        0.1515232662,
+        0.0291671582,
+    ],
+    "SDXL": [
+        14.6146412293,
+        6.3184485287,
+        3.7681790315,
+        2.1811480769,
+        1.3405244945,
+        0.8620721141,
+        0.5550693289,
+        0.3798540708,
+        0.2332364134,
+        0.1114188177,
+        0.0291671582,
+    ],
+    "SVD": [700.00, 54.5, 15.886, 7.977, 4.248, 1.789, 0.981, 0.403, 0.173, 0.034, 0.002],
+}
+
+
+class AlignYourStepsScheduler(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="AlignYourStepsScheduler_V3",
+            category="sampling/custom_sampling/schedulers",
+            inputs=[
+                io.Combo.Input("model_type", options=["SD1", "SDXL", "SVD"]),
+                io.Int.Input("steps", default=10, min=1, max=10000),
+                io.Float.Input("denoise", default=1.0, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[io.Sigmas.Output()],
+        )
+
+    @classmethod
+    def execute(cls, model_type, steps, denoise) -> io.NodeOutput:
+        total_steps = steps
+        if denoise < 1.0:
+            if denoise <= 0.0:
+                return io.NodeOutput(torch.FloatTensor([]))
+            total_steps = round(steps * denoise)
+
+        sigmas = NOISE_LEVELS[model_type][:]
+        if (steps + 1) != len(sigmas):
+            sigmas = loglinear_interp(sigmas, steps + 1)
+
+        sigmas = sigmas[-(total_steps + 1) :]
+        sigmas[-1] = 0
+        return io.NodeOutput(torch.FloatTensor(sigmas))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    AlignYourStepsScheduler,
+]

comfy_extras/v3/nodes_apg.py

@@ -0,0 +1,98 @@
+import torch
+
+from comfy_api.latest import io
+
+
+def project(v0, v1):
+    v1 = torch.nn.functional.normalize(v1, dim=[-1, -2, -3])
+    v0_parallel = (v0 * v1).sum(dim=[-1, -2, -3], keepdim=True) * v1
+    v0_orthogonal = v0 - v0_parallel
+    return v0_parallel, v0_orthogonal
+
+
+class APG(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="APG_V3",
+            display_name="Adaptive Projected Guidance _V3",
+            category="sampling/custom_sampling",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input(
+                    "eta",
+                    default=1.0,
+                    min=-10.0,
+                    max=10.0,
+                    step=0.01,
+                    tooltip="Controls the scale of the parallel guidance vector. Default CFG behavior at a setting of 1.",
+                ),
+                io.Float.Input(
+                    "norm_threshold",
+                    default=5.0,
+                    min=0.0,
+                    max=50.0,
+                    step=0.1,
+                    tooltip="Normalize guidance vector to this value, normalization disable at a setting of 0.",
+                ),
+                io.Float.Input(
+                    "momentum",
+                    default=0.0,
+                    min=-5.0,
+                    max=1.0,
+                    step=0.01,
+                    tooltip="Controls a running average of guidance during diffusion, disabled at a setting of 0.",
+                ),
+            ],
+            outputs=[io.Model.Output()],
+        )
+
+    @classmethod
+    def execute(cls, model, eta, norm_threshold, momentum) -> io.NodeOutput:
+        running_avg = 0
+        prev_sigma = None
+
+        def pre_cfg_function(args):
+            nonlocal running_avg, prev_sigma
+
+            if len(args["conds_out"]) == 1:
+                return args["conds_out"]
+
+            cond = args["conds_out"][0]
+            uncond = args["conds_out"][1]
+            sigma = args["sigma"][0]
+            cond_scale = args["cond_scale"]
+
+            if prev_sigma is not None and sigma > prev_sigma:
+                running_avg = 0
+            prev_sigma = sigma
+
+            guidance = cond - uncond
+
+            if momentum != 0:
+                if not torch.is_tensor(running_avg):
+                    running_avg = guidance
+                else:
+                    running_avg = momentum * running_avg + guidance
+                guidance = running_avg
+
+            if norm_threshold > 0:
+                guidance_norm = guidance.norm(p=2, dim=[-1, -2, -3], keepdim=True)
+                scale = torch.minimum(torch.ones_like(guidance_norm), norm_threshold / guidance_norm)
+                guidance = guidance * scale
+
+            guidance_parallel, guidance_orthogonal = project(guidance, cond)
+            modified_guidance = guidance_orthogonal + eta * guidance_parallel
+
+            modified_cond = (uncond + modified_guidance) + (cond - uncond) / cond_scale
+
+            return [modified_cond, uncond] + args["conds_out"][2:]
+
+        m = model.clone()
+        m.set_model_sampler_pre_cfg_function(pre_cfg_function)
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    APG,
+]

comfy_extras/v3/nodes_attention_multiply.py

@@ -0,0 +1,139 @@
+from comfy_api.latest import io
+
+
+def attention_multiply(attn, model, q, k, v, out):
+    m = model.clone()
+    sd = model.model_state_dict()
+
+    for key in sd:
+        if key.endswith("{}.to_q.bias".format(attn)) or key.endswith("{}.to_q.weight".format(attn)):
+            m.add_patches({key: (None,)}, 0.0, q)
+        if key.endswith("{}.to_k.bias".format(attn)) or key.endswith("{}.to_k.weight".format(attn)):
+            m.add_patches({key: (None,)}, 0.0, k)
+        if key.endswith("{}.to_v.bias".format(attn)) or key.endswith("{}.to_v.weight".format(attn)):
+            m.add_patches({key: (None,)}, 0.0, v)
+        if key.endswith("{}.to_out.0.bias".format(attn)) or key.endswith("{}.to_out.0.weight".format(attn)):
+            m.add_patches({key: (None,)}, 0.0, out)
+    return m
+
+
+class UNetSelfAttentionMultiply(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="UNetSelfAttentionMultiply_V3",
+            category="_for_testing/attention_experiments",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("q", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("k", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("v", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("out", default=1.0, min=0.0, max=10.0, step=0.01),
+            ],
+            outputs=[io.Model.Output()],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model, q, k, v, out) -> io.NodeOutput:
+        return io.NodeOutput(attention_multiply("attn1", model, q, k, v, out))
+
+
+class UNetCrossAttentionMultiply(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="UNetCrossAttentionMultiply_V3",
+            category="_for_testing/attention_experiments",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("q", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("k", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("v", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("out", default=1.0, min=0.0, max=10.0, step=0.01),
+            ],
+            outputs=[io.Model.Output()],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model, q, k, v, out) -> io.NodeOutput:
+        return io.NodeOutput(attention_multiply("attn2", model, q, k, v, out))
+
+
+class CLIPAttentionMultiply(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="CLIPAttentionMultiply_V3",
+            category="_for_testing/attention_experiments",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.Float.Input("q", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("k", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("v", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("out", default=1.0, min=0.0, max=10.0, step=0.01),
+            ],
+            outputs=[io.Clip.Output()],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, clip, q, k, v, out) -> io.NodeOutput:
+        m = clip.clone()
+        sd = m.patcher.model_state_dict()
+
+        for key in sd:
+            if key.endswith("self_attn.q_proj.weight") or key.endswith("self_attn.q_proj.bias"):
+                m.add_patches({key: (None,)}, 0.0, q)
+            if key.endswith("self_attn.k_proj.weight") or key.endswith("self_attn.k_proj.bias"):
+                m.add_patches({key: (None,)}, 0.0, k)
+            if key.endswith("self_attn.v_proj.weight") or key.endswith("self_attn.v_proj.bias"):
+                m.add_patches({key: (None,)}, 0.0, v)
+            if key.endswith("self_attn.out_proj.weight") or key.endswith("self_attn.out_proj.bias"):
+                m.add_patches({key: (None,)}, 0.0, out)
+        return io.NodeOutput(m)
+
+
+class UNetTemporalAttentionMultiply(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="UNetTemporalAttentionMultiply_V3",
+            category="_for_testing/attention_experiments",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("self_structural", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("self_temporal", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("cross_structural", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("cross_temporal", default=1.0, min=0.0, max=10.0, step=0.01),
+            ],
+            outputs=[io.Model.Output()],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model, self_structural, self_temporal, cross_structural, cross_temporal) -> io.NodeOutput:
+        m = model.clone()
+        sd = model.model_state_dict()
+
+        for k in sd:
+            if (k.endswith("attn1.to_out.0.bias") or k.endswith("attn1.to_out.0.weight")):
+                if '.time_stack.' in k:
+                    m.add_patches({k: (None,)}, 0.0, self_temporal)
+                else:
+                    m.add_patches({k: (None,)}, 0.0, self_structural)
+            elif (k.endswith("attn2.to_out.0.bias") or k.endswith("attn2.to_out.0.weight")):
+                if '.time_stack.' in k:
+                    m.add_patches({k: (None,)}, 0.0, cross_temporal)
+                else:
+                    m.add_patches({k: (None,)}, 0.0, cross_structural)
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CLIPAttentionMultiply,
+    UNetCrossAttentionMultiply,
+    UNetSelfAttentionMultiply,
+    UNetTemporalAttentionMultiply,
+]

comfy_extras/v3/nodes_audio.py

@@ -0,0 +1,290 @@
+from __future__ import annotations
+
+import hashlib
+import os
+
+import av
+import torch
+import torchaudio
+
+import comfy.model_management
+import folder_paths
+import node_helpers
+from comfy_api.latest import io, ui
+
+
+class EmptyLatentAudio(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="EmptyLatentAudio_V3",
+            category="latent/audio",
+            inputs=[
+                io.Float.Input("seconds", default=47.6, min=1.0, max=1000.0, step=0.1),
+                io.Int.Input(
+                    "batch_size", default=1, min=1, max=4096, tooltip="The number of latent images in the batch."
+                ),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, seconds, batch_size) -> io.NodeOutput:
+        length = round((seconds * 44100 / 2048) / 2) * 2
+        latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device())
+        return io.NodeOutput({"samples": latent, "type": "audio"})
+
+
+class ConditioningStableAudio(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ConditioningStableAudio_V3",
+            category="conditioning",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Float.Input("seconds_start", default=0.0, min=0.0, max=1000.0, step=0.1),
+                io.Float.Input("seconds_total", default=47.0, min=0.0, max=1000.0, step=0.1),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, positive, negative, seconds_start, seconds_total) -> io.NodeOutput:
+        return io.NodeOutput(
+            node_helpers.conditioning_set_values(
+                positive, {"seconds_start": seconds_start, "seconds_total": seconds_total}
+            ),
+            node_helpers.conditioning_set_values(
+                negative, {"seconds_start": seconds_start, "seconds_total": seconds_total}
+            ),
+        )
+
+
+class VAEEncodeAudio(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="VAEEncodeAudio_V3",
+            category="latent/audio",
+            inputs=[
+                io.Audio.Input("audio"),
+                io.Vae.Input("vae"),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, vae, audio) -> io.NodeOutput:
+        sample_rate = audio["sample_rate"]
+        if 44100 != sample_rate:
+            waveform = torchaudio.functional.resample(audio["waveform"], sample_rate, 44100)
+        else:
+            waveform = audio["waveform"]
+        return io.NodeOutput({"samples": vae.encode(waveform.movedim(1, -1))})
+
+
+class VAEDecodeAudio(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="VAEDecodeAudio_V3",
+            category="latent/audio",
+            inputs=[
+                io.Latent.Input("samples"),
+                io.Vae.Input("vae"),
+            ],
+            outputs=[io.Audio.Output()],
+        )
+
+    @classmethod
+    def execute(cls, vae, samples) -> io.NodeOutput:
+        audio = vae.decode(samples["samples"]).movedim(-1, 1)
+        std = torch.std(audio, dim=[1, 2], keepdim=True) * 5.0
+        std[std < 1.0] = 1.0
+        audio /= std
+        return io.NodeOutput({"waveform": audio, "sample_rate": 44100})
+
+
+class SaveAudio(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SaveAudio_V3",  # frontend expects "SaveAudio" to work
+            display_name="Save Audio _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Audio.Input("audio"),
+                io.String.Input("filename_prefix", default="audio/ComfyUI"),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, audio, filename_prefix="ComfyUI", format="flac") -> io.NodeOutput:
+        return io.NodeOutput(
+            ui=ui.AudioSaveHelper.get_save_audio_ui(audio, filename_prefix=filename_prefix, cls=cls, format=format)
+        )
+
+
+class SaveAudioMP3(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SaveAudioMP3_V3",  # frontend expects "SaveAudioMP3" to work
+            display_name="Save Audio(MP3) _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Audio.Input("audio"),
+                io.String.Input("filename_prefix", default="audio/ComfyUI"),
+                io.Combo.Input("quality", options=["V0", "128k", "320k"], default="V0"),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, audio, filename_prefix="ComfyUI", format="mp3", quality="V0") -> io.NodeOutput:
+        return io.NodeOutput(
+            ui=ui.AudioSaveHelper.get_save_audio_ui(
+                audio, filename_prefix=filename_prefix, cls=cls, format=format, quality=quality
+            )
+        )
+
+
+class SaveAudioOpus(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SaveAudioOpus_V3",  # frontend expects "SaveAudioOpus" to work
+            display_name="Save Audio(Opus) _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Audio.Input("audio"),
+                io.String.Input("filename_prefix", default="audio/ComfyUI"),
+                io.Combo.Input("quality", options=["64k", "96k", "128k", "192k", "320k"], default="128k"),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, audio, filename_prefix="ComfyUI", format="opus", quality="128k") -> io.NodeOutput:
+        return io.NodeOutput(
+            ui=ui.AudioSaveHelper.get_save_audio_ui(
+                audio, filename_prefix=filename_prefix, cls=cls, format=format, quality=quality
+            )
+        )
+
+
+class PreviewAudio(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PreviewAudio_V3",  # frontend expects "PreviewAudio" to work
+            display_name="Preview Audio _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Audio.Input("audio"),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, audio) -> io.NodeOutput:
+        return io.NodeOutput(ui=ui.PreviewAudio(audio, cls=cls))
+
+
+class LoadAudio(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LoadAudio_V3",  # frontend expects "LoadAudio" to work
+            display_name="Load Audio _V3",  # frontend ignores "display_name" for this node
+            category="audio",
+            inputs=[
+                io.Combo.Input("audio", upload=io.UploadType.audio, options=cls.get_files_options()),
+            ],
+            outputs=[io.Audio.Output()],
+        )
+
+    @classmethod
+    def get_files_options(cls) -> list[str]:
+        input_dir = folder_paths.get_input_directory()
+        return sorted(folder_paths.filter_files_content_types(os.listdir(input_dir), ["audio", "video"]))
+
+    @classmethod
+    def load(cls, filepath: str) -> tuple[torch.Tensor, int]:
+        with av.open(filepath) as af:
+            if not af.streams.audio:
+                raise ValueError("No audio stream found in the file.")
+
+            stream = af.streams.audio[0]
+            sr = stream.codec_context.sample_rate
+            n_channels = stream.channels
+
+            frames = []
+            length = 0
+            for frame in af.decode(streams=stream.index):
+                buf = torch.from_numpy(frame.to_ndarray())
+                if buf.shape[0] != n_channels:
+                    buf = buf.view(-1, n_channels).t()
+
+                frames.append(buf)
+                length += buf.shape[1]
+
+            if not frames:
+                raise ValueError("No audio frames decoded.")
+
+            wav = torch.cat(frames, dim=1)
+            wav = cls.f32_pcm(wav)
+            return wav, sr
+
+    @classmethod
+    def f32_pcm(cls, wav: torch.Tensor) -> torch.Tensor:
+        """Convert audio to float 32 bits PCM format."""
+        if wav.dtype.is_floating_point:
+            return wav
+        elif wav.dtype == torch.int16:
+            return wav.float() / (2 ** 15)
+        elif wav.dtype == torch.int32:
+            return wav.float() / (2 ** 31)
+        raise ValueError(f"Unsupported wav dtype: {wav.dtype}")
+
+    @classmethod
+    def execute(cls, audio) -> io.NodeOutput:
+        waveform, sample_rate = cls.load(folder_paths.get_annotated_filepath(audio))
+        return io.NodeOutput({"waveform": waveform.unsqueeze(0), "sample_rate": sample_rate})
+
+    @classmethod
+    def fingerprint_inputs(s, audio):
+        image_path = folder_paths.get_annotated_filepath(audio)
+        m = hashlib.sha256()
+        with open(image_path, "rb") as f:
+            m.update(f.read())
+        return m.digest().hex()
+
+    @classmethod
+    def validate_inputs(s, audio):
+        if not folder_paths.exists_annotated_filepath(audio):
+            return "Invalid audio file: {}".format(audio)
+        return True
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    ConditioningStableAudio,
+    EmptyLatentAudio,
+    LoadAudio,
+    PreviewAudio,
+    SaveAudio,
+    SaveAudioMP3,
+    SaveAudioOpus,
+    VAEDecodeAudio,
+    VAEEncodeAudio,
+]

comfy_extras/v3/nodes_camera_trajectory.py

@@ -0,0 +1,217 @@
+from __future__ import annotations
+
+import numpy as np
+import torch
+from einops import rearrange
+
+import comfy.model_management
+import nodes
+from comfy_api.latest import io
+
+CAMERA_DICT = {
+    "base_T_norm": 1.5,
+    "base_angle": np.pi / 3,
+    "Static": {"angle": [0.0, 0.0, 0.0], "T": [0.0, 0.0, 0.0]},
+    "Pan Up": {"angle": [0.0, 0.0, 0.0], "T": [0.0, -1.0, 0.0]},
+    "Pan Down": {"angle": [0.0, 0.0, 0.0], "T": [0.0, 1.0, 0.0]},
+    "Pan Left": {"angle": [0.0, 0.0, 0.0], "T": [-1.0, 0.0, 0.0]},
+    "Pan Right": {"angle": [0.0, 0.0, 0.0], "T": [1.0, 0.0, 0.0]},
+    "Zoom In": {"angle": [0.0, 0.0, 0.0], "T": [0.0, 0.0, 2.0]},
+    "Zoom Out": {"angle": [0.0, 0.0, 0.0], "T": [0.0, 0.0, -2.0]},
+    "Anti Clockwise (ACW)": {"angle": [0.0, 0.0, -1.0], "T": [0.0, 0.0, 0.0]},
+    "ClockWise (CW)": {"angle": [0.0, 0.0, 1.0], "T": [0.0, 0.0, 0.0]},
+}
+
+
+def process_pose_params(cam_params, width=672, height=384, original_pose_width=1280, original_pose_height=720, device="cpu"):
+    def get_relative_pose(cam_params):
+        """Copied from https://github.com/hehao13/CameraCtrl/blob/main/inference.py"""
+        abs_w2cs = [cam_param.w2c_mat for cam_param in cam_params]
+        abs_c2ws = [cam_param.c2w_mat for cam_param in cam_params]
+        cam_to_origin = 0
+        target_cam_c2w = np.array([[1, 0, 0, 0], [0, 1, 0, -cam_to_origin], [0, 0, 1, 0], [0, 0, 0, 1]])
+        abs2rel = target_cam_c2w @ abs_w2cs[0]
+        ret_poses = [target_cam_c2w] + [abs2rel @ abs_c2w for abs_c2w in abs_c2ws[1:]]
+        return np.array(ret_poses, dtype=np.float32)
+
+    """Modified from https://github.com/hehao13/CameraCtrl/blob/main/inference.py"""
+    cam_params = [Camera(cam_param) for cam_param in cam_params]
+
+    sample_wh_ratio = width / height
+    pose_wh_ratio = original_pose_width / original_pose_height  # Assuming placeholder ratios, change as needed
+
+    if pose_wh_ratio > sample_wh_ratio:
+        resized_ori_w = height * pose_wh_ratio
+        for cam_param in cam_params:
+            cam_param.fx = resized_ori_w * cam_param.fx / width
+    else:
+        resized_ori_h = width / pose_wh_ratio
+        for cam_param in cam_params:
+            cam_param.fy = resized_ori_h * cam_param.fy / height
+
+    intrinsic = np.asarray(
+        [[cam_param.fx * width, cam_param.fy * height, cam_param.cx * width, cam_param.cy * height] for cam_param in cam_params],
+        dtype=np.float32,
+    )
+
+    K = torch.as_tensor(intrinsic)[None]  # [1, 1, 4]
+    c2ws = get_relative_pose(cam_params)  # Assuming this function is defined elsewhere
+    c2ws = torch.as_tensor(c2ws)[None]  # [1, n_frame, 4, 4]
+    plucker_embedding = ray_condition(K, c2ws, height, width, device=device)[0].permute(0, 3, 1, 2).contiguous()  # V, 6, H, W
+    plucker_embedding = plucker_embedding[None]
+    return rearrange(plucker_embedding, "b f c h w -> b f h w c")[0]
+
+
+class Camera:
+    """Copied from https://github.com/hehao13/CameraCtrl/blob/main/inference.py"""
+
+    def __init__(self, entry):
+        fx, fy, cx, cy = entry[1:5]
+        self.fx = fx
+        self.fy = fy
+        self.cx = cx
+        self.cy = cy
+        c2w_mat = np.array(entry[7:]).reshape(4, 4)
+        self.c2w_mat = c2w_mat
+        self.w2c_mat = np.linalg.inv(c2w_mat)
+
+
+def ray_condition(K, c2w, H, W, device):
+    """Copied from https://github.com/hehao13/CameraCtrl/blob/main/inference.py"""
+    # c2w: B, V, 4, 4
+    # K: B, V, 4
+
+    B = K.shape[0]
+
+    j, i = torch.meshgrid(
+        torch.linspace(0, H - 1, H, device=device, dtype=c2w.dtype),
+        torch.linspace(0, W - 1, W, device=device, dtype=c2w.dtype),
+        indexing="ij",
+    )
+    i = i.reshape([1, 1, H * W]).expand([B, 1, H * W]) + 0.5  # [B, HxW]
+    j = j.reshape([1, 1, H * W]).expand([B, 1, H * W]) + 0.5  # [B, HxW]
+
+    fx, fy, cx, cy = K.chunk(4, dim=-1)  # B,V, 1
+
+    zs = torch.ones_like(i)  # [B, HxW]
+    xs = (i - cx) / fx * zs
+    ys = (j - cy) / fy * zs
+    zs = zs.expand_as(ys)
+
+    directions = torch.stack((xs, ys, zs), dim=-1)  # B, V, HW, 3
+    directions = directions / directions.norm(dim=-1, keepdim=True)  # B, V, HW, 3
+
+    rays_d = directions @ c2w[..., :3, :3].transpose(-1, -2)  # B, V, 3, HW
+    rays_o = c2w[..., :3, 3]  # B, V, 3
+    rays_o = rays_o[:, :, None].expand_as(rays_d)  # B, V, 3, HW
+    # c2w @ dirctions
+    rays_dxo = torch.cross(rays_o, rays_d)
+    plucker = torch.cat([rays_dxo, rays_d], dim=-1)
+    plucker = plucker.reshape(B, c2w.shape[1], H, W, 6)  # B, V, H, W, 6
+    # plucker = plucker.permute(0, 1, 4, 2, 3)
+    return plucker
+
+
+def get_camera_motion(angle, T, speed, n=81):
+    def compute_R_form_rad_angle(angles):
+        theta_x, theta_y, theta_z = angles
+        Rx = np.array([[1, 0, 0], [0, np.cos(theta_x), -np.sin(theta_x)], [0, np.sin(theta_x), np.cos(theta_x)]])
+
+        Ry = np.array([[np.cos(theta_y), 0, np.sin(theta_y)], [0, 1, 0], [-np.sin(theta_y), 0, np.cos(theta_y)]])
+
+        Rz = np.array([[np.cos(theta_z), -np.sin(theta_z), 0], [np.sin(theta_z), np.cos(theta_z), 0], [0, 0, 1]])
+
+        R = np.dot(Rz, np.dot(Ry, Rx))
+        return R
+
+    RT = []
+    for i in range(n):
+        _angle = (i / n) * speed * (CAMERA_DICT["base_angle"]) * angle
+        R = compute_R_form_rad_angle(_angle)
+        _T = (i / n) * speed * (CAMERA_DICT["base_T_norm"]) * (T.reshape(3, 1))
+        _RT = np.concatenate([R, _T], axis=1)
+        RT.append(_RT)
+    RT = np.stack(RT)
+    return RT
+
+
+class WanCameraEmbedding(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="WanCameraEmbedding_V3",
+            category="camera",
+            inputs=[
+                io.Combo.Input(
+                    "camera_pose",
+                    options=[
+                        "Static",
+                        "Pan Up",
+                        "Pan Down",
+                        "Pan Left",
+                        "Pan Right",
+                        "Zoom In",
+                        "Zoom Out",
+                        "Anti Clockwise (ACW)",
+                        "ClockWise (CW)",
+                    ],
+                    default="Static",
+                ),
+                io.Int.Input("width", default=832, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("height", default=480, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("length", default=81, min=1, max=nodes.MAX_RESOLUTION, step=4),
+                io.Float.Input("speed", default=1.0, min=0, max=10.0, step=0.1, optional=True),
+                io.Float.Input("fx", default=0.5, min=0, max=1, step=0.000000001, optional=True),
+                io.Float.Input("fy", default=0.5, min=0, max=1, step=0.000000001, optional=True),
+                io.Float.Input("cx", default=0.5, min=0, max=1, step=0.01, optional=True),
+                io.Float.Input("cy", default=0.5, min=0, max=1, step=0.01, optional=True),
+            ],
+            outputs=[
+                io.WanCameraEmbedding.Output(display_name="camera_embedding"),
+                io.Int.Output(display_name="width"),
+                io.Int.Output(display_name="height"),
+                io.Int.Output(display_name="length"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, camera_pose, width, height, length, speed=1.0, fx=0.5, fy=0.5, cx=0.5, cy=0.5) -> io.NodeOutput:
+        """
+        Use Camera trajectory as extrinsic parameters to calculate Plücker embeddings (Sitzmannet al., 2021)
+        Adapted from https://github.com/aigc-apps/VideoX-Fun/blob/main/comfyui/comfyui_nodes.py
+        """
+        motion_list = [camera_pose]
+        speed = speed
+        angle = np.array(CAMERA_DICT[motion_list[0]]["angle"])
+        T = np.array(CAMERA_DICT[motion_list[0]]["T"])
+        RT = get_camera_motion(angle, T, speed, length)
+
+        trajs = []
+        for cp in RT.tolist():
+            traj = [fx, fy, cx, cy, 0, 0]
+            traj.extend(cp[0])
+            traj.extend(cp[1])
+            traj.extend(cp[2])
+            traj.extend([0, 0, 0, 1])
+            trajs.append(traj)
+
+        cam_params = np.array([[float(x) for x in pose] for pose in trajs])
+        cam_params = np.concatenate([np.zeros_like(cam_params[:, :1]), cam_params], 1)
+        control_camera_video = process_pose_params(cam_params, width=width, height=height)
+        control_camera_video = control_camera_video.permute([3, 0, 1, 2]).unsqueeze(0).to(device=comfy.model_management.intermediate_device())
+
+        control_camera_video = torch.concat(
+            [torch.repeat_interleave(control_camera_video[:, :, 0:1], repeats=4, dim=2), control_camera_video[:, :, 1:]], dim=2
+        ).transpose(1, 2)
+
+        # Reshape, transpose, and view into desired shape
+        b, f, c, h, w = control_camera_video.shape
+        control_camera_video = control_camera_video.contiguous().view(b, f // 4, 4, c, h, w).transpose(2, 3)
+        control_camera_video = control_camera_video.contiguous().view(b, f // 4, c * 4, h, w).transpose(1, 2)
+
+        return io.NodeOutput(control_camera_video, width, height, length)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    WanCameraEmbedding,
+]

comfy_extras/v3/nodes_canny.py

@@ -0,0 +1,32 @@
+from __future__ import annotations
+
+from kornia.filters import canny
+
+import comfy.model_management
+from comfy_api.latest import io
+
+
+class Canny(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Canny_V3",
+            category="image/preprocessors",
+            inputs=[
+                io.Image.Input("image"),
+                io.Float.Input("low_threshold", default=0.4, min=0.01, max=0.99, step=0.01),
+                io.Float.Input("high_threshold", default=0.8, min=0.01, max=0.99, step=0.01),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, low_threshold, high_threshold) -> io.NodeOutput:
+        output = canny(image.to(comfy.model_management.get_torch_device()).movedim(-1, 1), low_threshold, high_threshold)
+        img_out = output[1].to(comfy.model_management.intermediate_device()).repeat(1, 3, 1, 1).movedim(1, -1)
+        return io.NodeOutput(img_out)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    Canny,
+]

comfy_extras/v3/nodes_cfg.py

@@ -0,0 +1,89 @@
+from __future__ import annotations
+
+import torch
+
+from comfy_api.latest import io
+
+
+# https://github.com/WeichenFan/CFG-Zero-star
+def optimized_scale(positive, negative):
+    positive_flat = positive.reshape(positive.shape[0], -1)
+    negative_flat = negative.reshape(negative.shape[0], -1)
+
+    # Calculate dot production
+    dot_product = torch.sum(positive_flat * negative_flat, dim=1, keepdim=True)
+
+    # Squared norm of uncondition
+    squared_norm = torch.sum(negative_flat ** 2, dim=1, keepdim=True) + 1e-8
+
+    # st_star = v_cond^T * v_uncond / ||v_uncond||^2
+    st_star = dot_product / squared_norm
+
+    return st_star.reshape([positive.shape[0]] + [1] * (positive.ndim - 1))
+
+
+class CFGZeroStar(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="CFGZeroStar_V3",
+            category="advanced/guidance",
+            inputs=[
+                io.Model.Input("model"),
+            ],
+            outputs=[io.Model.Output(display_name="patched_model")],
+        )
+
+    @classmethod
+    def execute(cls, model) -> io.NodeOutput:
+        m = model.clone()
+
+        def cfg_zero_star(args):
+            guidance_scale = args['cond_scale']
+            x = args['input']
+            cond_p = args['cond_denoised']
+            uncond_p = args['uncond_denoised']
+            out = args["denoised"]
+            alpha = optimized_scale(x - cond_p, x - uncond_p)
+
+            return out + uncond_p * (alpha - 1.0) + guidance_scale * uncond_p * (1.0 - alpha)
+
+        m.set_model_sampler_post_cfg_function(cfg_zero_star)
+        return io.NodeOutput(m)
+
+
+class CFGNorm(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="CFGNorm_V3",
+            category="advanced/guidance",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("strength", default=1.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[io.Model.Output(display_name="patched_model")],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model, strength) -> io.NodeOutput:
+        m = model.clone()
+
+        def cfg_norm(args):
+            cond_p = args['cond_denoised']
+            pred_text_ = args["denoised"]
+
+            norm_full_cond = torch.norm(cond_p, dim=1, keepdim=True)
+            norm_pred_text = torch.norm(pred_text_, dim=1, keepdim=True)
+            scale = (norm_full_cond / (norm_pred_text + 1e-8)).clamp(min=0.0, max=1.0)
+            return pred_text_ * scale * strength
+
+        m.set_model_sampler_post_cfg_function(cfg_norm)
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CFGNorm,
+    CFGZeroStar,
+]

comfy_extras/v3/nodes_clip_sdxl.py

@@ -0,0 +1,79 @@
+from __future__ import annotations
+
+import nodes
+from comfy_api.latest import io
+
+
+class CLIPTextEncodeSDXLRefiner(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeSDXLRefiner_V3",
+            category="advanced/conditioning",
+            inputs=[
+                io.Float.Input("ascore", default=6.0, min=0.0, max=1000.0, step=0.01),
+                io.Int.Input("width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.String.Input("text", multiline=True, dynamic_prompts=True),
+                io.Clip.Input("clip"),
+            ],
+            outputs=[io.Conditioning.Output()],
+        )
+
+    @classmethod
+    def execute(cls, ascore, width, height, text, clip) -> io.NodeOutput:
+        tokens = clip.tokenize(text)
+        conditioning = clip.encode_from_tokens_scheduled(
+            tokens, add_dict={"aesthetic_score": ascore, "width": width, "height": height}
+        )
+        return io.NodeOutput(conditioning)
+
+
+class CLIPTextEncodeSDXL(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeSDXL_V3",
+            category="advanced/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.Int.Input("width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("crop_w", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("crop_h", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("target_width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("target_height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.String.Input("text_g", multiline=True, dynamic_prompts=True),
+                io.String.Input("text_l", multiline=True, dynamic_prompts=True),
+            ],
+            outputs=[io.Conditioning.Output()],
+        )
+
+    @classmethod
+    def execute(cls, clip, width, height, crop_w, crop_h, target_width, target_height, text_g, text_l) -> io.NodeOutput:
+        tokens = clip.tokenize(text_g)
+        tokens["l"] = clip.tokenize(text_l)["l"]
+        if len(tokens["l"]) != len(tokens["g"]):
+            empty = clip.tokenize("")
+            while len(tokens["l"]) < len(tokens["g"]):
+                tokens["l"] += empty["l"]
+            while len(tokens["l"]) > len(tokens["g"]):
+                tokens["g"] += empty["g"]
+        conditioning = clip.encode_from_tokens_scheduled(
+            tokens,
+            add_dict={
+                "width": width,
+                "height": height,
+                "crop_w": crop_w,
+                "crop_h": crop_h,
+                "target_width": target_width,
+                "target_height": target_height,
+            },
+        )
+        return io.NodeOutput(conditioning)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CLIPTextEncodeSDXL,
+    CLIPTextEncodeSDXLRefiner,
+]

comfy_extras/v3/nodes_compositing.py

@@ -0,0 +1,226 @@
+from __future__ import annotations
+
+from enum import Enum
+
+import torch
+
+import comfy.utils
+from comfy_api.latest import io
+
+
+def resize_mask(mask, shape):
+    return torch.nn.functional.interpolate(
+        mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(shape[0], shape[1]), mode="bilinear"
+    ).squeeze(1)
+
+
+class PorterDuffMode(Enum):
+    ADD = 0
+    CLEAR = 1
+    DARKEN = 2
+    DST = 3
+    DST_ATOP = 4
+    DST_IN = 5
+    DST_OUT = 6
+    DST_OVER = 7
+    LIGHTEN = 8
+    MULTIPLY = 9
+    OVERLAY = 10
+    SCREEN = 11
+    SRC = 12
+    SRC_ATOP = 13
+    SRC_IN = 14
+    SRC_OUT = 15
+    SRC_OVER = 16
+    XOR = 17
+
+
+def porter_duff_composite(
+    src_image: torch.Tensor, src_alpha: torch.Tensor, dst_image: torch.Tensor, dst_alpha: torch.Tensor, mode: PorterDuffMode
+):
+    # convert mask to alpha
+    src_alpha = 1 - src_alpha
+    dst_alpha = 1 - dst_alpha
+    # premultiply alpha
+    src_image = src_image * src_alpha
+    dst_image = dst_image * dst_alpha
+
+    # composite ops below assume alpha-premultiplied images
+    if mode == PorterDuffMode.ADD:
+        out_alpha = torch.clamp(src_alpha + dst_alpha, 0, 1)
+        out_image = torch.clamp(src_image + dst_image, 0, 1)
+    elif mode == PorterDuffMode.CLEAR:
+        out_alpha = torch.zeros_like(dst_alpha)
+        out_image = torch.zeros_like(dst_image)
+    elif mode == PorterDuffMode.DARKEN:
+        out_alpha = src_alpha + dst_alpha - src_alpha * dst_alpha
+        out_image = (1 - dst_alpha) * src_image + (1 - src_alpha) * dst_image + torch.min(src_image, dst_image)
+    elif mode == PorterDuffMode.DST:
+        out_alpha = dst_alpha
+        out_image = dst_image
+    elif mode == PorterDuffMode.DST_ATOP:
+        out_alpha = src_alpha
+        out_image = src_alpha * dst_image + (1 - dst_alpha) * src_image
+    elif mode == PorterDuffMode.DST_IN:
+        out_alpha = src_alpha * dst_alpha
+        out_image = dst_image * src_alpha
+    elif mode == PorterDuffMode.DST_OUT:
+        out_alpha = (1 - src_alpha) * dst_alpha
+        out_image = (1 - src_alpha) * dst_image
+    elif mode == PorterDuffMode.DST_OVER:
+        out_alpha = dst_alpha + (1 - dst_alpha) * src_alpha
+        out_image = dst_image + (1 - dst_alpha) * src_image
+    elif mode == PorterDuffMode.LIGHTEN:
+        out_alpha = src_alpha + dst_alpha - src_alpha * dst_alpha
+        out_image = (1 - dst_alpha) * src_image + (1 - src_alpha) * dst_image + torch.max(src_image, dst_image)
+    elif mode == PorterDuffMode.MULTIPLY:
+        out_alpha = src_alpha * dst_alpha
+        out_image = src_image * dst_image
+    elif mode == PorterDuffMode.OVERLAY:
+        out_alpha = src_alpha + dst_alpha - src_alpha * dst_alpha
+        out_image = torch.where(2 * dst_image < dst_alpha, 2 * src_image * dst_image,
+            src_alpha * dst_alpha - 2 * (dst_alpha - src_image) * (src_alpha - dst_image))
+    elif mode == PorterDuffMode.SCREEN:
+        out_alpha = src_alpha + dst_alpha - src_alpha * dst_alpha
+        out_image = src_image + dst_image - src_image * dst_image
+    elif mode == PorterDuffMode.SRC:
+        out_alpha = src_alpha
+        out_image = src_image
+    elif mode == PorterDuffMode.SRC_ATOP:
+        out_alpha = dst_alpha
+        out_image = dst_alpha * src_image + (1 - src_alpha) * dst_image
+    elif mode == PorterDuffMode.SRC_IN:
+        out_alpha = src_alpha * dst_alpha
+        out_image = src_image * dst_alpha
+    elif mode == PorterDuffMode.SRC_OUT:
+        out_alpha = (1 - dst_alpha) * src_alpha
+        out_image = (1 - dst_alpha) * src_image
+    elif mode == PorterDuffMode.SRC_OVER:
+        out_alpha = src_alpha + (1 - src_alpha) * dst_alpha
+        out_image = src_image + (1 - src_alpha) * dst_image
+    elif mode == PorterDuffMode.XOR:
+        out_alpha = (1 - dst_alpha) * src_alpha + (1 - src_alpha) * dst_alpha
+        out_image = (1 - dst_alpha) * src_image + (1 - src_alpha) * dst_image
+    else:
+        return None, None
+
+    # back to non-premultiplied alpha
+    out_image = torch.where(out_alpha > 1e-5, out_image / out_alpha, torch.zeros_like(out_image))
+    out_image = torch.clamp(out_image, 0, 1)
+    # convert alpha to mask
+    out_alpha = 1 - out_alpha
+    return out_image, out_alpha
+
+
+class PorterDuffImageComposite(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PorterDuffImageComposite_V3",
+            display_name="Porter-Duff Image Composite _V3",
+            category="mask/compositing",
+            inputs=[
+                io.Image.Input("source"),
+                io.Mask.Input("source_alpha"),
+                io.Image.Input("destination"),
+                io.Mask.Input("destination_alpha"),
+                io.Combo.Input("mode", options=[mode.name for mode in PorterDuffMode], default=PorterDuffMode.DST.name),
+            ],
+            outputs=[io.Image.Output(), io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(
+        cls, source: torch.Tensor, source_alpha: torch.Tensor, destination: torch.Tensor, destination_alpha: torch.Tensor, mode
+    ) -> io.NodeOutput:
+        batch_size = min(len(source), len(source_alpha), len(destination), len(destination_alpha))
+        out_images = []
+        out_alphas = []
+
+        for i in range(batch_size):
+            src_image = source[i]
+            dst_image = destination[i]
+
+            assert src_image.shape[2] == dst_image.shape[2]  # inputs need to have same number of channels
+
+            src_alpha = source_alpha[i].unsqueeze(2)
+            dst_alpha = destination_alpha[i].unsqueeze(2)
+
+            if dst_alpha.shape[:2] != dst_image.shape[:2]:
+                upscale_input = dst_alpha.unsqueeze(0).permute(0, 3, 1, 2)
+                upscale_output = comfy.utils.common_upscale(
+                    upscale_input, dst_image.shape[1], dst_image.shape[0], upscale_method='bicubic', crop='center'
+                )
+                dst_alpha = upscale_output.permute(0, 2, 3, 1).squeeze(0)
+            if src_image.shape != dst_image.shape:
+                upscale_input = src_image.unsqueeze(0).permute(0, 3, 1, 2)
+                upscale_output = comfy.utils.common_upscale(
+                    upscale_input, dst_image.shape[1], dst_image.shape[0], upscale_method='bicubic', crop='center'
+                )
+                src_image = upscale_output.permute(0, 2, 3, 1).squeeze(0)
+            if src_alpha.shape != dst_alpha.shape:
+                upscale_input = src_alpha.unsqueeze(0).permute(0, 3, 1, 2)
+                upscale_output = comfy.utils.common_upscale(
+                    upscale_input, dst_alpha.shape[1], dst_alpha.shape[0], upscale_method='bicubic', crop='center'
+                )
+                src_alpha = upscale_output.permute(0, 2, 3, 1).squeeze(0)
+
+            out_image, out_alpha = porter_duff_composite(src_image, src_alpha, dst_image, dst_alpha, PorterDuffMode[mode])
+
+            out_images.append(out_image)
+            out_alphas.append(out_alpha.squeeze(2))
+
+        return io.NodeOutput(torch.stack(out_images), torch.stack(out_alphas))
+
+
+class SplitImageWithAlpha(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SplitImageWithAlpha_V3",
+            display_name="Split Image with Alpha _V3",
+            category="mask/compositing",
+            inputs=[
+                io.Image.Input("image"),
+            ],
+            outputs=[io.Image.Output(), io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image: torch.Tensor) -> io.NodeOutput:
+        out_images = [i[:, :, :3] for i in image]
+        out_alphas = [i[:, :, 3] if i.shape[2] > 3 else torch.ones_like(i[:, :, 0]) for i in image]
+        return io.NodeOutput(torch.stack(out_images), 1.0 - torch.stack(out_alphas))
+
+
+class JoinImageWithAlpha(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="JoinImageWithAlpha_V3",
+            display_name="Join Image with Alpha _V3",
+            category="mask/compositing",
+            inputs=[
+                io.Image.Input("image"),
+                io.Mask.Input("alpha"),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image: torch.Tensor, alpha: torch.Tensor) -> io.NodeOutput:
+        batch_size = min(len(image), len(alpha))
+        out_images = []
+
+        alpha = 1.0 - resize_mask(alpha, image.shape[1:])
+        for i in range(batch_size):
+            out_images.append(torch.cat((image[i][:, :, :3], alpha[i].unsqueeze(2)), dim=2))
+
+        return io.NodeOutput(torch.stack(out_images))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    JoinImageWithAlpha,
+    PorterDuffImageComposite,
+    SplitImageWithAlpha,
+]

comfy_extras/v3/nodes_cond.py

@@ -0,0 +1,60 @@
+from __future__ import annotations
+
+from comfy_api.latest import io
+
+
+class CLIPTextEncodeControlnet(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="CLIPTextEncodeControlnet_V3",
+            category="_for_testing/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.Conditioning.Input("conditioning"),
+                io.String.Input("text", multiline=True, dynamic_prompts=True),
+            ],
+            outputs=[io.Conditioning.Output()],
+        )
+
+    @classmethod
+    def execute(cls, clip, conditioning, text) -> io.NodeOutput:
+        tokens = clip.tokenize(text)
+        cond, pooled = clip.encode_from_tokens(tokens, return_pooled=True)
+        c = []
+        for t in conditioning:
+            n = [t[0], t[1].copy()]
+            n[1]['cross_attn_controlnet'] = cond
+            n[1]['pooled_output_controlnet'] = pooled
+            c.append(n)
+        return io.NodeOutput(c)
+
+
+class T5TokenizerOptions(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="T5TokenizerOptions_V3",
+            category="_for_testing/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.Int.Input("min_padding", default=0, min=0, max=10000, step=1),
+                io.Int.Input("min_length", default=0, min=0, max=10000, step=1),
+            ],
+            outputs=[io.Clip.Output()],
+        )
+
+    @classmethod
+    def execute(cls, clip, min_padding, min_length) -> io.NodeOutput:
+        clip = clip.clone()
+        for t5_type in ["t5xxl", "pile_t5xl", "t5base", "mt5xl", "umt5xxl"]:
+            clip.set_tokenizer_option("{}_min_padding".format(t5_type), min_padding)
+            clip.set_tokenizer_option("{}_min_length".format(t5_type), min_length)
+
+        return io.NodeOutput(clip)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CLIPTextEncodeControlnet,
+    T5TokenizerOptions,
+]

comfy_extras/v3/nodes_controlnet.py

@@ -0,0 +1,141 @@
+import comfy.utils
+from comfy.cldm.control_types import UNION_CONTROLNET_TYPES
+from comfy_api.latest import io
+
+
+class SetUnionControlNetType(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SetUnionControlNetType_V3",
+            category="conditioning/controlnet",
+            inputs=[
+                io.ControlNet.Input("control_net"),
+                io.Combo.Input("type", options=["auto"] + list(UNION_CONTROLNET_TYPES.keys())),
+            ],
+            outputs=[
+                io.ControlNet.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, control_net, type) -> io.NodeOutput:
+        control_net = control_net.copy()
+        type_number = UNION_CONTROLNET_TYPES.get(type, -1)
+        if type_number >= 0:
+            control_net.set_extra_arg("control_type", [type_number])
+        else:
+            control_net.set_extra_arg("control_type", [])
+
+        return io.NodeOutput(control_net)
+
+
+class ControlNetApplyAdvanced(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ControlNetApplyAdvanced_V3",
+            display_name="Apply ControlNet _V3",
+            category="conditioning/controlnet",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.ControlNet.Input("control_net"),
+                io.Image.Input("image"),
+                io.Float.Input("strength", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("start_percent", default=0.0, min=0.0, max=1.0, step=0.001),
+                io.Float.Input("end_percent", default=1.0, min=0.0, max=1.0, step=0.001),
+                io.Vae.Input("vae", optional=True),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+            ],
+        )
+
+    @classmethod
+    def execute(
+        cls, positive, negative, control_net, image, strength, start_percent, end_percent, vae=None, extra_concat=[]
+    ) -> io.NodeOutput:
+        if strength == 0:
+            return io.NodeOutput(positive, negative)
+
+        control_hint = image.movedim(-1, 1)
+        cnets = {}
+
+        out = []
+        for conditioning in [positive, negative]:
+            c = []
+            for t in conditioning:
+                d = t[1].copy()
+
+                prev_cnet = d.get("control", None)
+                if prev_cnet in cnets:
+                    c_net = cnets[prev_cnet]
+                else:
+                    c_net = control_net.copy().set_cond_hint(
+                        control_hint, strength, (start_percent, end_percent), vae=vae, extra_concat=extra_concat
+                    )
+                    c_net.set_previous_controlnet(prev_cnet)
+                    cnets[prev_cnet] = c_net
+
+                d["control"] = c_net
+                d["control_apply_to_uncond"] = False
+                n = [t[0], d]
+                c.append(n)
+            out.append(c)
+        return io.NodeOutput(out[0], out[1])
+
+
+class ControlNetInpaintingAliMamaApply(ControlNetApplyAdvanced):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ControlNetInpaintingAliMamaApply_V3",
+            category="conditioning/controlnet",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.ControlNet.Input("control_net"),
+                io.Vae.Input("vae"),
+                io.Image.Input("image"),
+                io.Mask.Input("mask"),
+                io.Float.Input("strength", default=1.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("start_percent", default=0.0, min=0.0, max=1.0, step=0.001),
+                io.Float.Input("end_percent", default=1.0, min=0.0, max=1.0, step=0.001),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+            ],
+        )
+
+    @classmethod
+    def execute(
+        cls, positive, negative, control_net, vae, image, mask, strength, start_percent, end_percent
+    ) -> io.NodeOutput:
+        extra_concat = []
+        if control_net.concat_mask:
+            mask = 1.0 - mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1]))
+            mask_apply = comfy.utils.common_upscale(mask, image.shape[2], image.shape[1], "bilinear", "center").round()
+            image = image * mask_apply.movedim(1, -1).repeat(1, 1, 1, image.shape[3])
+            extra_concat = [mask]
+
+        return super().execute(
+            positive,
+            negative,
+            control_net,
+            image,
+            strength,
+            start_percent,
+            end_percent,
+            vae=vae,
+            extra_concat=extra_concat,
+        )
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    ControlNetApplyAdvanced,
+    SetUnionControlNetType,
+    ControlNetInpaintingAliMamaApply,
+]

comfy_extras/v3/nodes_cosmos.py

@@ -0,0 +1,146 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.latent_formats
+import comfy.model_management
+import comfy.utils
+import nodes
+from comfy_api.latest import io
+
+
+class EmptyCosmosLatentVideo(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="EmptyCosmosLatentVideo_V3",
+            category="latent/video",
+            inputs=[
+                io.Int.Input("width", default=1280, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("height", default=704, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("length", default=121, min=1, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, width, height, length, batch_size) -> io.NodeOutput:
+        latent = torch.zeros(
+            [batch_size, 16, ((length - 1) // 8) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device()
+        )
+        return io.NodeOutput({"samples": latent})
+
+
+def vae_encode_with_padding(vae, image, width, height, length, padding=0):
+    pixels = comfy.utils.common_upscale(image[..., :3].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
+    pixel_len = min(pixels.shape[0], length)
+    padded_length = min(length, (((pixel_len - 1) // 8) + 1 + padding) * 8 - 7)
+    padded_pixels = torch.ones((padded_length, height, width, 3)) * 0.5
+    padded_pixels[:pixel_len] = pixels[:pixel_len]
+    latent_len = ((pixel_len - 1) // 8) + 1
+    latent_temp = vae.encode(padded_pixels)
+    return latent_temp[:, :, :latent_len]
+
+
+class CosmosImageToVideoLatent(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="CosmosImageToVideoLatent_V3",
+            category="conditioning/inpaint",
+            inputs=[
+                io.Vae.Input("vae"),
+                io.Int.Input("width", default=1280, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("height", default=704, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("length", default=121, min=1, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+                io.Image.Input("start_image", optional=True),
+                io.Image.Input("end_image", optional=True),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, vae, width, height, length, batch_size, start_image=None, end_image=None) -> io.NodeOutput:
+        latent = torch.zeros([1, 16, ((length - 1) // 8) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
+        if start_image is None and end_image is None:
+            out_latent = {}
+            out_latent["samples"] = latent
+            return io.NodeOutput(out_latent)
+
+        mask = torch.ones(
+            [latent.shape[0], 1, ((length - 1) // 8) + 1, latent.shape[-2], latent.shape[-1]],
+            device=comfy.model_management.intermediate_device(),
+        )
+
+        if start_image is not None:
+            latent_temp = vae_encode_with_padding(vae, start_image, width, height, length, padding=1)
+            latent[:, :, :latent_temp.shape[-3]] = latent_temp
+            mask[:, :, :latent_temp.shape[-3]] *= 0.0
+
+        if end_image is not None:
+            latent_temp = vae_encode_with_padding(vae, end_image, width, height, length, padding=0)
+            latent[:, :, -latent_temp.shape[-3]:] = latent_temp
+            mask[:, :, -latent_temp.shape[-3]:] *= 0.0
+
+        out_latent = {}
+        out_latent["samples"] = latent.repeat((batch_size, ) + (1,) * (latent.ndim - 1))
+        out_latent["noise_mask"] = mask.repeat((batch_size, ) + (1,) * (mask.ndim - 1))
+        return io.NodeOutput(out_latent)
+
+
+class CosmosPredict2ImageToVideoLatent(io.ComfyNode):
+    @classmethod
+    def define_schema(cls) -> io.Schema:
+        return io.Schema(
+            node_id="CosmosPredict2ImageToVideoLatent_V3",
+            category="conditioning/inpaint",
+            inputs=[
+                io.Vae.Input("vae"),
+                io.Int.Input("width", default=848, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("height", default=480, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("length", default=93, min=1, max=nodes.MAX_RESOLUTION, step=4),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+                io.Image.Input("start_image", optional=True),
+                io.Image.Input("end_image", optional=True),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, vae, width, height, length, batch_size, start_image=None, end_image=None) -> io.NodeOutput:
+        latent = torch.zeros([1, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
+        if start_image is None and end_image is None:
+            out_latent = {}
+            out_latent["samples"] = latent
+            return io.NodeOutput(out_latent)
+
+        mask = torch.ones(
+            [latent.shape[0], 1, ((length - 1) // 4) + 1, latent.shape[-2], latent.shape[-1]],
+            device=comfy.model_management.intermediate_device(),
+        )
+
+        if start_image is not None:
+            latent_temp = vae_encode_with_padding(vae, start_image, width, height, length, padding=1)
+            latent[:, :, :latent_temp.shape[-3]] = latent_temp
+            mask[:, :, :latent_temp.shape[-3]] *= 0.0
+
+        if end_image is not None:
+            latent_temp = vae_encode_with_padding(vae, end_image, width, height, length, padding=0)
+            latent[:, :, -latent_temp.shape[-3]:] = latent_temp
+            mask[:, :, -latent_temp.shape[-3]:] *= 0.0
+
+        out_latent = {}
+        latent_format = comfy.latent_formats.Wan21()
+        latent = latent_format.process_out(latent) * mask + latent * (1.0 - mask)
+        out_latent["samples"] = latent.repeat((batch_size, ) + (1,) * (latent.ndim - 1))
+        out_latent["noise_mask"] = mask.repeat((batch_size, ) + (1,) * (mask.ndim - 1))
+        return io.NodeOutput(out_latent)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CosmosImageToVideoLatent,
+    CosmosPredict2ImageToVideoLatent,
+    EmptyCosmosLatentVideo,
+]

comfy_extras/v3/nodes_differential_diffusion.py

@@ -0,0 +1,50 @@
+from __future__ import annotations
+
+import torch
+
+from comfy_api.latest import io
+
+
+class DifferentialDiffusion(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="DifferentialDiffusion_V3",
+            display_name="Differential Diffusion _V3",
+            category="_for_testing",
+            inputs=[
+                io.Model.Input("model"),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model):
+        model = model.clone()
+        model.set_model_denoise_mask_function(cls.forward)
+        return io.NodeOutput(model)
+
+    @classmethod
+    def forward(cls, sigma: torch.Tensor, denoise_mask: torch.Tensor, extra_options: dict):
+        model = extra_options["model"]
+        step_sigmas = extra_options["sigmas"]
+        sigma_to = model.inner_model.model_sampling.sigma_min
+        if step_sigmas[-1] > sigma_to:
+            sigma_to = step_sigmas[-1]
+        sigma_from = step_sigmas[0]
+
+        ts_from = model.inner_model.model_sampling.timestep(sigma_from)
+        ts_to = model.inner_model.model_sampling.timestep(sigma_to)
+        current_ts = model.inner_model.model_sampling.timestep(sigma[0])
+
+        threshold = (current_ts - ts_to) / (ts_from - ts_to)
+
+        return (denoise_mask >= threshold).to(denoise_mask.dtype)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    DifferentialDiffusion,
+]

comfy_extras/v3/nodes_edit_model.py

@@ -0,0 +1,34 @@
+from __future__ import annotations
+
+import node_helpers
+from comfy_api.latest import io
+
+
+class ReferenceLatent(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ReferenceLatent_V3",
+            category="advanced/conditioning/edit_models",
+            description="This node sets the guiding latent for an edit model. If the model supports it you can chain multiple to set multiple reference images.",
+            inputs=[
+                io.Conditioning.Input("conditioning"),
+                io.Latent.Input("latent", optional=True),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ]
+        )
+
+    @classmethod
+    def execute(cls, conditioning, latent=None):
+        if latent is not None:
+            conditioning = node_helpers.conditioning_set_values(
+                conditioning, {"reference_latents": [latent["samples"]]}, append=True
+            )
+        return io.NodeOutput(conditioning)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    ReferenceLatent,
+]

comfy_extras/v3/nodes_flux.py

@@ -0,0 +1,122 @@
+from __future__ import annotations
+
+import comfy.utils
+import node_helpers
+from comfy_api.latest import io
+
+PREFERED_KONTEXT_RESOLUTIONS = [
+    (672, 1568),
+    (688, 1504),
+    (720, 1456),
+    (752, 1392),
+    (800, 1328),
+    (832, 1248),
+    (880, 1184),
+    (944, 1104),
+    (1024, 1024),
+    (1104, 944),
+    (1184, 880),
+    (1248, 832),
+    (1328, 800),
+    (1392, 752),
+    (1456, 720),
+    (1504, 688),
+    (1568, 672),
+]
+
+
+class CLIPTextEncodeFlux(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeFlux_V3",
+            category="advanced/conditioning/flux",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("clip_l", multiline=True, dynamic_prompts=True),
+                io.String.Input("t5xxl", multiline=True, dynamic_prompts=True),
+                io.Float.Input("guidance", default=3.5, min=0.0, max=100.0, step=0.1),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, clip, clip_l, t5xxl, guidance):
+        tokens = clip.tokenize(clip_l)
+        tokens["t5xxl"] = clip.tokenize(t5xxl)["t5xxl"]
+
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens, add_dict={"guidance": guidance}))
+
+class FluxGuidance(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="FluxGuidance_V3",
+            category="advanced/conditioning/flux",
+            inputs=[
+                io.Conditioning.Input("conditioning"),
+                io.Float.Input("guidance", default=3.5, min=0.0, max=100.0, step=0.1),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, conditioning, guidance):
+        c = node_helpers.conditioning_set_values(conditioning, {"guidance": guidance})
+        return io.NodeOutput(c)
+
+class FluxDisableGuidance(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="FluxDisableGuidance_V3",
+            category="advanced/conditioning/flux",
+            description="This node completely disables the guidance embed on Flux and Flux like models",
+            inputs=[
+                io.Conditioning.Input("conditioning"),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, conditioning):
+        c = node_helpers.conditioning_set_values(conditioning, {"guidance": None})
+        return io.NodeOutput(c)
+
+class FluxKontextImageScale(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="FluxKontextImageScale_V3",
+            category="advanced/conditioning/flux",
+            description="This node resizes the image to one that is more optimal for flux kontext.",
+            inputs=[
+                io.Image.Input("image"),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image):
+        width = image.shape[2]
+        height = image.shape[1]
+        aspect_ratio = width / height
+        _, width, height = min((abs(aspect_ratio - w / h), w, h) for w, h in PREFERED_KONTEXT_RESOLUTIONS)
+        image = comfy.utils.common_upscale(image.movedim(-1, 1), width, height, "lanczos", "center").movedim(1, -1)
+        return io.NodeOutput(image)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CLIPTextEncodeFlux,
+    FluxDisableGuidance,
+    FluxGuidance,
+    FluxKontextImageScale,
+]

comfy_extras/v3/nodes_freelunch.py

@@ -0,0 +1,131 @@
+#code originally taken from: https://github.com/ChenyangSi/FreeU (under MIT License)
+
+from __future__ import annotations
+
+import logging
+
+import torch
+
+from comfy_api.latest import io
+
+
+def Fourier_filter(x, threshold, scale):
+    # FFT
+    x_freq = torch.fft.fftn(x.float(), dim=(-2, -1))
+    x_freq = torch.fft.fftshift(x_freq, dim=(-2, -1))
+
+    B, C, H, W = x_freq.shape
+    mask = torch.ones((B, C, H, W), device=x.device)
+
+    crow, ccol = H // 2, W //2
+    mask[..., crow - threshold:crow + threshold, ccol - threshold:ccol + threshold] = scale
+    x_freq = x_freq * mask
+
+    # IFFT
+    x_freq = torch.fft.ifftshift(x_freq, dim=(-2, -1))
+    x_filtered = torch.fft.ifftn(x_freq, dim=(-2, -1)).real
+
+    return x_filtered.to(x.dtype)
+
+
+class FreeU(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="FreeU_V3",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("b1", default=1.1, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("b2", default=1.2, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("s1", default=0.9, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("s2", default=0.2, min=0.0, max=10.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, b1, b2, s1, s2):
+        model_channels = model.model.model_config.unet_config["model_channels"]
+        scale_dict = {model_channels * 4: (b1, s1), model_channels * 2: (b2, s2)}
+        on_cpu_devices = {}
+
+        def output_block_patch(h, hsp, transformer_options):
+            scale = scale_dict.get(int(h.shape[1]), None)
+            if scale is not None:
+                h[:,:h.shape[1] // 2] = h[:,:h.shape[1] // 2] * scale[0]
+                if hsp.device not in on_cpu_devices:
+                    try:
+                        hsp = Fourier_filter(hsp, threshold=1, scale=scale[1])
+                    except Exception:
+                        logging.warning("Device {} does not support the torch.fft functions used in the FreeU node, switching to CPU.".format(hsp.device))
+                        on_cpu_devices[hsp.device] = True
+                        hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
+                else:
+                    hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
+
+            return h, hsp
+
+        m = model.clone()
+        m.set_model_output_block_patch(output_block_patch)
+        return io.NodeOutput(m)
+
+
+class FreeU_V2(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="FreeU_V2_V3",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("b1", default=1.3, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("b2", default=1.4, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("s1", default=0.9, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("s2", default=0.2, min=0.0, max=10.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, b1, b2, s1, s2):
+        model_channels = model.model.model_config.unet_config["model_channels"]
+        scale_dict = {model_channels * 4: (b1, s1), model_channels * 2: (b2, s2)}
+        on_cpu_devices = {}
+
+        def output_block_patch(h, hsp, transformer_options):
+            scale = scale_dict.get(int(h.shape[1]), None)
+            if scale is not None:
+                hidden_mean = h.mean(1).unsqueeze(1)
+                B = hidden_mean.shape[0]
+                hidden_max, _ = torch.max(hidden_mean.view(B, -1), dim=-1, keepdim=True)
+                hidden_min, _ = torch.min(hidden_mean.view(B, -1), dim=-1, keepdim=True)
+                hidden_mean = (hidden_mean - hidden_min.unsqueeze(2).unsqueeze(3)) / (hidden_max - hidden_min).unsqueeze(2).unsqueeze(3)
+
+                h[:,:h.shape[1] // 2] = h[:,:h.shape[1] // 2] * ((scale[0] - 1 ) * hidden_mean + 1)
+
+                if hsp.device not in on_cpu_devices:
+                    try:
+                        hsp = Fourier_filter(hsp, threshold=1, scale=scale[1])
+                    except Exception:
+                        logging.warning("Device {} does not support the torch.fft functions used in the FreeU node, switching to CPU.".format(hsp.device))
+                        on_cpu_devices[hsp.device] = True
+                        hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
+                else:
+                    hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
+
+            return h, hsp
+
+        m = model.clone()
+        m.set_model_output_block_patch(output_block_patch)
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    FreeU,
+    FreeU_V2,
+]

comfy_extras/v3/nodes_fresca.py

@@ -0,0 +1,110 @@
+# Code based on https://github.com/WikiChao/FreSca (MIT License)
+
+from __future__ import annotations
+
+import torch
+import torch.fft as fft
+
+from comfy_api.latest import io
+
+
+def Fourier_filter(x, scale_low=1.0, scale_high=1.5, freq_cutoff=20):
+    """
+    Apply frequency-dependent scaling to an image tensor using Fourier transforms.
+
+    Parameters:
+        x:           Input tensor of shape (B, C, H, W)
+        scale_low:   Scaling factor for low-frequency components (default: 1.0)
+        scale_high:  Scaling factor for high-frequency components (default: 1.5)
+        freq_cutoff: Number of frequency indices around center to consider as low-frequency (default: 20)
+
+    Returns:
+        x_filtered: Filtered version of x in spatial domain with frequency-specific scaling applied.
+    """
+    # Preserve input dtype and device
+    dtype, device = x.dtype, x.device
+
+    # Convert to float32 for FFT computations
+    x = x.to(torch.float32)
+
+    # 1) Apply FFT and shift low frequencies to center
+    x_freq = fft.fftn(x, dim=(-2, -1))
+    x_freq = fft.fftshift(x_freq, dim=(-2, -1))
+
+    # Initialize mask with high-frequency scaling factor
+    mask = torch.ones(x_freq.shape, device=device) * scale_high
+    m = mask
+    for d in range(len(x_freq.shape) - 2):
+        dim = d + 2
+        cc = x_freq.shape[dim] // 2
+        f_c = min(freq_cutoff, cc)
+        m = m.narrow(dim, cc - f_c, f_c * 2)
+
+    # Apply low-frequency scaling factor to center region
+    m[:] = scale_low
+
+    # 3) Apply frequency-specific scaling
+    x_freq = x_freq * mask
+
+    # 4) Convert back to spatial domain
+    x_freq = fft.ifftshift(x_freq, dim=(-2, -1))
+    x_filtered = fft.ifftn(x_freq, dim=(-2, -1)).real
+
+    # 5) Restore original dtype
+    x_filtered = x_filtered.to(dtype)
+
+    return x_filtered
+
+
+class FreSca(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="FreSca_V3",
+            display_name="FreSca _V3",
+            category="_for_testing",
+            description="Applies frequency-dependent scaling to the guidance",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("scale_low", default=1.0, min=0, max=10, step=0.01,
+                               tooltip="Scaling factor for low-frequency components"),
+                io.Float.Input("scale_high", default=1.25, min=0, max=10, step=0.01,
+                               tooltip="Scaling factor for high-frequency components"),
+                io.Int.Input("freq_cutoff", default=20, min=1, max=10000, step=1,
+                             tooltip="Number of frequency indices around center to consider as low-frequency"),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model, scale_low, scale_high, freq_cutoff):
+        def custom_cfg_function(args):
+            conds_out = args["conds_out"]
+            if len(conds_out) <= 1 or None in args["conds"][:2]:
+                return conds_out
+            cond = conds_out[0]
+            uncond = conds_out[1]
+
+            guidance = cond - uncond
+            filtered_guidance = Fourier_filter(
+                guidance,
+                scale_low=scale_low,
+                scale_high=scale_high,
+                freq_cutoff=freq_cutoff,
+            )
+            filtered_cond = filtered_guidance + uncond
+
+            return [filtered_cond, uncond] + conds_out[2:]
+
+        m = model.clone()
+        m.set_model_sampler_pre_cfg_function(custom_cfg_function)
+
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    FreSca,
+]

comfy_extras/v3/nodes_gits.py

@@ -0,0 +1,376 @@
+from __future__ import annotations
+
+import numpy as np
+import torch
+
+from comfy_api.latest import io
+
+
+def loglinear_interp(t_steps, num_steps):
+    """Performs log-linear interpolation of a given array of decreasing numbers."""
+    xs = np.linspace(0, 1, len(t_steps))
+    ys = np.log(t_steps[::-1])
+
+    new_xs = np.linspace(0, 1, num_steps)
+    new_ys = np.interp(new_xs, xs, ys)
+
+    return np.exp(new_ys)[::-1].copy()
+
+
+NOISE_LEVELS = {
+    0.80: [
+        [14.61464119, 7.49001646, 0.02916753],
+        [14.61464119, 11.54541874, 6.77309084, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 3.07277966, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 2.05039096, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.49001646, 5.85520077, 2.05039096, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.49001646, 5.85520077, 3.07277966, 1.56271636, 0.02916753],
+        [14.61464119, 12.96784878, 11.54541874, 8.75849152, 7.49001646, 5.85520077, 3.07277966, 1.56271636, 0.02916753],
+        [14.61464119, 13.76078796, 12.2308979, 10.90732002, 8.75849152, 7.49001646, 5.85520077, 3.07277966, 1.56271636, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 10.90732002, 8.75849152, 7.49001646, 5.85520077, 3.07277966, 1.56271636, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 5.85520077, 3.07277966, 1.56271636, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 4.86714602, 3.07277966, 1.56271636, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.31284904, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 4.86714602, 3.07277966, 1.56271636, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 4.86714602, 3.07277966, 1.56271636, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.24142551, 8.75849152, 8.30717278, 7.49001646, 6.14220476, 4.86714602, 3.07277966, 1.56271636, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.24142551, 8.75849152, 8.30717278, 7.49001646, 6.14220476, 4.86714602, 3.1956799, 1.98035145, 0.86115354, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.75859547, 9.24142551, 8.75849152, 8.30717278, 7.49001646, 6.14220476, 4.86714602, 3.1956799, 1.98035145, 0.86115354, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.75859547, 9.24142551, 8.75849152, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 4.65472794, 3.07277966, 1.84880662, 0.83188516, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.75859547, 9.24142551, 8.75849152, 8.30717278, 7.88507891, 7.49001646, 6.77309084, 5.85520077, 4.65472794, 3.07277966, 1.84880662, 0.83188516, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.75859547, 9.24142551, 8.75849152, 8.30717278, 7.88507891, 7.49001646, 6.77309084, 5.85520077, 4.86714602, 3.75677586, 2.84484982, 1.78698075, 0.803307, 0.02916753],
+    ],
+    0.85: [
+        [14.61464119, 7.49001646, 0.02916753],
+        [14.61464119, 7.49001646, 1.84880662, 0.02916753],
+        [14.61464119, 11.54541874, 6.77309084, 1.56271636, 0.02916753],
+        [14.61464119, 11.54541874, 7.11996698, 3.07277966, 1.24153244, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.09240818, 2.84484982, 0.95350921, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.49001646, 5.09240818, 2.84484982, 0.95350921, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.49001646, 5.58536053, 3.1956799, 1.84880662, 0.803307, 0.02916753],
+        [14.61464119, 12.96784878, 11.54541874, 8.75849152, 7.49001646, 5.58536053, 3.1956799, 1.84880662, 0.803307, 0.02916753],
+        [14.61464119, 12.96784878, 11.54541874, 8.75849152, 7.49001646, 6.14220476, 4.65472794, 3.07277966, 1.84880662, 0.803307, 0.02916753],
+        [14.61464119, 13.76078796, 12.2308979, 10.90732002, 8.75849152, 7.49001646, 6.14220476, 4.65472794, 3.07277966, 1.84880662, 0.803307, 0.02916753],
+        [14.61464119, 13.76078796, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 4.65472794, 3.07277966, 1.84880662, 0.803307, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 4.65472794, 3.07277966, 1.84880662, 0.803307, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.31284904, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 4.65472794, 3.07277966, 1.84880662, 0.803307, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.31284904, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 4.86714602, 3.60512662, 2.6383388, 1.56271636, 0.72133851, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.31284904, 9.24142551, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 4.65472794, 3.46139455, 2.45070267, 1.56271636, 0.72133851, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.31284904, 9.24142551, 8.75849152, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 4.65472794, 3.46139455, 2.45070267, 1.56271636, 0.72133851, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.24142551, 8.75849152, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 4.65472794, 3.46139455, 2.45070267, 1.56271636, 0.72133851, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.75859547, 9.24142551, 8.75849152, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 4.65472794, 3.46139455, 2.45070267, 1.56271636, 0.72133851, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.90732002, 10.31284904, 9.75859547, 9.24142551, 8.75849152, 8.30717278, 7.88507891, 7.49001646, 6.77309084, 5.85520077, 4.65472794, 3.46139455, 2.45070267, 1.56271636, 0.72133851, 0.02916753],
+    ],
+    0.90: [
+        [14.61464119, 6.77309084, 0.02916753],
+        [14.61464119, 7.49001646, 1.56271636, 0.02916753],
+        [14.61464119, 7.49001646, 3.07277966, 0.95350921, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.54230714, 0.89115214, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 4.86714602, 2.54230714, 0.89115214, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.09240818, 3.07277966, 1.61558151, 0.69515091, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.11996698, 4.86714602, 3.07277966, 1.61558151, 0.69515091, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.49001646, 5.85520077, 4.45427561, 2.95596409, 1.61558151, 0.69515091, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.19988537, 1.24153244, 0.57119018, 0.02916753],
+        [14.61464119, 12.96784878, 10.90732002, 8.75849152, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.19988537, 1.24153244, 0.57119018, 0.02916753],
+        [14.61464119, 12.96784878, 11.54541874, 9.24142551, 8.30717278, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.19988537, 1.24153244, 0.57119018, 0.02916753],
+        [14.61464119, 12.96784878, 11.54541874, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 4.86714602, 3.75677586, 2.84484982, 1.84880662, 1.08895338, 0.52423614, 0.02916753],
+        [14.61464119, 13.76078796, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 4.86714602, 3.75677586, 2.84484982, 1.84880662, 1.08895338, 0.52423614, 0.02916753],
+        [14.61464119, 13.76078796, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 6.44769001, 5.58536053, 4.45427561, 3.32507086, 2.45070267, 1.61558151, 0.95350921, 0.45573691, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 6.44769001, 5.58536053, 4.45427561, 3.32507086, 2.45070267, 1.61558151, 0.95350921, 0.45573691, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 4.86714602, 3.91689563, 3.07277966, 2.27973175, 1.56271636, 0.95350921, 0.45573691, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.31284904, 9.24142551, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 4.86714602, 3.91689563, 3.07277966, 2.27973175, 1.56271636, 0.95350921, 0.45573691, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.31284904, 9.24142551, 8.75849152, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 4.86714602, 3.91689563, 3.07277966, 2.27973175, 1.56271636, 0.95350921, 0.45573691, 0.02916753],
+        [14.61464119, 13.76078796, 12.96784878, 12.2308979, 11.54541874, 10.31284904, 9.24142551, 8.75849152, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 5.09240818, 4.45427561, 3.60512662, 2.95596409, 2.19988537, 1.51179266, 0.89115214, 0.43325692, 0.02916753],
+    ],
+    0.95: [
+        [14.61464119, 6.77309084, 0.02916753],
+        [14.61464119, 6.77309084, 1.56271636, 0.02916753],
+        [14.61464119, 7.49001646, 2.84484982, 0.89115214, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.36326075, 0.803307, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.95596409, 1.56271636, 0.64427125, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 4.86714602, 2.95596409, 1.56271636, 0.64427125, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 4.86714602, 3.07277966, 1.91321158, 1.08895338, 0.50118381, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.45427561, 3.07277966, 1.91321158, 1.08895338, 0.50118381, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.49001646, 5.85520077, 4.45427561, 3.07277966, 1.91321158, 1.08895338, 0.50118381, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.19988537, 1.41535246, 0.803307, 0.38853383, 0.02916753],
+        [14.61464119, 12.2308979, 8.75849152, 7.49001646, 5.85520077, 4.65472794, 3.46139455, 2.6383388, 1.84880662, 1.24153244, 0.72133851, 0.34370604, 0.02916753],
+        [14.61464119, 12.96784878, 10.90732002, 8.75849152, 7.49001646, 5.85520077, 4.65472794, 3.46139455, 2.6383388, 1.84880662, 1.24153244, 0.72133851, 0.34370604, 0.02916753],
+        [14.61464119, 12.96784878, 10.90732002, 8.75849152, 7.49001646, 6.14220476, 4.86714602, 3.75677586, 2.95596409, 2.19988537, 1.56271636, 1.05362725, 0.64427125, 0.32104823, 0.02916753],
+        [14.61464119, 12.96784878, 10.90732002, 8.75849152, 7.49001646, 6.44769001, 5.58536053, 4.65472794, 3.60512662, 2.95596409, 2.19988537, 1.56271636, 1.05362725, 0.64427125, 0.32104823, 0.02916753],
+        [14.61464119, 12.96784878, 11.54541874, 9.24142551, 8.30717278, 7.49001646, 6.44769001, 5.58536053, 4.65472794, 3.60512662, 2.95596409, 2.19988537, 1.56271636, 1.05362725, 0.64427125, 0.32104823, 0.02916753],
+        [14.61464119, 12.96784878, 11.54541874, 9.24142551, 8.30717278, 7.49001646, 6.44769001, 5.58536053, 4.65472794, 3.75677586, 3.07277966, 2.45070267, 1.78698075, 1.24153244, 0.83188516, 0.50118381, 0.22545385, 0.02916753],
+        [14.61464119, 12.96784878, 11.54541874, 9.24142551, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 5.09240818, 4.45427561, 3.60512662, 2.95596409, 2.36326075, 1.72759056, 1.24153244, 0.83188516, 0.50118381, 0.22545385, 0.02916753],
+        [14.61464119, 13.76078796, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 5.09240818, 4.45427561, 3.60512662, 2.95596409, 2.36326075, 1.72759056, 1.24153244, 0.83188516, 0.50118381, 0.22545385, 0.02916753],
+        [14.61464119, 13.76078796, 12.2308979, 10.90732002, 9.24142551, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 5.09240818, 4.45427561, 3.75677586, 3.07277966, 2.45070267, 1.91321158, 1.46270394, 1.05362725, 0.72133851, 0.43325692, 0.19894916, 0.02916753],
+    ],
+    1.00: [
+        [14.61464119, 1.56271636, 0.02916753],
+        [14.61464119, 6.77309084, 0.95350921, 0.02916753],
+        [14.61464119, 6.77309084, 2.36326075, 0.803307, 0.02916753],
+        [14.61464119, 7.11996698, 3.07277966, 1.56271636, 0.59516323, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.84484982, 1.41535246, 0.57119018, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.84484982, 1.61558151, 0.86115354, 0.38853383, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 4.86714602, 2.84484982, 1.61558151, 0.86115354, 0.38853383, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 4.86714602, 3.07277966, 1.98035145, 1.24153244, 0.72133851, 0.34370604, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.45427561, 3.07277966, 1.98035145, 1.24153244, 0.72133851, 0.34370604, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.27973175, 1.51179266, 0.95350921, 0.54755926, 0.25053367, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.36326075, 1.61558151, 1.08895338, 0.72133851, 0.41087446, 0.17026083, 0.02916753],
+        [14.61464119, 11.54541874, 8.75849152, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.36326075, 1.61558151, 1.08895338, 0.72133851, 0.41087446, 0.17026083, 0.02916753],
+        [14.61464119, 11.54541874, 8.75849152, 7.49001646, 5.85520077, 4.65472794, 3.60512662, 2.84484982, 2.12350607, 1.56271636, 1.08895338, 0.72133851, 0.41087446, 0.17026083, 0.02916753],
+        [14.61464119, 11.54541874, 8.75849152, 7.49001646, 5.85520077, 4.65472794, 3.60512662, 2.84484982, 2.19988537, 1.61558151, 1.162866, 0.803307, 0.50118381, 0.27464288, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 8.75849152, 7.49001646, 5.85520077, 4.65472794, 3.75677586, 3.07277966, 2.45070267, 1.84880662, 1.36964464, 1.01931262, 0.72133851, 0.45573691, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 8.75849152, 7.49001646, 6.14220476, 5.09240818, 4.26497746, 3.46139455, 2.84484982, 2.19988537, 1.67050016, 1.24153244, 0.92192322, 0.64427125, 0.43325692, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 8.75849152, 7.49001646, 6.14220476, 5.09240818, 4.26497746, 3.60512662, 2.95596409, 2.45070267, 1.91321158, 1.51179266, 1.12534678, 0.83188516, 0.59516323, 0.38853383, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 12.2308979, 9.24142551, 8.30717278, 7.49001646, 6.14220476, 5.09240818, 4.26497746, 3.60512662, 2.95596409, 2.45070267, 1.91321158, 1.51179266, 1.12534678, 0.83188516, 0.59516323, 0.38853383, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 12.2308979, 9.24142551, 8.30717278, 7.49001646, 6.77309084, 5.85520077, 5.09240818, 4.26497746, 3.60512662, 2.95596409, 2.45070267, 1.91321158, 1.51179266, 1.12534678, 0.83188516, 0.59516323, 0.38853383, 0.22545385, 0.09824532, 0.02916753],
+    ],
+    1.05: [
+        [14.61464119, 0.95350921, 0.02916753],
+        [14.61464119, 6.77309084, 0.89115214, 0.02916753],
+        [14.61464119, 6.77309084, 2.05039096, 0.72133851, 0.02916753],
+        [14.61464119, 6.77309084, 2.84484982, 1.28281462, 0.52423614, 0.02916753],
+        [14.61464119, 6.77309084, 3.07277966, 1.61558151, 0.803307, 0.34370604, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.84484982, 1.56271636, 0.803307, 0.34370604, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.84484982, 1.61558151, 0.95350921, 0.52423614, 0.22545385, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.07277966, 1.98035145, 1.24153244, 0.74807048, 0.41087446, 0.17026083, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.1956799, 2.27973175, 1.51179266, 0.95350921, 0.59516323, 0.34370604, 0.13792117, 0.02916753],
+        [14.61464119, 7.49001646, 5.09240818, 3.46139455, 2.45070267, 1.61558151, 1.08895338, 0.72133851, 0.45573691, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.09240818, 3.46139455, 2.45070267, 1.61558151, 1.08895338, 0.72133851, 0.45573691, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.36326075, 1.61558151, 1.08895338, 0.72133851, 0.45573691, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.45070267, 1.72759056, 1.24153244, 0.86115354, 0.59516323, 0.38853383, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.65472794, 3.60512662, 2.84484982, 2.19988537, 1.61558151, 1.162866, 0.83188516, 0.59516323, 0.38853383, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.65472794, 3.60512662, 2.84484982, 2.19988537, 1.67050016, 1.28281462, 0.95350921, 0.72133851, 0.52423614, 0.34370604, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.65472794, 3.60512662, 2.95596409, 2.36326075, 1.84880662, 1.41535246, 1.08895338, 0.83188516, 0.61951244, 0.45573691, 0.32104823, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.65472794, 3.60512662, 2.95596409, 2.45070267, 1.91321158, 1.51179266, 1.20157266, 0.95350921, 0.74807048, 0.57119018, 0.43325692, 0.29807833, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 8.30717278, 7.11996698, 5.85520077, 4.65472794, 3.60512662, 2.95596409, 2.45070267, 1.91321158, 1.51179266, 1.20157266, 0.95350921, 0.74807048, 0.57119018, 0.43325692, 0.29807833, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 8.30717278, 7.11996698, 5.85520077, 4.65472794, 3.60512662, 2.95596409, 2.45070267, 1.98035145, 1.61558151, 1.32549286, 1.08895338, 0.86115354, 0.69515091, 0.54755926, 0.41087446, 0.29807833, 0.19894916, 0.09824532, 0.02916753],
+    ],
+    1.10: [
+        [14.61464119, 0.89115214, 0.02916753],
+        [14.61464119, 2.36326075, 0.72133851, 0.02916753],
+        [14.61464119, 5.85520077, 1.61558151, 0.57119018, 0.02916753],
+        [14.61464119, 6.77309084, 2.45070267, 1.08895338, 0.45573691, 0.02916753],
+        [14.61464119, 6.77309084, 2.95596409, 1.56271636, 0.803307, 0.34370604, 0.02916753],
+        [14.61464119, 6.77309084, 3.07277966, 1.61558151, 0.89115214, 0.4783645, 0.19894916, 0.02916753],
+        [14.61464119, 6.77309084, 3.07277966, 1.84880662, 1.08895338, 0.64427125, 0.34370604, 0.13792117, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.84484982, 1.61558151, 0.95350921, 0.54755926, 0.27464288, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.95596409, 1.91321158, 1.24153244, 0.803307, 0.4783645, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.07277966, 2.05039096, 1.41535246, 0.95350921, 0.64427125, 0.41087446, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.1956799, 2.27973175, 1.61558151, 1.12534678, 0.803307, 0.54755926, 0.36617002, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.32507086, 2.45070267, 1.72759056, 1.24153244, 0.89115214, 0.64427125, 0.45573691, 0.32104823, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 5.09240818, 3.60512662, 2.84484982, 2.05039096, 1.51179266, 1.08895338, 0.803307, 0.59516323, 0.43325692, 0.29807833, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 5.09240818, 3.60512662, 2.84484982, 2.12350607, 1.61558151, 1.24153244, 0.95350921, 0.72133851, 0.54755926, 0.41087446, 0.29807833, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.45070267, 1.84880662, 1.41535246, 1.08895338, 0.83188516, 0.64427125, 0.50118381, 0.36617002, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 5.85520077, 4.45427561, 3.1956799, 2.45070267, 1.91321158, 1.51179266, 1.20157266, 0.95350921, 0.74807048, 0.59516323, 0.45573691, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 5.85520077, 4.45427561, 3.46139455, 2.84484982, 2.19988537, 1.72759056, 1.36964464, 1.08895338, 0.86115354, 0.69515091, 0.54755926, 0.43325692, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.45427561, 3.46139455, 2.84484982, 2.19988537, 1.72759056, 1.36964464, 1.08895338, 0.86115354, 0.69515091, 0.54755926, 0.43325692, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 11.54541874, 7.49001646, 5.85520077, 4.45427561, 3.46139455, 2.84484982, 2.19988537, 1.72759056, 1.36964464, 1.08895338, 0.89115214, 0.72133851, 0.59516323, 0.4783645, 0.38853383, 0.29807833, 0.22545385, 0.17026083, 0.09824532, 0.02916753],
+    ],
+    1.15: [
+        [14.61464119, 0.83188516, 0.02916753],
+        [14.61464119, 1.84880662, 0.59516323, 0.02916753],
+        [14.61464119, 5.85520077, 1.56271636, 0.52423614, 0.02916753],
+        [14.61464119, 5.85520077, 1.91321158, 0.83188516, 0.34370604, 0.02916753],
+        [14.61464119, 5.85520077, 2.45070267, 1.24153244, 0.59516323, 0.25053367, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.51179266, 0.803307, 0.41087446, 0.17026083, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.56271636, 0.89115214, 0.50118381, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 6.77309084, 3.07277966, 1.84880662, 1.12534678, 0.72133851, 0.43325692, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 6.77309084, 3.07277966, 1.91321158, 1.24153244, 0.803307, 0.52423614, 0.34370604, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 2.95596409, 1.91321158, 1.24153244, 0.803307, 0.52423614, 0.34370604, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.07277966, 2.05039096, 1.36964464, 0.95350921, 0.69515091, 0.4783645, 0.32104823, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.07277966, 2.12350607, 1.51179266, 1.08895338, 0.803307, 0.59516323, 0.43325692, 0.29807833, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.07277966, 2.12350607, 1.51179266, 1.08895338, 0.803307, 0.59516323, 0.45573691, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.07277966, 2.19988537, 1.61558151, 1.24153244, 0.95350921, 0.74807048, 0.59516323, 0.45573691, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.1956799, 2.45070267, 1.78698075, 1.32549286, 1.01931262, 0.803307, 0.64427125, 0.50118381, 0.38853383, 0.29807833, 0.22545385, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.1956799, 2.45070267, 1.78698075, 1.32549286, 1.01931262, 0.803307, 0.64427125, 0.52423614, 0.41087446, 0.32104823, 0.25053367, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.1956799, 2.45070267, 1.84880662, 1.41535246, 1.12534678, 0.89115214, 0.72133851, 0.59516323, 0.4783645, 0.38853383, 0.32104823, 0.25053367, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.1956799, 2.45070267, 1.84880662, 1.41535246, 1.12534678, 0.89115214, 0.72133851, 0.59516323, 0.50118381, 0.41087446, 0.34370604, 0.27464288, 0.22545385, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.86714602, 3.1956799, 2.45070267, 1.84880662, 1.41535246, 1.12534678, 0.89115214, 0.72133851, 0.59516323, 0.50118381, 0.41087446, 0.34370604, 0.29807833, 0.25053367, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+    ],
+    1.20: [
+        [14.61464119, 0.803307, 0.02916753],
+        [14.61464119, 1.56271636, 0.52423614, 0.02916753],
+        [14.61464119, 2.36326075, 0.92192322, 0.36617002, 0.02916753],
+        [14.61464119, 2.84484982, 1.24153244, 0.59516323, 0.25053367, 0.02916753],
+        [14.61464119, 5.85520077, 2.05039096, 0.95350921, 0.45573691, 0.17026083, 0.02916753],
+        [14.61464119, 5.85520077, 2.45070267, 1.24153244, 0.64427125, 0.29807833, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.45070267, 1.36964464, 0.803307, 0.45573691, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.61558151, 0.95350921, 0.59516323, 0.36617002, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.67050016, 1.08895338, 0.74807048, 0.50118381, 0.32104823, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.95596409, 1.84880662, 1.24153244, 0.83188516, 0.59516323, 0.41087446, 0.27464288, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 3.07277966, 1.98035145, 1.36964464, 0.95350921, 0.69515091, 0.50118381, 0.36617002, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 6.77309084, 3.46139455, 2.36326075, 1.56271636, 1.08895338, 0.803307, 0.59516323, 0.45573691, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 6.77309084, 3.46139455, 2.45070267, 1.61558151, 1.162866, 0.86115354, 0.64427125, 0.50118381, 0.38853383, 0.29807833, 0.22545385, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.65472794, 3.07277966, 2.12350607, 1.51179266, 1.08895338, 0.83188516, 0.64427125, 0.50118381, 0.38853383, 0.29807833, 0.22545385, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.65472794, 3.07277966, 2.12350607, 1.51179266, 1.08895338, 0.83188516, 0.64427125, 0.50118381, 0.41087446, 0.32104823, 0.25053367, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.65472794, 3.07277966, 2.12350607, 1.51179266, 1.08895338, 0.83188516, 0.64427125, 0.50118381, 0.41087446, 0.34370604, 0.27464288, 0.22545385, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.65472794, 3.07277966, 2.19988537, 1.61558151, 1.20157266, 0.92192322, 0.72133851, 0.57119018, 0.45573691, 0.36617002, 0.29807833, 0.25053367, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.65472794, 3.07277966, 2.19988537, 1.61558151, 1.24153244, 0.95350921, 0.74807048, 0.59516323, 0.4783645, 0.38853383, 0.32104823, 0.27464288, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 7.49001646, 4.65472794, 3.07277966, 2.19988537, 1.61558151, 1.24153244, 0.95350921, 0.74807048, 0.59516323, 0.50118381, 0.41087446, 0.34370604, 0.29807833, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+    ],
+    1.25: [
+        [14.61464119, 0.72133851, 0.02916753],
+        [14.61464119, 1.56271636, 0.50118381, 0.02916753],
+        [14.61464119, 2.05039096, 0.803307, 0.32104823, 0.02916753],
+        [14.61464119, 2.36326075, 0.95350921, 0.43325692, 0.17026083, 0.02916753],
+        [14.61464119, 2.84484982, 1.24153244, 0.59516323, 0.27464288, 0.09824532, 0.02916753],
+        [14.61464119, 3.07277966, 1.51179266, 0.803307, 0.43325692, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.36326075, 1.24153244, 0.72133851, 0.41087446, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.45070267, 1.36964464, 0.83188516, 0.52423614, 0.34370604, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.61558151, 0.98595673, 0.64427125, 0.43325692, 0.27464288, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.67050016, 1.08895338, 0.74807048, 0.52423614, 0.36617002, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.72759056, 1.162866, 0.803307, 0.59516323, 0.45573691, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.95596409, 1.84880662, 1.24153244, 0.86115354, 0.64427125, 0.4783645, 0.36617002, 0.27464288, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.95596409, 1.84880662, 1.28281462, 0.92192322, 0.69515091, 0.52423614, 0.41087446, 0.32104823, 0.25053367, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.95596409, 1.91321158, 1.32549286, 0.95350921, 0.72133851, 0.54755926, 0.43325692, 0.34370604, 0.27464288, 0.22545385, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.95596409, 1.91321158, 1.32549286, 0.95350921, 0.72133851, 0.57119018, 0.45573691, 0.36617002, 0.29807833, 0.25053367, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.95596409, 1.91321158, 1.32549286, 0.95350921, 0.74807048, 0.59516323, 0.4783645, 0.38853383, 0.32104823, 0.27464288, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 3.07277966, 2.05039096, 1.41535246, 1.05362725, 0.803307, 0.61951244, 0.50118381, 0.41087446, 0.34370604, 0.29807833, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 3.07277966, 2.05039096, 1.41535246, 1.05362725, 0.803307, 0.64427125, 0.52423614, 0.43325692, 0.36617002, 0.32104823, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 3.07277966, 2.05039096, 1.46270394, 1.08895338, 0.83188516, 0.66947293, 0.54755926, 0.45573691, 0.38853383, 0.34370604, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+    ],
+    1.30: [
+        [14.61464119, 0.72133851, 0.02916753],
+        [14.61464119, 1.24153244, 0.43325692, 0.02916753],
+        [14.61464119, 1.56271636, 0.59516323, 0.22545385, 0.02916753],
+        [14.61464119, 1.84880662, 0.803307, 0.36617002, 0.13792117, 0.02916753],
+        [14.61464119, 2.36326075, 1.01931262, 0.52423614, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.36964464, 0.74807048, 0.41087446, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 3.07277966, 1.56271636, 0.89115214, 0.54755926, 0.34370604, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 3.07277966, 1.61558151, 0.95350921, 0.61951244, 0.41087446, 0.27464288, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.45070267, 1.36964464, 0.83188516, 0.54755926, 0.36617002, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.45070267, 1.41535246, 0.92192322, 0.64427125, 0.45573691, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.6383388, 1.56271636, 1.01931262, 0.72133851, 0.50118381, 0.36617002, 0.27464288, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.61558151, 1.05362725, 0.74807048, 0.54755926, 0.41087446, 0.32104823, 0.25053367, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.61558151, 1.08895338, 0.77538133, 0.57119018, 0.43325692, 0.34370604, 0.27464288, 0.22545385, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.61558151, 1.08895338, 0.803307, 0.59516323, 0.45573691, 0.36617002, 0.29807833, 0.25053367, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.61558151, 1.08895338, 0.803307, 0.59516323, 0.4783645, 0.38853383, 0.32104823, 0.27464288, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.72759056, 1.162866, 0.83188516, 0.64427125, 0.50118381, 0.41087446, 0.34370604, 0.29807833, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.72759056, 1.162866, 0.83188516, 0.64427125, 0.52423614, 0.43325692, 0.36617002, 0.32104823, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.78698075, 1.24153244, 0.92192322, 0.72133851, 0.57119018, 0.45573691, 0.38853383, 0.34370604, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.84484982, 1.78698075, 1.24153244, 0.92192322, 0.72133851, 0.57119018, 0.4783645, 0.41087446, 0.36617002, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+    ],
+    1.35: [
+        [14.61464119, 0.69515091, 0.02916753],
+        [14.61464119, 0.95350921, 0.34370604, 0.02916753],
+        [14.61464119, 1.56271636, 0.57119018, 0.19894916, 0.02916753],
+        [14.61464119, 1.61558151, 0.69515091, 0.29807833, 0.09824532, 0.02916753],
+        [14.61464119, 1.84880662, 0.83188516, 0.43325692, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.162866, 0.64427125, 0.36617002, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.36964464, 0.803307, 0.50118381, 0.32104823, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.41535246, 0.83188516, 0.54755926, 0.36617002, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.56271636, 0.95350921, 0.64427125, 0.45573691, 0.32104823, 0.22545385, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.56271636, 0.95350921, 0.64427125, 0.45573691, 0.34370604, 0.25053367, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 3.07277966, 1.61558151, 1.01931262, 0.72133851, 0.52423614, 0.38853383, 0.29807833, 0.22545385, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 3.07277966, 1.61558151, 1.01931262, 0.72133851, 0.52423614, 0.41087446, 0.32104823, 0.25053367, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 3.07277966, 1.61558151, 1.05362725, 0.74807048, 0.54755926, 0.43325692, 0.34370604, 0.27464288, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 3.07277966, 1.72759056, 1.12534678, 0.803307, 0.59516323, 0.45573691, 0.36617002, 0.29807833, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 3.07277966, 1.72759056, 1.12534678, 0.803307, 0.59516323, 0.4783645, 0.38853383, 0.32104823, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.45070267, 1.51179266, 1.01931262, 0.74807048, 0.57119018, 0.45573691, 0.36617002, 0.32104823, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.6383388, 1.61558151, 1.08895338, 0.803307, 0.61951244, 0.50118381, 0.41087446, 0.34370604, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.6383388, 1.61558151, 1.08895338, 0.803307, 0.64427125, 0.52423614, 0.43325692, 0.36617002, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 5.85520077, 2.6383388, 1.61558151, 1.08895338, 0.803307, 0.64427125, 0.52423614, 0.45573691, 0.38853383, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+    ],
+    1.40: [
+        [14.61464119, 0.59516323, 0.02916753],
+        [14.61464119, 0.95350921, 0.34370604, 0.02916753],
+        [14.61464119, 1.08895338, 0.43325692, 0.13792117, 0.02916753],
+        [14.61464119, 1.56271636, 0.64427125, 0.27464288, 0.09824532, 0.02916753],
+        [14.61464119, 1.61558151, 0.803307, 0.43325692, 0.22545385, 0.09824532, 0.02916753],
+        [14.61464119, 2.05039096, 0.95350921, 0.54755926, 0.34370604, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.24153244, 0.72133851, 0.43325692, 0.27464288, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.24153244, 0.74807048, 0.50118381, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.28281462, 0.803307, 0.52423614, 0.36617002, 0.27464288, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.28281462, 0.803307, 0.54755926, 0.38853383, 0.29807833, 0.22545385, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.41535246, 0.86115354, 0.59516323, 0.43325692, 0.32104823, 0.25053367, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.51179266, 0.95350921, 0.64427125, 0.45573691, 0.34370604, 0.27464288, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.51179266, 0.95350921, 0.64427125, 0.4783645, 0.36617002, 0.29807833, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.56271636, 0.98595673, 0.69515091, 0.52423614, 0.41087446, 0.34370604, 0.29807833, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.56271636, 1.01931262, 0.72133851, 0.54755926, 0.43325692, 0.36617002, 0.32104823, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.61558151, 1.05362725, 0.74807048, 0.57119018, 0.45573691, 0.38853383, 0.34370604, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.61558151, 1.08895338, 0.803307, 0.61951244, 0.50118381, 0.41087446, 0.36617002, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.61558151, 1.08895338, 0.803307, 0.61951244, 0.50118381, 0.43325692, 0.38853383, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.61558151, 1.08895338, 0.803307, 0.64427125, 0.52423614, 0.45573691, 0.41087446, 0.36617002, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+    ],
+    1.45: [
+        [14.61464119, 0.59516323, 0.02916753],
+        [14.61464119, 0.803307, 0.25053367, 0.02916753],
+        [14.61464119, 0.95350921, 0.34370604, 0.09824532, 0.02916753],
+        [14.61464119, 1.24153244, 0.54755926, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 1.56271636, 0.72133851, 0.36617002, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 1.61558151, 0.803307, 0.45573691, 0.27464288, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 1.91321158, 0.95350921, 0.57119018, 0.36617002, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 2.19988537, 1.08895338, 0.64427125, 0.41087446, 0.27464288, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.24153244, 0.74807048, 0.50118381, 0.34370604, 0.25053367, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.24153244, 0.74807048, 0.50118381, 0.36617002, 0.27464288, 0.22545385, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.28281462, 0.803307, 0.54755926, 0.41087446, 0.32104823, 0.25053367, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.28281462, 0.803307, 0.57119018, 0.43325692, 0.34370604, 0.27464288, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.28281462, 0.83188516, 0.59516323, 0.45573691, 0.36617002, 0.29807833, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.28281462, 0.83188516, 0.59516323, 0.45573691, 0.36617002, 0.32104823, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.51179266, 0.95350921, 0.69515091, 0.52423614, 0.41087446, 0.34370604, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.51179266, 0.95350921, 0.69515091, 0.52423614, 0.43325692, 0.36617002, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.56271636, 0.98595673, 0.72133851, 0.54755926, 0.45573691, 0.38853383, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.56271636, 1.01931262, 0.74807048, 0.57119018, 0.4783645, 0.41087446, 0.36617002, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.84484982, 1.56271636, 1.01931262, 0.74807048, 0.59516323, 0.50118381, 0.43325692, 0.38853383, 0.36617002, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+    ],
+    1.50: [
+        [14.61464119, 0.54755926, 0.02916753],
+        [14.61464119, 0.803307, 0.25053367, 0.02916753],
+        [14.61464119, 0.86115354, 0.32104823, 0.09824532, 0.02916753],
+        [14.61464119, 1.24153244, 0.54755926, 0.25053367, 0.09824532, 0.02916753],
+        [14.61464119, 1.56271636, 0.72133851, 0.36617002, 0.19894916, 0.09824532, 0.02916753],
+        [14.61464119, 1.61558151, 0.803307, 0.45573691, 0.27464288, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 1.61558151, 0.83188516, 0.52423614, 0.34370604, 0.25053367, 0.17026083, 0.09824532, 0.02916753],
+        [14.61464119, 1.84880662, 0.95350921, 0.59516323, 0.38853383, 0.27464288, 0.19894916, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 1.84880662, 0.95350921, 0.59516323, 0.41087446, 0.29807833, 0.22545385, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 1.84880662, 0.95350921, 0.61951244, 0.43325692, 0.32104823, 0.25053367, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.19988537, 1.12534678, 0.72133851, 0.50118381, 0.36617002, 0.27464288, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.19988537, 1.12534678, 0.72133851, 0.50118381, 0.36617002, 0.29807833, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.36326075, 1.24153244, 0.803307, 0.57119018, 0.43325692, 0.34370604, 0.29807833, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.36326075, 1.24153244, 0.803307, 0.57119018, 0.43325692, 0.34370604, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.36326075, 1.24153244, 0.803307, 0.59516323, 0.45573691, 0.36617002, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.36326075, 1.24153244, 0.803307, 0.59516323, 0.45573691, 0.38853383, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.32549286, 0.86115354, 0.64427125, 0.50118381, 0.41087446, 0.36617002, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.36964464, 0.92192322, 0.69515091, 0.54755926, 0.45573691, 0.41087446, 0.36617002, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+        [14.61464119, 2.45070267, 1.41535246, 0.95350921, 0.72133851, 0.57119018, 0.4783645, 0.43325692, 0.38853383, 0.36617002, 0.34370604, 0.32104823, 0.29807833, 0.27464288, 0.25053367, 0.22545385, 0.19894916, 0.17026083, 0.13792117, 0.09824532, 0.02916753],
+    ],
+}
+
+
+class GITSScheduler(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="GITSScheduler_V3",
+            category="sampling/custom_sampling/schedulers",
+            inputs=[
+                io.Float.Input("coeff", default=1.20, min=0.80, max=1.50, step=0.05),
+                io.Int.Input("steps", default=10, min=2, max=1000),
+                io.Float.Input("denoise", default=1.0, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[
+                io.Sigmas.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, coeff, steps, denoise):
+        total_steps = steps
+        if denoise < 1.0:
+            if denoise <= 0.0:
+                return io.NodeOutput(torch.FloatTensor([]))
+            total_steps = round(steps * denoise)
+
+        if steps <= 20:
+            sigmas = NOISE_LEVELS[round(coeff, 2)][steps-2][:]
+        else:
+            sigmas = NOISE_LEVELS[round(coeff, 2)][-1][:]
+            sigmas = loglinear_interp(sigmas, steps + 1)
+
+        sigmas = sigmas[-(total_steps + 1):]
+        sigmas[-1] = 0
+        return io.NodeOutput(torch.FloatTensor(sigmas))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    GITSScheduler,
+]

comfy_extras/v3/nodes_hidream.py

@@ -0,0 +1,71 @@
+from __future__ import annotations
+
+import comfy.model_management
+import comfy.sd
+import folder_paths
+from comfy_api.latest import io
+
+
+class QuadrupleCLIPLoader(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="QuadrupleCLIPLoader_V3",
+            category="advanced/loaders",
+            description="[Recipes]\n\nhidream: long clip-l, long clip-g, t5xxl, llama_8b_3.1_instruct",
+            inputs=[
+                io.Combo.Input("clip_name1", options=folder_paths.get_filename_list("text_encoders")),
+                io.Combo.Input("clip_name2", options=folder_paths.get_filename_list("text_encoders")),
+                io.Combo.Input("clip_name3", options=folder_paths.get_filename_list("text_encoders")),
+                io.Combo.Input("clip_name4", options=folder_paths.get_filename_list("text_encoders")),
+            ],
+            outputs=[
+                io.Clip.Output(),
+            ]
+        )
+
+    @classmethod
+    def execute(cls, clip_name1, clip_name2, clip_name3, clip_name4):
+        clip_path1 = folder_paths.get_full_path_or_raise("text_encoders", clip_name1)
+        clip_path2 = folder_paths.get_full_path_or_raise("text_encoders", clip_name2)
+        clip_path3 = folder_paths.get_full_path_or_raise("text_encoders", clip_name3)
+        clip_path4 = folder_paths.get_full_path_or_raise("text_encoders", clip_name4)
+        return io.NodeOutput(
+            comfy.sd.load_clip(
+                ckpt_paths=[clip_path1, clip_path2, clip_path3, clip_path4],
+                embedding_directory=folder_paths.get_folder_paths("embeddings"),
+            )
+        )
+
+
+class CLIPTextEncodeHiDream(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeHiDream_V3",
+            category="advanced/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("clip_l", multiline=True, dynamic_prompts=True),
+                io.String.Input("clip_g", multiline=True, dynamic_prompts=True),
+                io.String.Input("t5xxl", multiline=True, dynamic_prompts=True),
+                io.String.Input("llama", multiline=True, dynamic_prompts=True),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ]
+        )
+
+    @classmethod
+    def execute(cls, clip, clip_l, clip_g, t5xxl, llama):
+        tokens = clip.tokenize(clip_g)
+        tokens["l"] = clip.tokenize(clip_l)["l"]
+        tokens["t5xxl"] = clip.tokenize(t5xxl)["t5xxl"]
+        tokens["llama"] = clip.tokenize(llama)["llama"]
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CLIPTextEncodeHiDream,
+    QuadrupleCLIPLoader,
+]

comfy_extras/v3/nodes_hunyuan.py

@@ -0,0 +1,169 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.model_management
+import node_helpers
+import nodes
+from comfy_api.latest import io
+
+
+class CLIPTextEncodeHunyuanDiT(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeHunyuanDiT_V3",
+            category="advanced/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("bert", multiline=True, dynamic_prompts=True),
+                io.String.Input("mt5xl", multiline=True, dynamic_prompts=True),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, clip, bert, mt5xl):
+        tokens = clip.tokenize(bert)
+        tokens["mt5xl"] = clip.tokenize(mt5xl)["mt5xl"]
+
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens))
+
+
+class EmptyHunyuanLatentVideo(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="EmptyHunyuanLatentVideo_V3",
+            category="latent/video",
+            inputs=[
+                io.Int.Input("width", default=848, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("height", default=480, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("length", default=25, min=1, max=nodes.MAX_RESOLUTION, step=4),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, width, height, length, batch_size):
+        latent = torch.zeros(
+            [batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8],
+            device=comfy.model_management.intermediate_device(),
+        )
+        return io.NodeOutput({"samples":latent})
+
+
+PROMPT_TEMPLATE_ENCODE_VIDEO_I2V = (
+    "<|start_header_id|>system<|end_header_id|>\n\n<image>\nDescribe the video by detailing the following aspects according to the reference image: "
+    "1. The main content and theme of the video."
+    "2. The color, shape, size, texture, quantity, text, and spatial relationships of the objects."
+    "3. Actions, events, behaviors temporal relationships, physical movement changes of the objects."
+    "4. background environment, light, style and atmosphere."
+    "5. camera angles, movements, and transitions used in the video:<|eot_id|>\n\n"
+    "<|start_header_id|>user<|end_header_id|>\n\n{}<|eot_id|>"
+    "<|start_header_id|>assistant<|end_header_id|>\n\n"
+)
+
+
+class TextEncodeHunyuanVideo_ImageToVideo(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="TextEncodeHunyuanVideo_ImageToVideo_V3",
+            category="advanced/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.ClipVisionOutput.Input("clip_vision_output"),
+                io.String.Input("prompt", multiline=True, dynamic_prompts=True),
+                io.Int.Input(
+                    "image_interleave",
+                    default=2,
+                    min=1,
+                    max=512,
+                    tooltip="How much the image influences things vs the text prompt. Higher number means more influence from the text prompt.",
+                ),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, clip, clip_vision_output, prompt, image_interleave):
+        tokens = clip.tokenize(
+            prompt, llama_template=PROMPT_TEMPLATE_ENCODE_VIDEO_I2V,
+            image_embeds=clip_vision_output.mm_projected,
+            image_interleave=image_interleave,
+        )
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens))
+
+
+class HunyuanImageToVideo(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="HunyuanImageToVideo_V3",
+            category="conditioning/video_models",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Vae.Input("vae"),
+                io.Int.Input("width", default=848, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("height", default=480, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("length", default=53, min=1, max=nodes.MAX_RESOLUTION, step=4),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+                io.Combo.Input("guidance_type", options=["v1 (concat)", "v2 (replace)", "custom"]),
+                io.Image.Input("start_image", optional=True),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, positive, vae, width, height, length, batch_size, guidance_type, start_image=None):
+        latent = torch.zeros(
+            [batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8],
+            device=comfy.model_management.intermediate_device(),
+        )
+        out_latent = {}
+
+        if start_image is not None:
+            start_image = comfy.utils.common_upscale(
+                start_image[:length, :, :, :3].movedim(-1, 1), width, height, "bilinear", "center"
+            ).movedim(1, -1)
+
+            concat_latent_image = vae.encode(start_image)
+            mask = torch.ones(
+                (1, 1, latent.shape[2], concat_latent_image.shape[-2], concat_latent_image.shape[-1]),
+                device=start_image.device,
+                dtype=start_image.dtype,
+            )
+            mask[:, :, :((start_image.shape[0] - 1) // 4) + 1] = 0.0
+
+            if guidance_type == "v1 (concat)":
+                cond = {"concat_latent_image": concat_latent_image, "concat_mask": mask}
+            elif guidance_type == "v2 (replace)":
+                cond = {'guiding_frame_index': 0}
+                latent[:, :, :concat_latent_image.shape[2]] = concat_latent_image
+                out_latent["noise_mask"] = mask
+            elif guidance_type == "custom":
+                cond = {"ref_latent": concat_latent_image}
+
+            positive = node_helpers.conditioning_set_values(positive, cond)
+
+        out_latent["samples"] = latent
+        return io.NodeOutput(positive, out_latent)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CLIPTextEncodeHunyuanDiT,
+    EmptyHunyuanLatentVideo,
+    HunyuanImageToVideo,
+    TextEncodeHunyuanVideo_ImageToVideo,
+]

comfy_extras/v3/nodes_hunyuan3d.py

@@ -0,0 +1,672 @@
+from __future__ import annotations
+
+import json
+import os
+import struct
+
+import numpy as np
+import torch
+
+import comfy.model_management
+import folder_paths
+from comfy.cli_args import args
+from comfy.ldm.modules.diffusionmodules.mmdit import (
+    get_1d_sincos_pos_embed_from_grid_torch,
+)
+from comfy_api.latest import io
+
+
+class VOXEL:
+    def __init__(self, data):
+        self.data = data
+
+
+class MESH:
+    def __init__(self, vertices, faces):
+        self.vertices = vertices
+        self.faces = faces
+
+
+def voxel_to_mesh(voxels, threshold=0.5, device=None):
+    if device is None:
+        device = torch.device("cpu")
+    voxels = voxels.to(device)
+
+    binary = (voxels > threshold).float()
+    padded = torch.nn.functional.pad(binary, (1, 1, 1, 1, 1, 1), 'constant', 0)
+
+    D, H, W = binary.shape
+
+    neighbors = torch.tensor([
+        [0, 0, 1],
+        [0, 0, -1],
+        [0, 1, 0],
+        [0, -1, 0],
+        [1, 0, 0],
+        [-1, 0, 0]
+    ], device=device)
+
+    z, y, x = torch.meshgrid(
+        torch.arange(D, device=device),
+        torch.arange(H, device=device),
+        torch.arange(W, device=device),
+        indexing='ij'
+    )
+    voxel_indices = torch.stack([z.flatten(), y.flatten(), x.flatten()], dim=1)
+
+    solid_mask = binary.flatten() > 0
+    solid_indices = voxel_indices[solid_mask]
+
+    corner_offsets = [
+        torch.tensor([
+            [0, 0, 1], [0, 1, 1], [1, 1, 1], [1, 0, 1]
+        ], device=device),
+        torch.tensor([
+            [0, 0, 0], [1, 0, 0], [1, 1, 0], [0, 1, 0]
+        ], device=device),
+        torch.tensor([
+            [0, 1, 0], [1, 1, 0], [1, 1, 1], [0, 1, 1]
+        ], device=device),
+        torch.tensor([
+            [0, 0, 0], [0, 0, 1], [1, 0, 1], [1, 0, 0]
+        ], device=device),
+        torch.tensor([
+            [1, 0, 1], [1, 1, 1], [1, 1, 0], [1, 0, 0]
+        ], device=device),
+        torch.tensor([
+            [0, 1, 0], [0, 1, 1], [0, 0, 1], [0, 0, 0]
+        ], device=device)
+    ]
+
+    all_vertices = []
+    all_indices = []
+
+    vertex_count = 0
+
+    for face_idx, offset in enumerate(neighbors):
+        neighbor_indices = solid_indices + offset
+
+        padded_indices = neighbor_indices + 1
+
+        is_exposed = padded[
+            padded_indices[:, 0],
+            padded_indices[:, 1],
+            padded_indices[:, 2]
+        ] == 0
+
+        if not is_exposed.any():
+            continue
+
+        exposed_indices = solid_indices[is_exposed]
+
+        corners = corner_offsets[face_idx].unsqueeze(0)
+
+        face_vertices = exposed_indices.unsqueeze(1) + corners
+
+        all_vertices.append(face_vertices.reshape(-1, 3))
+
+        num_faces = exposed_indices.shape[0]
+        face_indices = torch.arange(
+            vertex_count,
+            vertex_count + 4 * num_faces,
+            device=device
+        ).reshape(-1, 4)
+
+        all_indices.append(torch.stack([face_indices[:, 0], face_indices[:, 1], face_indices[:, 2]], dim=1))
+        all_indices.append(torch.stack([face_indices[:, 0], face_indices[:, 2], face_indices[:, 3]], dim=1))
+
+        vertex_count += 4 * num_faces
+
+    if len(all_vertices) > 0:
+        vertices = torch.cat(all_vertices, dim=0)
+        faces = torch.cat(all_indices, dim=0)
+    else:
+        vertices = torch.zeros((1, 3))
+        faces = torch.zeros((1, 3))
+
+    v_min = 0
+    v_max = max(voxels.shape)
+
+    vertices = vertices - (v_min + v_max) / 2
+
+    scale = (v_max - v_min) / 2
+    if scale > 0:
+        vertices = vertices / scale
+
+    vertices = torch.fliplr(vertices)
+    return vertices, faces
+
+def voxel_to_mesh_surfnet(voxels, threshold=0.5, device=None):
+    if device is None:
+        device = torch.device("cpu")
+    voxels = voxels.to(device)
+
+    D, H, W = voxels.shape
+
+    padded = torch.nn.functional.pad(voxels, (1, 1, 1, 1, 1, 1), 'constant', 0)
+    z, y, x = torch.meshgrid(
+        torch.arange(D, device=device),
+        torch.arange(H, device=device),
+        torch.arange(W, device=device),
+        indexing='ij'
+    )
+    cell_positions = torch.stack([z.flatten(), y.flatten(), x.flatten()], dim=1)
+
+    corner_offsets = torch.tensor([
+        [0, 0, 0], [1, 0, 0], [0, 1, 0], [1, 1, 0],
+        [0, 0, 1], [1, 0, 1], [0, 1, 1], [1, 1, 1]
+    ], device=device)
+
+    corner_values = torch.zeros((cell_positions.shape[0], 8), device=device)
+    for c, (dz, dy, dx) in enumerate(corner_offsets):
+        corner_values[:, c] = padded[
+            cell_positions[:, 0] + dz,
+            cell_positions[:, 1] + dy,
+            cell_positions[:, 2] + dx
+        ]
+
+    corner_signs = corner_values > threshold
+    has_inside = torch.any(corner_signs, dim=1)
+    has_outside = torch.any(~corner_signs, dim=1)
+    contains_surface = has_inside & has_outside
+
+    active_cells = cell_positions[contains_surface]
+    active_signs = corner_signs[contains_surface]
+    active_values = corner_values[contains_surface]
+
+    if active_cells.shape[0] == 0:
+        return torch.zeros((0, 3), device=device), torch.zeros((0, 3), dtype=torch.long, device=device)
+
+    edges = torch.tensor([
+        [0, 1], [0, 2], [0, 4], [1, 3],
+        [1, 5], [2, 3], [2, 6], [3, 7],
+        [4, 5], [4, 6], [5, 7], [6, 7]
+    ], device=device)
+
+    cell_vertices = {}
+    progress = comfy.utils.ProgressBar(100)
+
+    for edge_idx, (e1, e2) in enumerate(edges):
+        progress.update(1)
+        crossing = active_signs[:, e1] != active_signs[:, e2]
+        if not crossing.any():
+            continue
+
+        cell_indices = torch.nonzero(crossing, as_tuple=True)[0]
+
+        v1 = active_values[cell_indices, e1]
+        v2 = active_values[cell_indices, e2]
+
+        t = torch.zeros_like(v1, device=device)
+        denom = v2 - v1
+        valid = denom != 0
+        t[valid] = (threshold - v1[valid]) / denom[valid]
+        t[~valid] = 0.5
+
+        p1 = corner_offsets[e1].float()
+        p2 = corner_offsets[e2].float()
+
+        intersection = p1.unsqueeze(0) + t.unsqueeze(1) * (p2.unsqueeze(0) - p1.unsqueeze(0))
+
+        for i, point in zip(cell_indices.tolist(), intersection):
+            if i not in cell_vertices:
+                cell_vertices[i] = []
+            cell_vertices[i].append(point)
+
+    # Calculate the final vertices as the average of intersection points for each cell
+    vertices = []
+    vertex_lookup = {}
+
+    vert_progress_mod = round(len(cell_vertices)/50)
+
+    for i, points in cell_vertices.items():
+        if not i % vert_progress_mod:
+            progress.update(1)
+
+        if points:
+            vertex = torch.stack(points).mean(dim=0)
+            vertex = vertex + active_cells[i].float()
+            vertex_lookup[tuple(active_cells[i].tolist())] = len(vertices)
+            vertices.append(vertex)
+
+    if not vertices:
+        return torch.zeros((0, 3), device=device), torch.zeros((0, 3), dtype=torch.long, device=device)
+
+    final_vertices = torch.stack(vertices)
+
+    inside_corners_mask = active_signs
+    outside_corners_mask = ~active_signs
+
+    inside_counts = inside_corners_mask.sum(dim=1, keepdim=True).float()
+    outside_counts = outside_corners_mask.sum(dim=1, keepdim=True).float()
+
+    inside_pos = torch.zeros((active_cells.shape[0], 3), device=device)
+    outside_pos = torch.zeros((active_cells.shape[0], 3), device=device)
+
+    for i in range(8):
+        mask_inside = inside_corners_mask[:, i].unsqueeze(1)
+        mask_outside = outside_corners_mask[:, i].unsqueeze(1)
+        inside_pos += corner_offsets[i].float().unsqueeze(0) * mask_inside
+        outside_pos += corner_offsets[i].float().unsqueeze(0) * mask_outside
+
+    inside_pos /= inside_counts
+    outside_pos /= outside_counts
+    gradients = inside_pos - outside_pos
+
+    pos_dirs = torch.tensor([
+        [1, 0, 0],
+        [0, 1, 0],
+        [0, 0, 1]
+    ], device=device)
+
+    cross_products = [
+        torch.linalg.cross(pos_dirs[i].float(), pos_dirs[j].float())
+        for i in range(3) for j in range(i+1, 3)
+    ]
+
+    faces = []
+    all_keys = set(vertex_lookup.keys())
+
+    face_progress_mod = round(len(active_cells)/38*3)
+
+    for pair_idx, (i, j) in enumerate([(0,1), (0,2), (1,2)]):
+        dir_i = pos_dirs[i]
+        dir_j = pos_dirs[j]
+        cross_product = cross_products[pair_idx]
+
+        ni_positions = active_cells + dir_i
+        nj_positions = active_cells + dir_j
+        diag_positions = active_cells + dir_i + dir_j
+
+        alignments = torch.matmul(gradients, cross_product)
+
+        valid_quads = []
+        quad_indices = []
+
+        for idx, active_cell in enumerate(active_cells):
+            if not idx % face_progress_mod:
+                progress.update(1)
+            cell_key = tuple(active_cell.tolist())
+            ni_key = tuple(ni_positions[idx].tolist())
+            nj_key = tuple(nj_positions[idx].tolist())
+            diag_key = tuple(diag_positions[idx].tolist())
+
+            if cell_key in all_keys and ni_key in all_keys and nj_key in all_keys and diag_key in all_keys:
+                v0 = vertex_lookup[cell_key]
+                v1 = vertex_lookup[ni_key]
+                v2 = vertex_lookup[nj_key]
+                v3 = vertex_lookup[diag_key]
+
+                valid_quads.append((v0, v1, v2, v3))
+                quad_indices.append(idx)
+
+        for q_idx, (v0, v1, v2, v3) in enumerate(valid_quads):
+            cell_idx = quad_indices[q_idx]
+            if alignments[cell_idx] > 0:
+                faces.append(torch.tensor([v0, v1, v3], device=device, dtype=torch.long))
+                faces.append(torch.tensor([v0, v3, v2], device=device, dtype=torch.long))
+            else:
+                faces.append(torch.tensor([v0, v3, v1], device=device, dtype=torch.long))
+                faces.append(torch.tensor([v0, v2, v3], device=device, dtype=torch.long))
+
+    if faces:
+        faces = torch.stack(faces)
+    else:
+        faces = torch.zeros((0, 3), dtype=torch.long, device=device)
+
+    v_min = 0
+    v_max = max(D, H, W)
+
+    final_vertices = final_vertices - (v_min + v_max) / 2
+
+    scale = (v_max - v_min) / 2
+    if scale > 0:
+        final_vertices = final_vertices / scale
+
+    final_vertices = torch.fliplr(final_vertices)
+
+    return final_vertices, faces
+
+
+def save_glb(vertices, faces, filepath, metadata=None):
+    """
+    Save PyTorch tensor vertices and faces as a GLB file without external dependencies.
+
+    Parameters:
+    vertices: torch.Tensor of shape (N, 3) - The vertex coordinates
+    faces: torch.Tensor of shape (M, 3) - The face indices (triangle faces)
+    filepath: str - Output filepath (should end with .glb)
+    """
+
+    # Convert tensors to numpy arrays
+    vertices_np = vertices.cpu().numpy().astype(np.float32)
+    faces_np = faces.cpu().numpy().astype(np.uint32)
+
+    vertices_buffer = vertices_np.tobytes()
+    indices_buffer = faces_np.tobytes()
+
+    def pad_to_4_bytes(buffer):
+        padding_length = (4 - (len(buffer) % 4)) % 4
+        return buffer + b'\x00' * padding_length
+
+    vertices_buffer_padded = pad_to_4_bytes(vertices_buffer)
+    indices_buffer_padded = pad_to_4_bytes(indices_buffer)
+
+    buffer_data = vertices_buffer_padded + indices_buffer_padded
+
+    vertices_byte_length = len(vertices_buffer)
+    vertices_byte_offset = 0
+    indices_byte_length = len(indices_buffer)
+    indices_byte_offset = len(vertices_buffer_padded)
+
+    gltf = {
+        "asset": {"version": "2.0", "generator": "ComfyUI"},
+        "buffers": [
+            {
+                "byteLength": len(buffer_data)
+            }
+        ],
+        "bufferViews": [
+            {
+                "buffer": 0,
+                "byteOffset": vertices_byte_offset,
+                "byteLength": vertices_byte_length,
+                "target": 34962  # ARRAY_BUFFER
+            },
+            {
+                "buffer": 0,
+                "byteOffset": indices_byte_offset,
+                "byteLength": indices_byte_length,
+                "target": 34963  # ELEMENT_ARRAY_BUFFER
+            }
+        ],
+        "accessors": [
+            {
+                "bufferView": 0,
+                "byteOffset": 0,
+                "componentType": 5126,  # FLOAT
+                "count": len(vertices_np),
+                "type": "VEC3",
+                "max": vertices_np.max(axis=0).tolist(),
+                "min": vertices_np.min(axis=0).tolist()
+            },
+            {
+                "bufferView": 1,
+                "byteOffset": 0,
+                "componentType": 5125,  # UNSIGNED_INT
+                "count": faces_np.size,
+                "type": "SCALAR"
+            }
+        ],
+        "meshes": [
+            {
+                "primitives": [
+                    {
+                        "attributes": {
+                            "POSITION": 0
+                        },
+                        "indices": 1,
+                        "mode": 4  # TRIANGLES
+                    }
+                ]
+            }
+        ],
+        "nodes": [
+            {
+                "mesh": 0
+            }
+        ],
+        "scenes": [
+            {
+                "nodes": [0]
+            }
+        ],
+        "scene": 0
+    }
+
+    if metadata is not None:
+        gltf["asset"]["extras"] = metadata
+
+    # Convert the JSON to bytes
+    gltf_json = json.dumps(gltf).encode('utf8')
+
+    def pad_json_to_4_bytes(buffer):
+        padding_length = (4 - (len(buffer) % 4)) % 4
+        return buffer + b' ' * padding_length
+
+    gltf_json_padded = pad_json_to_4_bytes(gltf_json)
+
+    # Create the GLB header
+    # Magic glTF
+    glb_header = struct.pack('<4sII', b'glTF', 2, 12 + 8 + len(gltf_json_padded) + 8 + len(buffer_data))
+
+    # Create JSON chunk header (chunk type 0)
+    json_chunk_header = struct.pack('<II', len(gltf_json_padded), 0x4E4F534A)  # "JSON" in little endian
+
+    # Create BIN chunk header (chunk type 1)
+    bin_chunk_header = struct.pack('<II', len(buffer_data), 0x004E4942)  # "BIN\0" in little endian
+
+    # Write the GLB file
+    with open(filepath, 'wb') as f:
+        f.write(glb_header)
+        f.write(json_chunk_header)
+        f.write(gltf_json_padded)
+        f.write(bin_chunk_header)
+        f.write(buffer_data)
+
+    return filepath
+
+
+class EmptyLatentHunyuan3Dv2(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="EmptyLatentHunyuan3Dv2_V3",
+            category="latent/3d",
+            inputs=[
+                io.Int.Input("resolution", default=3072, min=1, max=8192),
+                io.Int.Input("batch_size", default=1, min=1, max=4096, tooltip="The number of latent images in the batch.")
+            ],
+            outputs=[
+                io.Latent.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, resolution, batch_size):
+        latent = torch.zeros([batch_size, 64, resolution], device=comfy.model_management.intermediate_device())
+        return io.NodeOutput({"samples": latent, "type": "hunyuan3dv2"})
+
+
+class Hunyuan3Dv2Conditioning(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Hunyuan3Dv2Conditioning_V3",
+            category="conditioning/video_models",
+            inputs=[
+                io.ClipVisionOutput.Input("clip_vision_output")
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative")
+            ]
+        )
+
+    @classmethod
+    def execute(cls, clip_vision_output):
+        embeds = clip_vision_output.last_hidden_state
+        positive = [[embeds, {}]]
+        negative = [[torch.zeros_like(embeds), {}]]
+        return io.NodeOutput(positive, negative)
+
+
+class Hunyuan3Dv2ConditioningMultiView(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Hunyuan3Dv2ConditioningMultiView_V3",
+            category="conditioning/video_models",
+            inputs=[
+                io.ClipVisionOutput.Input("front", optional=True),
+                io.ClipVisionOutput.Input("left", optional=True),
+                io.ClipVisionOutput.Input("back", optional=True),
+                io.ClipVisionOutput.Input("right", optional=True)
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative")
+            ]
+        )
+
+    @classmethod
+    def execute(cls, front=None, left=None, back=None, right=None):
+        all_embeds = [front, left, back, right]
+        out = []
+        pos_embeds = None
+        for i, e in enumerate(all_embeds):
+            if e is not None:
+                if pos_embeds is None:
+                    pos_embeds = get_1d_sincos_pos_embed_from_grid_torch(e.last_hidden_state.shape[-1], torch.arange(4))
+                out.append(e.last_hidden_state + pos_embeds[i].reshape(1, 1, -1))
+
+        embeds = torch.cat(out, dim=1)
+        positive = [[embeds, {}]]
+        negative = [[torch.zeros_like(embeds), {}]]
+        return io.NodeOutput(positive, negative)
+
+
+class SaveGLB(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SaveGLB_V3",
+            category="3d",
+            is_output_node=True,
+            inputs=[
+                io.Mesh.Input("mesh"),
+                io.String.Input("filename_prefix", default="mesh/ComfyUI")
+            ],
+            outputs=[],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo]
+        )
+
+    @classmethod
+    def execute(cls, mesh, filename_prefix):
+        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, folder_paths.get_output_directory())
+        results = []
+
+        metadata = {}
+        if not args.disable_metadata:
+            if cls.hidden.prompt is not None:
+                metadata["prompt"] = json.dumps(cls.hidden.prompt)
+            if cls.hidden.extra_pnginfo is not None:
+                for x in cls.hidden.extra_pnginfo:
+                    metadata[x] = json.dumps(cls.hidden.extra_pnginfo[x])
+
+        for i in range(mesh.vertices.shape[0]):
+            f = f"{filename}_{counter:05}_.glb"
+            save_glb(mesh.vertices[i], mesh.faces[i], os.path.join(full_output_folder, f), metadata)
+            results.append({
+                "filename": f,
+                "subfolder": subfolder,
+                "type": "output"
+            })
+            counter += 1
+
+        return io.NodeOutput(ui={"ui": {"3d": results}})  # TODO: do we need an additional type of preview for this?
+
+
+class VAEDecodeHunyuan3D(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="VAEDecodeHunyuan3D_V3",
+            category="latent/3d",
+            inputs=[
+                io.Latent.Input("samples"),
+                io.Vae.Input("vae"),
+                io.Int.Input("num_chunks", default=8000, min=1000, max=500000),
+                io.Int.Input("octree_resolution", default=256, min=16, max=512)
+            ],
+            outputs=[
+                io.Voxel.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, vae, samples, num_chunks, octree_resolution):
+        voxels = VOXEL(vae.decode(samples["samples"], vae_options={"num_chunks": num_chunks, "octree_resolution": octree_resolution}))
+        return io.NodeOutput(voxels)
+
+
+class VoxelToMesh(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="VoxelToMesh_V3",
+            category="3d",
+            inputs=[
+                io.Voxel.Input("voxel"),
+                io.Combo.Input("algorithm", options=["surface net", "basic"]),
+                io.Float.Input("threshold", default=0.6, min=-1.0, max=1.0, step=0.01)
+            ],
+            outputs=[
+                io.Mesh.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, voxel, algorithm, threshold):
+        vertices = []
+        faces = []
+
+        if algorithm == "basic":
+            mesh_function = voxel_to_mesh
+        elif algorithm == "surface net":
+            mesh_function = voxel_to_mesh_surfnet
+
+        for x in voxel.data:
+            v, f = mesh_function(x, threshold=threshold, device=None)
+            vertices.append(v)
+            faces.append(f)
+
+        return io.NodeOutput(MESH(torch.stack(vertices), torch.stack(faces)))
+
+
+class VoxelToMeshBasic(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="VoxelToMeshBasic_V3",
+            category="3d",
+            inputs=[
+                io.Voxel.Input("voxel"),
+                io.Float.Input("threshold", default=0.6, min=-1.0, max=1.0, step=0.01)
+            ],
+            outputs=[
+                io.Mesh.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, voxel, threshold):
+        vertices = []
+        faces = []
+        for x in voxel.data:
+            v, f = voxel_to_mesh(x, threshold=threshold, device=None)
+            vertices.append(v)
+            faces.append(f)
+
+        return io.NodeOutput(MESH(torch.stack(vertices), torch.stack(faces)))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    EmptyLatentHunyuan3Dv2,
+    Hunyuan3Dv2Conditioning,
+    Hunyuan3Dv2ConditioningMultiView,
+    SaveGLB,
+    VAEDecodeHunyuan3D,
+    VoxelToMesh,
+    VoxelToMeshBasic,
+]

comfy_extras/v3/nodes_hypernetwork.py

@@ -0,0 +1,136 @@
+from __future__ import annotations
+
+import logging
+
+import torch
+
+import comfy.utils
+import folder_paths
+from comfy_api.latest import io
+
+
+def load_hypernetwork_patch(path, strength):
+    sd = comfy.utils.load_torch_file(path, safe_load=True)
+    activation_func = sd.get('activation_func', 'linear')
+    is_layer_norm = sd.get('is_layer_norm', False)
+    use_dropout = sd.get('use_dropout', False)
+    activate_output = sd.get('activate_output', False)
+    last_layer_dropout = sd.get('last_layer_dropout', False)
+
+    valid_activation = {
+        "linear": torch.nn.Identity,
+        "relu": torch.nn.ReLU,
+        "leakyrelu": torch.nn.LeakyReLU,
+        "elu": torch.nn.ELU,
+        "swish": torch.nn.Hardswish,
+        "tanh": torch.nn.Tanh,
+        "sigmoid": torch.nn.Sigmoid,
+        "softsign": torch.nn.Softsign,
+        "mish": torch.nn.Mish,
+    }
+
+    logging.error(
+        "Unsupported Hypernetwork format, if you report it I might implement it. {}   {} {} {} {} {}".format(
+            path, activation_func, is_layer_norm, use_dropout, activate_output, last_layer_dropout
+        )
+    )
+
+    out = {}
+
+    for d in sd:
+        try:
+            dim = int(d)
+        except Exception:
+            continue
+
+        output = []
+        for index in [0, 1]:
+            attn_weights = sd[dim][index]
+            keys = attn_weights.keys()
+
+            linears = filter(lambda a: a.endswith(".weight"), keys)
+            linears = list(map(lambda a: a[:-len(".weight")], linears))
+            layers = []
+
+            i = 0
+            while i < len(linears):
+                lin_name = linears[i]
+                last_layer = (i == (len(linears) - 1))
+                penultimate_layer = (i == (len(linears) - 2))
+
+                lin_weight = attn_weights['{}.weight'.format(lin_name)]
+                lin_bias = attn_weights['{}.bias'.format(lin_name)]
+                layer = torch.nn.Linear(lin_weight.shape[1], lin_weight.shape[0])
+                layer.load_state_dict({"weight": lin_weight, "bias": lin_bias})
+                layers.append(layer)
+                if activation_func != "linear":
+                    if (not last_layer) or (activate_output):
+                        layers.append(valid_activation[activation_func]())
+                if is_layer_norm:
+                    i += 1
+                    ln_name = linears[i]
+                    ln_weight = attn_weights['{}.weight'.format(ln_name)]
+                    ln_bias = attn_weights['{}.bias'.format(ln_name)]
+                    ln = torch.nn.LayerNorm(ln_weight.shape[0])
+                    ln.load_state_dict({"weight": ln_weight, "bias": ln_bias})
+                    layers.append(ln)
+                if use_dropout:
+                    if (not last_layer) and (not penultimate_layer or last_layer_dropout):
+                        layers.append(torch.nn.Dropout(p=0.3))
+                i += 1
+
+            output.append(torch.nn.Sequential(*layers))
+        out[dim] = torch.nn.ModuleList(output)
+
+    class hypernetwork_patch:
+        def __init__(self, hypernet, strength):
+            self.hypernet = hypernet
+            self.strength = strength
+
+        def __call__(self, q, k, v, extra_options):
+            dim = k.shape[-1]
+            if dim in self.hypernet:
+                hn = self.hypernet[dim]
+                k = k + hn[0](k) * self.strength
+                v = v + hn[1](v) * self.strength
+
+            return q, k, v
+
+        def to(self, device):
+            for d in self.hypernet.keys():
+                self.hypernet[d] = self.hypernet[d].to(device)
+            return self
+
+    return hypernetwork_patch(out, strength)
+
+
+class HypernetworkLoader(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="HypernetworkLoader_V3",
+            category="loaders",
+            inputs=[
+                io.Model.Input("model"),
+                io.Combo.Input("hypernetwork_name", options=folder_paths.get_filename_list("hypernetworks")),
+                io.Float.Input("strength", default=1.0, min=-10.0, max=10.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, hypernetwork_name, strength):
+        hypernetwork_path = folder_paths.get_full_path_or_raise("hypernetworks", hypernetwork_name)
+        model_hypernetwork = model.clone()
+        patch = load_hypernetwork_patch(hypernetwork_path, strength)
+        if patch is not None:
+            model_hypernetwork.set_model_attn1_patch(patch)
+            model_hypernetwork.set_model_attn2_patch(patch)
+        return io.NodeOutput(model_hypernetwork)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    HypernetworkLoader,
+]

comfy_extras/v3/nodes_hypertile.py

@@ -0,0 +1,95 @@
+"""Taken from: https://github.com/tfernd/HyperTile/"""
+
+from __future__ import annotations
+
+import math
+
+from einops import rearrange
+from torch import randint
+
+from comfy_api.latest import io
+
+
+def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int:
+    min_value = min(min_value, value)
+
+    # All big divisors of value (inclusive)
+    divisors = [i for i in range(min_value, value + 1) if value % i == 0]
+
+    ns = [value // i for i in divisors[:max_options]]  # has at least 1 element
+
+    if len(ns) - 1 > 0:
+        idx = randint(low=0, high=len(ns) - 1, size=(1,)).item()
+    else:
+        idx = 0
+
+    return ns[idx]
+
+
+class HyperTile(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="HyperTile_V3",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Int.Input("tile_size", default=256, min=1, max=2048),
+                io.Int.Input("swap_size", default=2, min=1, max=128),
+                io.Int.Input("max_depth", default=0, min=0, max=10),
+                io.Boolean.Input("scale_depth", default=False),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, tile_size, swap_size, max_depth, scale_depth):
+        latent_tile_size = max(32, tile_size) // 8
+        temp = None
+
+        def hypertile_in(q, k, v, extra_options):
+            nonlocal temp
+            model_chans = q.shape[-2]
+            orig_shape = extra_options['original_shape']
+            apply_to = []
+            for i in range(max_depth + 1):
+                apply_to.append((orig_shape[-2] / (2 ** i)) * (orig_shape[-1] / (2 ** i)))
+
+            if model_chans in apply_to:
+                shape = extra_options["original_shape"]
+                aspect_ratio = shape[-1] / shape[-2]
+
+                hw = q.size(1)
+                h, w = round(math.sqrt(hw * aspect_ratio)), round(math.sqrt(hw / aspect_ratio))
+
+                factor = (2 ** apply_to.index(model_chans)) if scale_depth else 1
+                nh = random_divisor(h, latent_tile_size * factor, swap_size)
+                nw = random_divisor(w, latent_tile_size * factor, swap_size)
+
+                if nh * nw > 1:
+                    q = rearrange(q, "b (nh h nw w) c -> (b nh nw) (h w) c", h=h // nh, w=w // nw, nh=nh, nw=nw)
+                    temp = (nh, nw, h, w)
+                return q, k, v
+
+            return q, k, v
+
+        def hypertile_out(out, extra_options):
+            nonlocal temp
+            if temp is not None:
+                nh, nw, h, w = temp
+                temp = None
+                out = rearrange(out, "(b nh nw) hw c -> b nh nw hw c", nh=nh, nw=nw)
+                out = rearrange(out, "b nh nw (h w) c -> b (nh h nw w) c", h=h // nh, w=w // nw)
+            return out
+
+        m = model.clone()
+        m.set_model_attn1_patch(hypertile_in)
+        m.set_model_attn1_output_patch(hypertile_out)
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    HyperTile,
+]

comfy_extras/v3/nodes_images.py

@@ -0,0 +1,727 @@
+import hashlib
+import os
+
+import numpy as np
+import torch
+from PIL import Image, ImageOps, ImageSequence
+
+import comfy.utils
+import folder_paths
+import node_helpers
+import nodes
+from comfy_api.latest import io, ui
+from server import PromptServer
+
+
+class GetImageSize(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="GetImageSize_V3",
+            display_name="Get Image Size _V3",
+            description="Returns width and height of the image, and passes it through unchanged.",
+            category="image",
+            inputs=[
+                io.Image.Input("image"),
+            ],
+            outputs=[
+                io.Int.Output(display_name="width"),
+                io.Int.Output(display_name="height"),
+                io.Int.Output(display_name="batch_size"),
+            ],
+            hidden=[io.Hidden.unique_id],
+        )
+
+    @classmethod
+    def execute(cls, image) -> io.NodeOutput:
+        height = image.shape[1]
+        width = image.shape[2]
+        batch_size = image.shape[0]
+
+        if cls.hidden.unique_id:
+            PromptServer.instance.send_progress_text(
+                f"width: {width}, height: {height}\n batch size: {batch_size}", cls.hidden.unique_id
+            )
+
+        return io.NodeOutput(width, height, batch_size)
+
+
+class ImageAddNoise(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageAddNoise_V3",
+            display_name="Image Add Noise _V3",
+            category="image",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=0xFFFFFFFFFFFFFFFF,
+                    control_after_generate=True,
+                    tooltip="The random seed used for creating the noise.",
+                ),
+                io.Float.Input("strength", default=0.5, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, seed, strength) -> io.NodeOutput:
+        generator = torch.manual_seed(seed)
+        s = torch.clip(
+            (image + strength * torch.randn(image.size(), generator=generator, device="cpu").to(image)),
+            min=0.0,
+            max=1.0,
+        )
+        return io.NodeOutput(s)
+
+
+class ImageCrop(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageCrop_V3",
+            display_name="Image Crop _V3",
+            category="image/transform",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("width", default=512, min=1, max=nodes.MAX_RESOLUTION, step=1),
+                io.Int.Input("height", default=512, min=1, max=nodes.MAX_RESOLUTION, step=1),
+                io.Int.Input("x", default=0, min=0, max=nodes.MAX_RESOLUTION, step=1),
+                io.Int.Input("y", default=0, min=0, max=nodes.MAX_RESOLUTION, step=1),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, width, height, x, y) -> io.NodeOutput:
+        x = min(x, image.shape[2] - 1)
+        y = min(y, image.shape[1] - 1)
+        to_x = width + x
+        to_y = height + y
+        return io.NodeOutput(image[:, y:to_y, x:to_x, :])
+
+
+class ImageFlip(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageFlip_V3",
+            display_name="Image Flip _V3",
+            category="image/transform",
+            inputs=[
+                io.Image.Input("image"),
+                io.Combo.Input("flip_method", options=["x-axis: vertically", "y-axis: horizontally"]),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, flip_method) -> io.NodeOutput:
+        if flip_method.startswith("x"):
+            image = torch.flip(image, dims=[1])
+        elif flip_method.startswith("y"):
+            image = torch.flip(image, dims=[2])
+
+        return io.NodeOutput(image)
+
+
+class ImageFromBatch(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageFromBatch_V3",
+            display_name="Image From Batch _V3",
+            category="image/batch",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("batch_index", default=0, min=0, max=4095),
+                io.Int.Input("length", default=1, min=1, max=4096),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, batch_index, length) -> io.NodeOutput:
+        s_in = image
+        batch_index = min(s_in.shape[0] - 1, batch_index)
+        length = min(s_in.shape[0] - batch_index, length)
+        s = s_in[batch_index : batch_index + length].clone()
+        return io.NodeOutput(s)
+
+
+class ImageRotate(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageRotate_V3",
+            display_name="Image Rotate _V3",
+            category="image/transform",
+            inputs=[
+                io.Image.Input("image"),
+                io.Combo.Input("rotation", options=["none", "90 degrees", "180 degrees", "270 degrees"]),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, rotation) -> io.NodeOutput:
+        rotate_by = 0
+        if rotation.startswith("90"):
+            rotate_by = 1
+        elif rotation.startswith("180"):
+            rotate_by = 2
+        elif rotation.startswith("270"):
+            rotate_by = 3
+
+        return io.NodeOutput(torch.rot90(image, k=rotate_by, dims=[2, 1]))
+
+
+class ImageStitch(io.ComfyNode):
+    """Upstreamed from https://github.com/kijai/ComfyUI-KJNodes"""
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageStitch_V3",
+            display_name="Image Stitch _V3",
+            description="Stitches image2 to image1 in the specified direction. "
+            "If image2 is not provided, returns image1 unchanged. "
+            "Optional spacing can be added between images.",
+            category="image/transform",
+            inputs=[
+                io.Image.Input("image1"),
+                io.Combo.Input("direction", options=["right", "down", "left", "up"], default="right"),
+                io.Boolean.Input("match_image_size", default=True),
+                io.Int.Input("spacing_width", default=0, min=0, max=1024, step=2),
+                io.Combo.Input("spacing_color", options=["white", "black", "red", "green", "blue"], default="white"),
+                io.Image.Input("image2", optional=True),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image1, direction, match_image_size, spacing_width, spacing_color, image2=None) -> io.NodeOutput:
+        if image2 is None:
+            return io.NodeOutput(image1)
+
+        # Handle batch size differences
+        if image1.shape[0] != image2.shape[0]:
+            max_batch = max(image1.shape[0], image2.shape[0])
+            if image1.shape[0] < max_batch:
+                image1 = torch.cat([image1, image1[-1:].repeat(max_batch - image1.shape[0], 1, 1, 1)])
+            if image2.shape[0] < max_batch:
+                image2 = torch.cat([image2, image2[-1:].repeat(max_batch - image2.shape[0], 1, 1, 1)])
+
+        # Match image sizes if requested
+        if match_image_size:
+            h1, w1 = image1.shape[1:3]
+            h2, w2 = image2.shape[1:3]
+            aspect_ratio = w2 / h2
+
+            if direction in ["left", "right"]:
+                target_h, target_w = h1, int(h1 * aspect_ratio)
+            else:  # up, down
+                target_w, target_h = w1, int(w1 / aspect_ratio)
+
+            image2 = comfy.utils.common_upscale(
+                image2.movedim(-1, 1), target_w, target_h, "lanczos", "disabled"
+            ).movedim(1, -1)
+
+        color_map = {
+            "white": 1.0,
+            "black": 0.0,
+            "red": (1.0, 0.0, 0.0),
+            "green": (0.0, 1.0, 0.0),
+            "blue": (0.0, 0.0, 1.0),
+        }
+
+        color_val = color_map[spacing_color]
+
+        # When not matching sizes, pad to align non-concat dimensions
+        if not match_image_size:
+            h1, w1 = image1.shape[1:3]
+            h2, w2 = image2.shape[1:3]
+            pad_value = 0.0
+            if not isinstance(color_val, tuple):
+                pad_value = color_val
+
+            if direction in ["left", "right"]:
+                # For horizontal concat, pad heights to match
+                if h1 != h2:
+                    target_h = max(h1, h2)
+                    if h1 < target_h:
+                        pad_h = target_h - h1
+                        pad_top, pad_bottom = pad_h // 2, pad_h - pad_h // 2
+                        image1 = torch.nn.functional.pad(
+                            image1, (0, 0, 0, 0, pad_top, pad_bottom), mode="constant", value=pad_value
+                        )
+                    if h2 < target_h:
+                        pad_h = target_h - h2
+                        pad_top, pad_bottom = pad_h // 2, pad_h - pad_h // 2
+                        image2 = torch.nn.functional.pad(
+                            image2, (0, 0, 0, 0, pad_top, pad_bottom), mode="constant", value=pad_value
+                        )
+            else:  # up, down
+                # For vertical concat, pad widths to match
+                if w1 != w2:
+                    target_w = max(w1, w2)
+                    if w1 < target_w:
+                        pad_w = target_w - w1
+                        pad_left, pad_right = pad_w // 2, pad_w - pad_w // 2
+                        image1 = torch.nn.functional.pad(
+                            image1, (0, 0, pad_left, pad_right), mode="constant", value=pad_value
+                        )
+                    if w2 < target_w:
+                        pad_w = target_w - w2
+                        pad_left, pad_right = pad_w // 2, pad_w - pad_w // 2
+                        image2 = torch.nn.functional.pad(
+                            image2, (0, 0, pad_left, pad_right), mode="constant", value=pad_value
+                        )
+
+        # Ensure same number of channels
+        if image1.shape[-1] != image2.shape[-1]:
+            max_channels = max(image1.shape[-1], image2.shape[-1])
+            if image1.shape[-1] < max_channels:
+                image1 = torch.cat(
+                    [
+                        image1,
+                        torch.ones(
+                            *image1.shape[:-1],
+                            max_channels - image1.shape[-1],
+                            device=image1.device,
+                        ),
+                    ],
+                    dim=-1,
+                )
+            if image2.shape[-1] < max_channels:
+                image2 = torch.cat(
+                    [
+                        image2,
+                        torch.ones(
+                            *image2.shape[:-1],
+                            max_channels - image2.shape[-1],
+                            device=image2.device,
+                        ),
+                    ],
+                    dim=-1,
+                )
+
+        # Add spacing if specified
+        if spacing_width > 0:
+            spacing_width = spacing_width + (spacing_width % 2)  # Ensure even
+
+            if direction in ["left", "right"]:
+                spacing_shape = (
+                    image1.shape[0],
+                    max(image1.shape[1], image2.shape[1]),
+                    spacing_width,
+                    image1.shape[-1],
+                )
+            else:
+                spacing_shape = (
+                    image1.shape[0],
+                    spacing_width,
+                    max(image1.shape[2], image2.shape[2]),
+                    image1.shape[-1],
+                )
+
+            spacing = torch.full(spacing_shape, 0.0, device=image1.device)
+            if isinstance(color_val, tuple):
+                for i, c in enumerate(color_val):
+                    if i < spacing.shape[-1]:
+                        spacing[..., i] = c
+                if spacing.shape[-1] == 4:  # Add alpha
+                    spacing[..., 3] = 1.0
+            else:
+                spacing[..., : min(3, spacing.shape[-1])] = color_val
+                if spacing.shape[-1] == 4:
+                    spacing[..., 3] = 1.0
+
+        # Concatenate images
+        images = [image2, image1] if direction in ["left", "up"] else [image1, image2]
+        if spacing_width > 0:
+            images.insert(1, spacing)
+
+        concat_dim = 2 if direction in ["left", "right"] else 1
+        return io.NodeOutput(torch.cat(images, dim=concat_dim))
+
+
+class LoadImage(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LoadImage_V3",
+            display_name="Load Image _V3",
+            category="image",
+            inputs=[
+                io.Combo.Input(
+                    "image",
+                    upload=io.UploadType.image,
+                    image_folder=io.FolderType.input,
+                    options=cls.get_files_options(),
+                ),
+            ],
+            outputs=[
+                io.Image.Output(),
+                io.Mask.Output(),
+            ],
+        )
+
+    @classmethod
+    def get_files_options(cls) -> list[str]:
+        target_dir = folder_paths.get_input_directory()
+        files = [f for f in os.listdir(target_dir) if os.path.isfile(os.path.join(target_dir, f))]
+        return sorted(folder_paths.filter_files_content_types(files, ["image"]))
+
+    @classmethod
+    def execute(cls, image) -> io.NodeOutput:
+        img = node_helpers.pillow(Image.open, folder_paths.get_annotated_filepath(image))
+
+        output_images = []
+        output_masks = []
+        w, h = None, None
+
+        excluded_formats = ["MPO"]
+
+        for i in ImageSequence.Iterator(img):
+            i = node_helpers.pillow(ImageOps.exif_transpose, i)
+
+            if i.mode == "I":
+                i = i.point(lambda i: i * (1 / 255))
+            image = i.convert("RGB")
+
+            if len(output_images) == 0:
+                w = image.size[0]
+                h = image.size[1]
+
+            if image.size[0] != w or image.size[1] != h:
+                continue
+
+            image = np.array(image).astype(np.float32) / 255.0
+            image = torch.from_numpy(image)[None,]
+            if "A" in i.getbands():
+                mask = np.array(i.getchannel("A")).astype(np.float32) / 255.0
+                mask = 1.0 - torch.from_numpy(mask)
+            elif i.mode == "P" and "transparency" in i.info:
+                mask = np.array(i.convert("RGBA").getchannel("A")).astype(np.float32) / 255.0
+                mask = 1.0 - torch.from_numpy(mask)
+            else:
+                mask = torch.zeros((64, 64), dtype=torch.float32, device="cpu")
+            output_images.append(image)
+            output_masks.append(mask.unsqueeze(0))
+
+        if len(output_images) > 1 and img.format not in excluded_formats:
+            output_image = torch.cat(output_images, dim=0)
+            output_mask = torch.cat(output_masks, dim=0)
+        else:
+            output_image = output_images[0]
+            output_mask = output_masks[0]
+
+        return io.NodeOutput(output_image, output_mask)
+
+    @classmethod
+    def fingerprint_inputs(s, image):
+        image_path = folder_paths.get_annotated_filepath(image)
+        m = hashlib.sha256()
+        with open(image_path, "rb") as f:
+            m.update(f.read())
+        return m.digest().hex()
+
+    @classmethod
+    def validate_inputs(s, image):
+        if not folder_paths.exists_annotated_filepath(image):
+            return "Invalid image file: {}".format(image)
+        return True
+
+
+class LoadImageOutput(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LoadImageOutput_V3",
+            display_name="Load Image (from Outputs) _V3",
+            description="Load an image from the output folder. "
+            "When the refresh button is clicked, the node will update the image list "
+            "and automatically select the first image, allowing for easy iteration.",
+            category="image",
+            inputs=[
+                io.Combo.Input(
+                    "image",
+                    upload=io.UploadType.image,
+                    image_folder=io.FolderType.output,
+                    remote=io.RemoteOptions(
+                        route="/internal/files/output",
+                        refresh_button=True,
+                        control_after_refresh="first",
+                    ),
+                ),
+            ],
+            outputs=[
+                io.Image.Output(),
+                io.Mask.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image) -> io.NodeOutput:
+        img = node_helpers.pillow(Image.open, folder_paths.get_annotated_filepath(image))
+
+        output_images = []
+        output_masks = []
+        w, h = None, None
+
+        excluded_formats = ["MPO"]
+
+        for i in ImageSequence.Iterator(img):
+            i = node_helpers.pillow(ImageOps.exif_transpose, i)
+
+            if i.mode == "I":
+                i = i.point(lambda i: i * (1 / 255))
+            image = i.convert("RGB")
+
+            if len(output_images) == 0:
+                w = image.size[0]
+                h = image.size[1]
+
+            if image.size[0] != w or image.size[1] != h:
+                continue
+
+            image = np.array(image).astype(np.float32) / 255.0
+            image = torch.from_numpy(image)[None,]
+            if "A" in i.getbands():
+                mask = np.array(i.getchannel("A")).astype(np.float32) / 255.0
+                mask = 1.0 - torch.from_numpy(mask)
+            elif i.mode == "P" and "transparency" in i.info:
+                mask = np.array(i.convert("RGBA").getchannel("A")).astype(np.float32) / 255.0
+                mask = 1.0 - torch.from_numpy(mask)
+            else:
+                mask = torch.zeros((64, 64), dtype=torch.float32, device="cpu")
+            output_images.append(image)
+            output_masks.append(mask.unsqueeze(0))
+
+        if len(output_images) > 1 and img.format not in excluded_formats:
+            output_image = torch.cat(output_images, dim=0)
+            output_mask = torch.cat(output_masks, dim=0)
+        else:
+            output_image = output_images[0]
+            output_mask = output_masks[0]
+
+        return io.NodeOutput(output_image, output_mask)
+
+    @classmethod
+    def fingerprint_inputs(s, image):
+        image_path = folder_paths.get_annotated_filepath(image)
+        m = hashlib.sha256()
+        with open(image_path, "rb") as f:
+            m.update(f.read())
+        return m.digest().hex()
+
+    @classmethod
+    def validate_inputs(s, image):
+        if not folder_paths.exists_annotated_filepath(image):
+            return "Invalid image file: {}".format(image)
+        return True
+
+
+class PreviewImage(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PreviewImage_V3",
+            display_name="Preview Image _V3",
+            description="Preview the input images.",
+            category="image",
+            inputs=[
+                io.Image.Input("images", tooltip="The images to preview."),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, images) -> io.NodeOutput:
+        return io.NodeOutput(ui=ui.PreviewImage(images, cls=cls))
+
+
+class RepeatImageBatch(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RepeatImageBatch_V3",
+            display_name="Repeat Image Batch _V3",
+            category="image/batch",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("amount", default=1, min=1, max=4096),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, amount) -> io.NodeOutput:
+        return io.NodeOutput(image.repeat((amount, 1, 1, 1)))
+
+
+class ResizeAndPadImage(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ResizeAndPadImage_V3",
+            display_name="Resize and Pad Image _V3",
+            category="image/transform",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("target_width", default=512, min=1, max=nodes.MAX_RESOLUTION, step=1),
+                io.Int.Input("target_height", default=512, min=1, max=nodes.MAX_RESOLUTION, step=1),
+                io.Combo.Input("padding_color", options=["white", "black"]),
+                io.Combo.Input("interpolation", options=["area", "bicubic", "nearest-exact", "bilinear", "lanczos"]),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, target_width, target_height, padding_color, interpolation) -> io.NodeOutput:
+        batch_size, orig_height, orig_width, channels = image.shape
+
+        scale_w = target_width / orig_width
+        scale_h = target_height / orig_height
+        scale = min(scale_w, scale_h)
+
+        new_width = int(orig_width * scale)
+        new_height = int(orig_height * scale)
+
+        image_permuted = image.permute(0, 3, 1, 2)
+
+        resized = comfy.utils.common_upscale(image_permuted, new_width, new_height, interpolation, "disabled")
+
+        pad_value = 0.0 if padding_color == "black" else 1.0
+        padded = torch.full(
+            (batch_size, channels, target_height, target_width), pad_value, dtype=image.dtype, device=image.device
+        )
+
+        y_offset = (target_height - new_height) // 2
+        x_offset = (target_width - new_width) // 2
+
+        padded[:, :, y_offset : y_offset + new_height, x_offset : x_offset + new_width] = resized
+
+        return io.NodeOutput(padded.permute(0, 2, 3, 1))
+
+
+class SaveAnimatedPNG(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SaveAnimatedPNG_V3",
+            display_name="Save Animated PNG _V3",
+            category="image/animation",
+            inputs=[
+                io.Image.Input("images"),
+                io.String.Input("filename_prefix", default="ComfyUI"),
+                io.Float.Input("fps", default=6.0, min=0.01, max=1000.0, step=0.01),
+                io.Int.Input("compress_level", default=4, min=0, max=9),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, images, fps, compress_level, filename_prefix="ComfyUI") -> io.NodeOutput:
+        return io.NodeOutput(
+            ui=ui.ImageSaveHelper.get_save_animated_png_ui(
+                images=images,
+                filename_prefix=filename_prefix,
+                cls=cls,
+                fps=fps,
+                compress_level=compress_level,
+            )
+        )
+
+
+class SaveAnimatedWEBP(io.ComfyNode):
+    COMPRESS_METHODS = {"default": 4, "fastest": 0, "slowest": 6}
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SaveAnimatedWEBP_V3",
+            display_name="Save Animated WEBP _V3",
+            category="image/animation",
+            inputs=[
+                io.Image.Input("images"),
+                io.String.Input("filename_prefix", default="ComfyUI"),
+                io.Float.Input("fps", default=6.0, min=0.01, max=1000.0, step=0.01),
+                io.Boolean.Input("lossless", default=True),
+                io.Int.Input("quality", default=80, min=0, max=100),
+                io.Combo.Input("method", options=list(cls.COMPRESS_METHODS.keys())),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, images, fps, filename_prefix, lossless, quality, method) -> io.NodeOutput:
+        return io.NodeOutput(
+            ui=ui.ImageSaveHelper.get_save_animated_webp_ui(
+                images=images,
+                filename_prefix=filename_prefix,
+                cls=cls,
+                fps=fps,
+                lossless=lossless,
+                quality=quality,
+                method=cls.COMPRESS_METHODS.get(method)
+            )
+        )
+
+
+class SaveImage(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SaveImage_V3",
+            display_name="Save Image _V3",
+            description="Saves the input images to your ComfyUI output directory.",
+            category="image",
+            inputs=[
+                io.Image.Input(
+                    "images",
+                    tooltip="The images to save.",
+                ),
+                io.String.Input(
+                    "filename_prefix",
+                    default="ComfyUI",
+                    tooltip="The prefix for the file to save. This may include formatting information "
+                    "such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes.",
+                ),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, images, filename_prefix="ComfyUI") -> io.NodeOutput:
+        return io.NodeOutput(
+            ui=ui.ImageSaveHelper.get_save_images_ui(images, filename_prefix=filename_prefix, cls=cls, compress_level=4)
+        )
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    GetImageSize,
+    ImageAddNoise,
+    ImageCrop,
+    ImageFlip,
+    ImageFromBatch,
+    ImageRotate,
+    ImageStitch,
+    LoadImage,
+    LoadImageOutput,
+    PreviewImage,
+    RepeatImageBatch,
+    ResizeAndPadImage,
+    SaveAnimatedPNG,
+    SaveAnimatedWEBP,
+    SaveImage,
+]

comfy_extras/v3/nodes_ip2p.py

@@ -0,0 +1,56 @@
+from __future__ import annotations
+
+import torch
+
+from comfy_api.latest import io
+
+
+class InstructPixToPixConditioning(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="InstructPixToPixConditioning_V3",
+            category="conditioning/instructpix2pix",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Vae.Input("vae"),
+                io.Image.Input("pixels"),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, positive, negative, pixels, vae):
+        x = (pixels.shape[1] // 8) * 8
+        y = (pixels.shape[2] // 8) * 8
+
+        if pixels.shape[1] != x or pixels.shape[2] != y:
+            x_offset = (pixels.shape[1] % 8) // 2
+            y_offset = (pixels.shape[2] % 8) // 2
+            pixels = pixels[:,x_offset:x + x_offset, y_offset:y + y_offset,:]
+
+        concat_latent = vae.encode(pixels)
+
+        out_latent = {}
+        out_latent["samples"] = torch.zeros_like(concat_latent)
+
+        out = []
+        for conditioning in [positive, negative]:
+            c = []
+            for t in conditioning:
+                d = t[1].copy()
+                d["concat_latent_image"] = concat_latent
+                n = [t[0], d]
+                c.append(n)
+            out.append(c)
+        return io.NodeOutput(out[0], out[1], out_latent)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    InstructPixToPixConditioning,
+]

comfy_extras/v3/nodes_latent.py

@@ -0,0 +1,340 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.utils
+import comfy_extras.nodes_post_processing
+from comfy_api.latest import io
+
+
+def reshape_latent_to(target_shape, latent, repeat_batch=True):
+    if latent.shape[1:] != target_shape[1:]:
+        latent = comfy.utils.common_upscale(
+            latent, target_shape[-1], target_shape[-2], "bilinear", "center"
+        )
+    if repeat_batch:
+        return comfy.utils.repeat_to_batch_size(latent, target_shape[0])
+    return latent
+
+
+class LatentAdd(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentAdd_V3",
+            category="latent/advanced",
+            inputs=[
+                io.Latent.Input("samples1"),
+                io.Latent.Input("samples2"),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, samples1, samples2):
+        samples_out = samples1.copy()
+
+        s1 = samples1["samples"]
+        s2 = samples2["samples"]
+
+        s2 = reshape_latent_to(s1.shape, s2)
+        samples_out["samples"] = s1 + s2
+        return io.NodeOutput(samples_out)
+
+
+class LatentSubtract(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentSubtract_V3",
+            category="latent/advanced",
+            inputs=[
+                io.Latent.Input("samples1"),
+                io.Latent.Input("samples2"),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, samples1, samples2):
+        samples_out = samples1.copy()
+
+        s1 = samples1["samples"]
+        s2 = samples2["samples"]
+
+        s2 = reshape_latent_to(s1.shape, s2)
+        samples_out["samples"] = s1 - s2
+        return io.NodeOutput(samples_out)
+
+
+class LatentMultiply(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentMultiply_V3",
+            category="latent/advanced",
+            inputs=[
+                io.Latent.Input("samples"),
+                io.Float.Input("multiplier", default=1.0, min=-10.0, max=10.0, step=0.01),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, samples, multiplier):
+        samples_out = samples.copy()
+
+        s1 = samples["samples"]
+        samples_out["samples"] = s1 * multiplier
+        return io.NodeOutput(samples_out)
+
+
+class LatentInterpolate(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentInterpolate_V3",
+            category="latent/advanced",
+            inputs=[
+                io.Latent.Input("samples1"),
+                io.Latent.Input("samples2"),
+                io.Float.Input("ratio", default=1.0, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, samples1, samples2, ratio):
+        samples_out = samples1.copy()
+
+        s1 = samples1["samples"]
+        s2 = samples2["samples"]
+
+        s2 = reshape_latent_to(s1.shape, s2)
+
+        m1 = torch.linalg.vector_norm(s1, dim=(1))
+        m2 = torch.linalg.vector_norm(s2, dim=(1))
+
+        s1 = torch.nan_to_num(s1 / m1)
+        s2 = torch.nan_to_num(s2 / m2)
+
+        t = (s1 * ratio + s2 * (1.0 - ratio))
+        mt = torch.linalg.vector_norm(t, dim=(1))
+        st = torch.nan_to_num(t / mt)
+
+        samples_out["samples"] = st * (m1 * ratio + m2 * (1.0 - ratio))
+        return io.NodeOutput(samples_out)
+
+
+class LatentBatch(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentBatch_V3",
+            category="latent/batch",
+            inputs=[
+                io.Latent.Input("samples1"),
+                io.Latent.Input("samples2"),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, samples1, samples2):
+        samples_out = samples1.copy()
+        s1 = samples1["samples"]
+        s2 = samples2["samples"]
+
+        s2 = reshape_latent_to(s1.shape, s2, repeat_batch=False)
+        s = torch.cat((s1, s2), dim=0)
+        samples_out["samples"] = s
+        samples_out["batch_index"] = (samples1.get("batch_index", [x for x in range(0, s1.shape[0])]) +
+                                      samples2.get("batch_index", [x for x in range(0, s2.shape[0])]))
+        return io.NodeOutput(samples_out)
+
+
+class LatentBatchSeedBehavior(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentBatchSeedBehavior_V3",
+            category="latent/advanced",
+            inputs=[
+                io.Latent.Input("samples"),
+                io.Combo.Input("seed_behavior", options=["random", "fixed"], default="fixed"),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, samples, seed_behavior):
+        samples_out = samples.copy()
+        latent = samples["samples"]
+        if seed_behavior == "random":
+            if 'batch_index' in samples_out:
+                samples_out.pop('batch_index')
+        elif seed_behavior == "fixed":
+            batch_number = samples_out.get("batch_index", [0])[0]
+            samples_out["batch_index"] = [batch_number] * latent.shape[0]
+
+        return io.NodeOutput(samples_out)
+
+
+class LatentApplyOperation(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentApplyOperation_V3",
+            category="latent/advanced/operations",
+            is_experimental=True,
+            inputs=[
+                io.Latent.Input("samples"),
+                io.LatentOperation.Input("operation"),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, samples, operation):
+        samples_out = samples.copy()
+
+        s1 = samples["samples"]
+        samples_out["samples"] = operation(latent=s1)
+        return io.NodeOutput(samples_out)
+
+
+class LatentApplyOperationCFG(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentApplyOperationCFG_V3",
+            category="latent/advanced/operations",
+            is_experimental=True,
+            inputs=[
+                io.Model.Input("model"),
+                io.LatentOperation.Input("operation"),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, operation):
+        m = model.clone()
+
+        def pre_cfg_function(args):
+            conds_out = args["conds_out"]
+            if len(conds_out) == 2:
+                conds_out[0] = operation(latent=(conds_out[0] - conds_out[1])) + conds_out[1]
+            else:
+                conds_out[0] = operation(latent=conds_out[0])
+            return conds_out
+
+        m.set_model_sampler_pre_cfg_function(pre_cfg_function)
+        return io.NodeOutput(m)
+
+
+class LatentOperationTonemapReinhard(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentOperationTonemapReinhard_V3",
+            category="latent/advanced/operations",
+            is_experimental=True,
+            inputs=[
+                io.Float.Input("multiplier", default=1.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.LatentOperation.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, multiplier):
+        def tonemap_reinhard(latent, **kwargs):
+            latent_vector_magnitude = (torch.linalg.vector_norm(latent, dim=(1)) + 0.0000000001)[:,None]
+            normalized_latent = latent / latent_vector_magnitude
+
+            mean = torch.mean(latent_vector_magnitude, dim=(1,2,3), keepdim=True)
+            std = torch.std(latent_vector_magnitude, dim=(1,2,3), keepdim=True)
+
+            top = (std * 5 + mean) * multiplier
+
+            #reinhard
+            latent_vector_magnitude *= (1.0 / top)
+            new_magnitude = latent_vector_magnitude / (latent_vector_magnitude + 1.0)
+            new_magnitude *= top
+
+            return normalized_latent * new_magnitude
+        return io.NodeOutput(tonemap_reinhard)
+
+
+class LatentOperationSharpen(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentOperationSharpen_V3",
+            category="latent/advanced/operations",
+            is_experimental=True,
+            inputs=[
+                io.Int.Input("sharpen_radius", default=9, min=1, max=31, step=1),
+                io.Float.Input("sigma", default=1.0, min=0.1, max=10.0, step=0.1),
+                io.Float.Input("alpha", default=0.1, min=0.0, max=5.0, step=0.01),
+            ],
+            outputs=[
+                io.LatentOperation.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, sharpen_radius, sigma, alpha):
+        def sharpen(latent, **kwargs):
+            luminance = (torch.linalg.vector_norm(latent, dim=(1)) + 1e-6)[:,None]
+            normalized_latent = latent / luminance
+            channels = latent.shape[1]
+
+            kernel_size = sharpen_radius * 2 + 1
+            kernel = comfy_extras.nodes_post_processing.gaussian_kernel(kernel_size, sigma, device=luminance.device)
+            center = kernel_size // 2
+
+            kernel *= alpha * -10
+            kernel[center, center] = kernel[center, center] - kernel.sum() + 1.0
+
+            padded_image = torch.nn.functional.pad(
+                normalized_latent, (sharpen_radius,sharpen_radius,sharpen_radius,sharpen_radius), "reflect"
+            )
+            sharpened = torch.nn.functional.conv2d(
+                padded_image, kernel.repeat(channels, 1, 1).unsqueeze(1), padding=kernel_size // 2, groups=channels
+            )[:,:,sharpen_radius:-sharpen_radius, sharpen_radius:-sharpen_radius]
+
+            return luminance * sharpened
+        return io.NodeOutput(sharpen)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    LatentAdd,
+    LatentApplyOperation,
+    LatentApplyOperationCFG,
+    LatentBatch,
+    LatentBatchSeedBehavior,
+    LatentInterpolate,
+    LatentMultiply,
+    LatentOperationSharpen,
+    LatentOperationTonemapReinhard,
+    LatentSubtract,
+]

comfy_extras/v3/nodes_load_3d.py

@@ -0,0 +1,180 @@
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+import folder_paths
+import nodes
+from comfy_api.input_impl import VideoFromFile
+from comfy_api.latest import io, ui
+
+
+def normalize_path(path):
+    return path.replace("\\", "/")
+
+
+class Load3D(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        input_dir = os.path.join(folder_paths.get_input_directory(), "3d")
+
+        os.makedirs(input_dir, exist_ok=True)
+
+        input_path = Path(input_dir)
+        base_path = Path(folder_paths.get_input_directory())
+
+        files = [
+            normalize_path(str(file_path.relative_to(base_path)))
+            for file_path in input_path.rglob("*")
+            if file_path.suffix.lower() in {".gltf", ".glb", ".obj", ".fbx", ".stl"}
+        ]
+
+        return io.Schema(
+            node_id="Load3D_V3",
+            display_name="Load 3D _V3",
+            category="3d",
+            is_experimental=True,
+            inputs=[
+                io.Combo.Input("model_file", options=sorted(files), upload=io.UploadType.model),
+                io.Load3D.Input("image"),
+                io.Int.Input("width", default=1024, min=1, max=4096, step=1),
+                io.Int.Input("height", default=1024, min=1, max=4096, step=1),
+            ],
+            outputs=[
+                io.Image.Output(display_name="image"),
+                io.Mask.Output(display_name="mask"),
+                io.String.Output(display_name="mesh_path"),
+                io.Image.Output(display_name="normal"),
+                io.Image.Output(display_name="lineart"),
+                io.Load3DCamera.Output(display_name="camera_info"),
+                io.Video.Output(display_name="recording_video"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model_file, image, **kwargs):
+        image_path = folder_paths.get_annotated_filepath(image["image"])
+        mask_path = folder_paths.get_annotated_filepath(image["mask"])
+        normal_path = folder_paths.get_annotated_filepath(image["normal"])
+        lineart_path = folder_paths.get_annotated_filepath(image["lineart"])
+
+        load_image_node = nodes.LoadImage()
+        output_image, ignore_mask = load_image_node.load_image(image=image_path)
+        ignore_image, output_mask = load_image_node.load_image(image=mask_path)
+        normal_image, ignore_mask2 = load_image_node.load_image(image=normal_path)
+        lineart_image, ignore_mask3 = load_image_node.load_image(image=lineart_path)
+
+        video = None
+        if image["recording"] != "":
+            recording_video_path = folder_paths.get_annotated_filepath(image["recording"])
+            video = VideoFromFile(recording_video_path)
+
+        return io.NodeOutput(
+            output_image, output_mask, model_file, normal_image, lineart_image, image["camera_info"], video
+        )
+
+
+class Load3DAnimation(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        input_dir = os.path.join(folder_paths.get_input_directory(), "3d")
+
+        os.makedirs(input_dir, exist_ok=True)
+
+        input_path = Path(input_dir)
+        base_path = Path(folder_paths.get_input_directory())
+
+        files = [
+            normalize_path(str(file_path.relative_to(base_path)))
+            for file_path in input_path.rglob("*")
+            if file_path.suffix.lower() in {".gltf", ".glb", ".fbx"}
+        ]
+
+        return io.Schema(
+            node_id="Load3DAnimation_V3",
+            display_name="Load 3D - Animation _V3",
+            category="3d",
+            is_experimental=True,
+            inputs=[
+                io.Combo.Input("model_file", options=sorted(files), upload=io.UploadType.model),
+                io.Load3DAnimation.Input("image"),
+                io.Int.Input("width", default=1024, min=1, max=4096, step=1),
+                io.Int.Input("height", default=1024, min=1, max=4096, step=1),
+            ],
+            outputs=[
+                io.Image.Output(display_name="image"),
+                io.Mask.Output(display_name="mask"),
+                io.String.Output(display_name="mesh_path"),
+                io.Image.Output(display_name="normal"),
+                io.Load3DCamera.Output(display_name="camera_info"),
+                io.Video.Output(display_name="recording_video"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model_file, image, **kwargs):
+        image_path = folder_paths.get_annotated_filepath(image["image"])
+        mask_path = folder_paths.get_annotated_filepath(image["mask"])
+        normal_path = folder_paths.get_annotated_filepath(image["normal"])
+
+        load_image_node = nodes.LoadImage()
+        output_image, ignore_mask = load_image_node.load_image(image=image_path)
+        ignore_image, output_mask = load_image_node.load_image(image=mask_path)
+        normal_image, ignore_mask2 = load_image_node.load_image(image=normal_path)
+
+        video = None
+        if image['recording'] != "":
+            recording_video_path = folder_paths.get_annotated_filepath(image["recording"])
+            video = VideoFromFile(recording_video_path)
+
+        return io.NodeOutput(output_image, output_mask, model_file, normal_image, image["camera_info"], video)
+
+
+class Preview3D(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Preview3D_V3",  # frontend expects "Preview3D" to work
+            display_name="Preview 3D _V3",
+            category="3d",
+            is_experimental=True,
+            is_output_node=True,
+            inputs=[
+                io.String.Input("model_file", default="", multiline=False),
+                io.Load3DCamera.Input("camera_info", optional=True),
+            ],
+            outputs=[],
+        )
+
+    @classmethod
+    def execute(cls, model_file, camera_info=None):
+        return io.NodeOutput(ui=ui.PreviewUI3D(model_file, camera_info, cls=cls))
+
+
+class Preview3DAnimation(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Preview3DAnimation_V3",  # frontend expects "Preview3DAnimation" to work
+            display_name="Preview 3D - Animation _V3",
+            category="3d",
+            is_experimental=True,
+            is_output_node=True,
+            inputs=[
+                io.String.Input("model_file", default="", multiline=False),
+                io.Load3DCamera.Input("camera_info", optional=True),
+            ],
+            outputs=[],
+        )
+
+    @classmethod
+    def execute(cls, model_file, camera_info=None):
+        return io.NodeOutput(ui=ui.PreviewUI3D(model_file, camera_info, cls=cls))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    Load3D,
+    Load3DAnimation,
+    Preview3D,
+    Preview3DAnimation,
+]

comfy_extras/v3/nodes_lora_extract.py

@@ -0,0 +1,138 @@
+from __future__ import annotations
+
+import logging
+import os
+from enum import Enum
+
+import torch
+
+import comfy.model_management
+import comfy.utils
+import folder_paths
+from comfy_api.latest import io
+
+CLAMP_QUANTILE = 0.99
+
+
+def extract_lora(diff, rank):
+    conv2d = (len(diff.shape) == 4)
+    kernel_size = None if not conv2d else diff.size()[2:4]
+    conv2d_3x3 = conv2d and kernel_size != (1, 1)
+    out_dim, in_dim = diff.size()[0:2]
+    rank = min(rank, in_dim, out_dim)
+
+    if conv2d:
+        if conv2d_3x3:
+            diff = diff.flatten(start_dim=1)
+        else:
+            diff = diff.squeeze()
+
+    U, S, Vh = torch.linalg.svd(diff.float())
+    U = U[:, :rank]
+    S = S[:rank]
+    U = U @ torch.diag(S)
+    Vh = Vh[:rank, :]
+
+    dist = torch.cat([U.flatten(), Vh.flatten()])
+    hi_val = torch.quantile(dist, CLAMP_QUANTILE)
+    low_val = -hi_val
+
+    U = U.clamp(low_val, hi_val)
+    Vh = Vh.clamp(low_val, hi_val)
+    if conv2d:
+        U = U.reshape(out_dim, rank, 1, 1)
+        Vh = Vh.reshape(rank, in_dim, kernel_size[0], kernel_size[1])
+    return (U, Vh)
+
+
+class LORAType(Enum):
+    STANDARD = 0
+    FULL_DIFF = 1
+
+
+LORA_TYPES = {
+    "standard": LORAType.STANDARD,
+    "full_diff": LORAType.FULL_DIFF,
+}
+
+
+def calc_lora_model(model_diff, rank, prefix_model, prefix_lora, output_sd, lora_type, bias_diff=False):
+    comfy.model_management.load_models_gpu([model_diff], force_patch_weights=True)
+    sd = model_diff.model_state_dict(filter_prefix=prefix_model)
+
+    for k in sd:
+        if k.endswith(".weight"):
+            weight_diff = sd[k]
+            if lora_type == LORAType.STANDARD:
+                if weight_diff.ndim < 2:
+                    if bias_diff:
+                        output_sd["{}{}.diff".format(prefix_lora, k[len(prefix_model):-7])] = weight_diff.contiguous().half().cpu()
+                    continue
+                try:
+                    out = extract_lora(weight_diff, rank)
+                    output_sd["{}{}.lora_up.weight".format(prefix_lora, k[len(prefix_model):-7])] = out[0].contiguous().half().cpu()
+                    output_sd["{}{}.lora_down.weight".format(prefix_lora, k[len(prefix_model):-7])] = out[1].contiguous().half().cpu()
+                except Exception:
+                    logging.warning("Could not generate lora weights for key {}, is the weight difference a zero?".format(k))
+            elif lora_type == LORAType.FULL_DIFF:
+                output_sd["{}{}.diff".format(prefix_lora, k[len(prefix_model):-7])] = weight_diff.contiguous().half().cpu()
+
+        elif bias_diff and k.endswith(".bias"):
+            output_sd["{}{}.diff_b".format(prefix_lora, k[len(prefix_model):-5])] = sd[k].contiguous().half().cpu()
+    return output_sd
+
+
+class LoraSave(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LoraSave_V3",
+            display_name="Extract and Save Lora _V3",
+            category="_for_testing",
+            is_output_node=True,
+            inputs=[
+                io.String.Input("filename_prefix", default="loras/ComfyUI_extracted_lora"),
+                io.Int.Input("rank", default=8, min=1, max=4096, step=1),
+                io.Combo.Input("lora_type", options=list(LORA_TYPES.keys())),
+                io.Boolean.Input("bias_diff", default=True),
+                io.Model.Input(
+                    id="model_diff", optional=True, tooltip="The ModelSubtract output to be converted to a lora."
+                ),
+                io.Clip.Input(
+                    id="text_encoder_diff", optional=True, tooltip="The CLIPSubtract output to be converted to a lora."
+                ),
+            ],
+            outputs=[],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, filename_prefix, rank, lora_type, bias_diff, model_diff=None, text_encoder_diff=None):
+        if model_diff is None and text_encoder_diff is None:
+            return io.NodeOutput()
+
+        lora_type = LORA_TYPES.get(lora_type)
+        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(
+            filename_prefix, folder_paths.get_output_directory()
+        )
+
+        output_sd = {}
+        if model_diff is not None:
+            output_sd = calc_lora_model(
+                model_diff, rank, "diffusion_model.", "diffusion_model.", output_sd, lora_type, bias_diff=bias_diff
+            )
+        if text_encoder_diff is not None:
+            output_sd = calc_lora_model(
+                text_encoder_diff.patcher, rank, "", "text_encoders.", output_sd, lora_type, bias_diff=bias_diff
+            )
+
+        output_checkpoint = f"{filename}_{counter:05}_.safetensors"
+        output_checkpoint = os.path.join(full_output_folder, output_checkpoint)
+
+        comfy.utils.save_torch_file(output_sd, output_checkpoint, metadata=None)
+        return io.NodeOutput()
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    LoraSave,
+]

comfy_extras/v3/nodes_lt.py

@@ -0,0 +1,528 @@
+from __future__ import annotations
+
+import math
+import sys
+
+import av
+import numpy as np
+import torch
+
+import comfy.model_management
+import comfy.model_sampling
+import comfy.utils
+import node_helpers
+import nodes
+from comfy.ldm.lightricks.symmetric_patchifier import (
+    SymmetricPatchifier,
+    latent_to_pixel_coords,
+)
+from comfy_api.latest import io
+
+
+def conditioning_get_any_value(conditioning, key, default=None):
+    for t in conditioning:
+        if key in t[1]:
+            return t[1][key]
+    return default
+
+
+def get_noise_mask(latent):
+    noise_mask = latent.get("noise_mask", None)
+    latent_image = latent["samples"]
+    if noise_mask is None:
+        batch_size, _, latent_length, _, _ = latent_image.shape
+        return torch.ones(
+            (batch_size, 1, latent_length, 1, 1),
+            dtype=torch.float32,
+            device=latent_image.device,
+        )
+    return noise_mask.clone()
+
+
+def get_keyframe_idxs(cond):
+    keyframe_idxs = conditioning_get_any_value(cond, "keyframe_idxs", None)
+    if keyframe_idxs is None:
+        return None, 0
+    return keyframe_idxs, torch.unique(keyframe_idxs[:, 0]).shape[0]
+
+
+def encode_single_frame(output_file, image_array: np.ndarray, crf):
+    container = av.open(output_file, "w", format="mp4")
+    try:
+        stream = container.add_stream(
+            "libx264", rate=1, options={"crf": str(crf), "preset": "veryfast"}
+        )
+        stream.height = image_array.shape[0]
+        stream.width = image_array.shape[1]
+        av_frame = av.VideoFrame.from_ndarray(image_array, format="rgb24").reformat(
+            format="yuv420p"
+        )
+        container.mux(stream.encode(av_frame))
+        container.mux(stream.encode())
+    finally:
+        container.close()
+
+
+def decode_single_frame(video_file):
+    container = av.open(video_file)
+    try:
+        stream = next(s for s in container.streams if s.type == "video")
+        frame = next(container.decode(stream))
+    finally:
+        container.close()
+    return frame.to_ndarray(format="rgb24")
+
+
+def preprocess(image: torch.Tensor, crf=29):
+    if crf == 0:
+        return image
+
+    image_array = (image[:(image.shape[0] // 2) * 2, :(image.shape[1] // 2) * 2] * 255.0).byte().cpu().numpy()
+    with sys.modules['io'].BytesIO() as output_file:
+        encode_single_frame(output_file, image_array, crf)
+        video_bytes = output_file.getvalue()
+    with sys.modules['io'].BytesIO(video_bytes) as video_file:
+        image_array = decode_single_frame(video_file)
+    return torch.tensor(image_array, dtype=image.dtype, device=image.device) / 255.0
+
+
+class EmptyLTXVLatentVideo(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="EmptyLTXVLatentVideo_V3",
+            category="latent/video/ltxv",
+            inputs=[
+                io.Int.Input("width", default=768, min=64, max=nodes.MAX_RESOLUTION, step=32),
+                io.Int.Input("height", default=512, min=64, max=nodes.MAX_RESOLUTION, step=32),
+                io.Int.Input("length", default=97, min=1, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, width, height, length, batch_size):
+        latent = torch.zeros(
+            [batch_size, 128, ((length - 1) // 8) + 1, height // 32, width // 32],
+            device=comfy.model_management.intermediate_device(),
+        )
+        return io.NodeOutput({"samples": latent})
+
+
+class LTXVAddGuide(io.ComfyNode):
+    NUM_PREFIX_FRAMES = 2
+    PATCHIFIER = SymmetricPatchifier(1)
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVAddGuide_V3",
+            category="conditioning/video_models",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Vae.Input("vae"),
+                io.Latent.Input("latent"),
+                io.Image.Input(
+                    "image",
+                    tooltip="Image or video to condition the latent video on. Must be 8*n + 1 frames. "
+                            "If the video is not 8*n + 1 frames, it will be cropped to the nearest 8*n + 1 frames.",
+                ),
+                io.Int.Input(
+                    "frame_idx",
+                    default=0,
+                    min=-9999,
+                    max=9999,
+                    tooltip="Frame index to start the conditioning at. "
+                            "For single-frame images or videos with 1-8 frames, any frame_idx value is acceptable. "
+                            "For videos with 9+ frames, frame_idx must be divisible by 8, otherwise it will be rounded "
+                            "down to the nearest multiple of 8. Negative values are counted from the end of the video.",
+                ),
+                io.Float.Input("strength", default=1.0, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, positive, negative, vae, latent, image, frame_idx, strength):
+        scale_factors = vae.downscale_index_formula
+        latent_image = latent["samples"]
+        noise_mask = get_noise_mask(latent)
+
+        _, _, latent_length, latent_height, latent_width = latent_image.shape
+        image, t = cls._encode(vae, latent_width, latent_height, image, scale_factors)
+
+        frame_idx, latent_idx = cls._get_latent_index(positive, latent_length, len(image), frame_idx, scale_factors)
+        assert latent_idx + t.shape[2] <= latent_length, "Conditioning frames exceed the length of the latent sequence."
+
+        num_prefix_frames = min(cls.NUM_PREFIX_FRAMES, t.shape[2])
+
+        positive, negative, latent_image, noise_mask = cls._append_keyframe(
+            positive,
+            negative,
+            frame_idx,
+            latent_image,
+            noise_mask,
+            t[:, :, :num_prefix_frames],
+            strength,
+            scale_factors,
+        )
+
+        latent_idx += num_prefix_frames
+
+        t = t[:, :, num_prefix_frames:]
+        if t.shape[2] == 0:
+            return io.NodeOutput(positive, negative, {"samples": latent_image, "noise_mask": noise_mask})
+
+        latent_image, noise_mask = cls._replace_latent_frames(
+            latent_image,
+            noise_mask,
+            t,
+            latent_idx,
+            strength,
+        )
+
+        return io.NodeOutput(positive, negative, {"samples": latent_image, "noise_mask": noise_mask})
+
+    @classmethod
+    def _encode(cls, vae, latent_width, latent_height, images, scale_factors):
+        time_scale_factor, width_scale_factor, height_scale_factor = scale_factors
+        images = images[:(images.shape[0] - 1) // time_scale_factor * time_scale_factor + 1]
+        pixels = comfy.utils.common_upscale(
+            images.movedim(-1, 1),
+            latent_width * width_scale_factor,
+            latent_height * height_scale_factor,
+            "bilinear",
+            crop="disabled",
+        ).movedim(1, -1)
+        encode_pixels = pixels[:, :, :, :3]
+        t = vae.encode(encode_pixels)
+        return encode_pixels, t
+
+    @classmethod
+    def _get_latent_index(cls, cond, latent_length, guide_length, frame_idx, scale_factors):
+        time_scale_factor, _, _ = scale_factors
+        _, num_keyframes = get_keyframe_idxs(cond)
+        latent_count = latent_length - num_keyframes
+        frame_idx = frame_idx if frame_idx >= 0 else max((latent_count - 1) * time_scale_factor + 1 + frame_idx, 0)
+        if guide_length > 1 and frame_idx != 0:
+            frame_idx = (frame_idx - 1) // time_scale_factor * time_scale_factor + 1
+        return frame_idx, (frame_idx + time_scale_factor - 1) // time_scale_factor
+
+    @classmethod
+    def _add_keyframe_index(cls, cond, frame_idx, guiding_latent, scale_factors):
+        keyframe_idxs, _ = get_keyframe_idxs(cond)
+        _, latent_coords = cls.PATCHIFIER.patchify(guiding_latent)
+        pixel_coords = latent_to_pixel_coords(latent_coords, scale_factors, causal_fix=frame_idx == 0)
+        pixel_coords[:, 0] += frame_idx
+        if keyframe_idxs is None:
+            keyframe_idxs = pixel_coords
+        else:
+            keyframe_idxs = torch.cat([keyframe_idxs, pixel_coords], dim=2)
+        return node_helpers.conditioning_set_values(cond, {"keyframe_idxs": keyframe_idxs})
+
+    @classmethod
+    def _append_keyframe(
+        cls, positive, negative, frame_idx, latent_image, noise_mask, guiding_latent, strength, scale_factors
+    ):
+        _, latent_idx = cls._get_latent_index(
+            cond=positive,
+            latent_length=latent_image.shape[2],
+            guide_length=guiding_latent.shape[2],
+            frame_idx=frame_idx,
+            scale_factors=scale_factors,
+        )
+        noise_mask[:, :, latent_idx:latent_idx + guiding_latent.shape[2]] = 1.0
+
+        positive = cls._add_keyframe_index(positive, frame_idx, guiding_latent, scale_factors)
+        negative = cls._add_keyframe_index(negative, frame_idx, guiding_latent, scale_factors)
+
+        mask = torch.full(
+            (noise_mask.shape[0], 1, guiding_latent.shape[2], 1, 1),
+            1.0 - strength,
+            dtype=noise_mask.dtype,
+            device=noise_mask.device,
+        )
+
+        latent_image = torch.cat([latent_image, guiding_latent], dim=2)
+        return positive, negative, latent_image, torch.cat([noise_mask, mask], dim=2)
+
+    @classmethod
+    def _replace_latent_frames(cls, latent_image, noise_mask, guiding_latent, latent_idx, strength):
+        cond_length = guiding_latent.shape[2]
+        assert latent_image.shape[2] >= latent_idx + cond_length, "Conditioning frames exceed the length of the latent sequence."
+
+        mask = torch.full(
+            (noise_mask.shape[0], 1, cond_length, 1, 1),
+            1.0 - strength,
+            dtype=noise_mask.dtype,
+            device=noise_mask.device,
+        )
+
+        latent_image = latent_image.clone()
+        noise_mask = noise_mask.clone()
+
+        latent_image[:, :, latent_idx : latent_idx + cond_length] = guiding_latent
+        noise_mask[:, :, latent_idx : latent_idx + cond_length] = mask
+
+        return latent_image, noise_mask
+
+
+class LTXVConditioning(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVConditioning_V3",
+            category="conditioning/video_models",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Float.Input("frame_rate", default=25.0, min=0.0, max=1000.0, step=0.01),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, positive, negative, frame_rate):
+        positive = node_helpers.conditioning_set_values(positive, {"frame_rate": frame_rate})
+        negative = node_helpers.conditioning_set_values(negative, {"frame_rate": frame_rate})
+        return io.NodeOutput(positive, negative)
+
+
+class LTXVCropGuides(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVCropGuides_V3",
+            category="conditioning/video_models",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Latent.Input("latent"),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, positive, negative, latent):
+        latent_image = latent["samples"].clone()
+        noise_mask = get_noise_mask(latent)
+
+        _, num_keyframes = get_keyframe_idxs(positive)
+        if num_keyframes == 0:
+            return io.NodeOutput(positive, negative, {"samples": latent_image, "noise_mask": noise_mask})
+
+        latent_image = latent_image[:, :, :-num_keyframes]
+        noise_mask = noise_mask[:, :, :-num_keyframes]
+
+        positive = node_helpers.conditioning_set_values(positive, {"keyframe_idxs": None})
+        negative = node_helpers.conditioning_set_values(negative, {"keyframe_idxs": None})
+
+        return io.NodeOutput(positive, negative, {"samples": latent_image, "noise_mask": noise_mask})
+
+
+class LTXVImgToVideo(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVImgToVideo_V3",
+            category="conditioning/video_models",
+            inputs=[
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Vae.Input("vae"),
+                io.Image.Input("image"),
+                io.Int.Input("width", default=768, min=64, max=nodes.MAX_RESOLUTION, step=32),
+                io.Int.Input("height", default=512, min=64, max=nodes.MAX_RESOLUTION, step=32),
+                io.Int.Input("length", default=97, min=9, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+                io.Float.Input("strength", default=1.0, min=0.0, max=1.0),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, positive, negative, image, vae, width, height, length, batch_size, strength):
+        pixels = comfy.utils.common_upscale(
+            image.movedim(-1, 1), width, height, "bilinear", "center"
+        ).movedim(1, -1)
+        encode_pixels = pixels[:, :, :, :3]
+        t = vae.encode(encode_pixels)
+
+        latent = torch.zeros(
+            [batch_size, 128, ((length - 1) // 8) + 1, height // 32, width // 32],
+            device=comfy.model_management.intermediate_device(),
+        )
+        latent[:, :, :t.shape[2]] = t
+
+        conditioning_latent_frames_mask = torch.ones(
+            (batch_size, 1, latent.shape[2], 1, 1),
+            dtype=torch.float32,
+            device=latent.device,
+        )
+        conditioning_latent_frames_mask[:, :, :t.shape[2]] = 1.0 - strength
+
+        return io.NodeOutput(positive, negative, {"samples": latent, "noise_mask": conditioning_latent_frames_mask})
+
+
+class LTXVPreprocess(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVPreprocess_V3",
+            category="image",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input(
+                    id="img_compression", default=35, min=0, max=100, tooltip="Amount of compression to apply on image."
+                ),
+            ],
+            outputs=[
+                io.Image.Output(display_name="output_image"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image, img_compression):
+        output_images = []
+        for i in range(image.shape[0]):
+            output_images.append(preprocess(image[i], img_compression))
+        return io.NodeOutput(torch.stack(output_images))
+
+
+class LTXVScheduler(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LTXVScheduler_V3",
+            category="sampling/custom_sampling/schedulers",
+            inputs=[
+                io.Int.Input("steps", default=20, min=1, max=10000),
+                io.Float.Input("max_shift", default=2.05, min=0.0, max=100.0, step=0.01),
+                io.Float.Input("base_shift", default=0.95, min=0.0, max=100.0, step=0.01),
+                io.Boolean.Input(
+                    id="stretch",
+                    default=True,
+                    tooltip="Stretch the sigmas to be in the range [terminal, 1].",
+                ),
+                io.Float.Input(
+                    id="terminal",
+                    default=0.1,
+                    min=0.0,
+                    max=0.99,
+                    step=0.01,
+                    tooltip="The terminal value of the sigmas after stretching.",
+                ),
+                io.Latent.Input("latent", optional=True),
+            ],
+            outputs=[
+                io.Sigmas.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, steps, max_shift, base_shift, stretch, terminal, latent=None):
+        if latent is None:
+            tokens = 4096
+        else:
+            tokens = math.prod(latent["samples"].shape[2:])
+
+        sigmas = torch.linspace(1.0, 0.0, steps + 1)
+
+        x1 = 1024
+        x2 = 4096
+        mm = (max_shift - base_shift) / (x2 - x1)
+        b = base_shift - mm * x1
+        sigma_shift = (tokens) * mm + b
+
+        power = 1
+        sigmas = torch.where(
+            sigmas != 0,
+            math.exp(sigma_shift) / (math.exp(sigma_shift) + (1 / sigmas - 1) ** power),
+            0,
+        )
+
+        if stretch:
+            non_zero_mask = sigmas != 0
+            non_zero_sigmas = sigmas[non_zero_mask]
+            one_minus_z = 1.0 - non_zero_sigmas
+            scale_factor = one_minus_z[-1] / (1.0 - terminal)
+            stretched = 1.0 - (one_minus_z / scale_factor)
+            sigmas[non_zero_mask] = stretched
+
+        return io.NodeOutput(sigmas)
+
+
+class ModelSamplingLTXV(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSamplingLTXV_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("max_shift", default=2.05, min=0.0, max=100.0, step=0.01),
+                io.Float.Input("base_shift", default=0.95, min=0.0, max=100.0, step=0.01),
+                io.Latent.Input("latent", optional=True),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, max_shift, base_shift, latent=None):
+        m = model.clone()
+
+        if latent is None:
+            tokens = 4096
+        else:
+            tokens = math.prod(latent["samples"].shape[2:])
+
+        x1 = 1024
+        x2 = 4096
+        mm = (max_shift - base_shift) / (x2 - x1)
+        b = base_shift - mm * x1
+        shift = (tokens) * mm + b
+
+        sampling_base = comfy.model_sampling.ModelSamplingFlux
+        sampling_type = comfy.model_sampling.CONST
+
+        class ModelSamplingAdvanced(sampling_base, sampling_type):
+            pass
+
+        model_sampling = ModelSamplingAdvanced(model.model.model_config)
+        model_sampling.set_parameters(shift=shift)
+        m.add_object_patch("model_sampling", model_sampling)
+
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    EmptyLTXVLatentVideo,
+    LTXVAddGuide,
+    LTXVConditioning,
+    LTXVCropGuides,
+    LTXVImgToVideo,
+    LTXVPreprocess,
+    LTXVScheduler,
+    ModelSamplingLTXV,
+]

comfy_extras/v3/nodes_lumina2.py

@@ -0,0 +1,116 @@
+from __future__ import annotations
+
+import torch
+
+from comfy_api.latest import io
+
+
+class RenormCFG(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RenormCFG_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("cfg_trunc", default=100, min=0.0, max=100.0, step=0.01),
+                io.Float.Input("renorm_cfg", default=1.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, cfg_trunc, renorm_cfg):
+        def renorm_cfg_func(args):
+            cond_denoised = args["cond_denoised"]
+            uncond_denoised = args["uncond_denoised"]
+            cond_scale = args["cond_scale"]
+            timestep = args["timestep"]
+            x_orig = args["input"]
+            in_channels = model.model.diffusion_model.in_channels
+
+            if timestep[0] < cfg_trunc:
+                cond_eps, uncond_eps = cond_denoised[:, :in_channels], uncond_denoised[:, :in_channels]
+                cond_rest, _ = cond_denoised[:, in_channels:], uncond_denoised[:, in_channels:]
+                half_eps = uncond_eps + cond_scale * (cond_eps - uncond_eps)
+                half_rest = cond_rest
+
+                if float(renorm_cfg) > 0.0:
+                    ori_pos_norm = torch.linalg.vector_norm(
+                        cond_eps,
+                        dim=tuple(range(1, len(cond_eps.shape))),
+                        keepdim=True
+                    )
+                    max_new_norm = ori_pos_norm * float(renorm_cfg)
+                    new_pos_norm = torch.linalg.vector_norm(
+                        half_eps, dim=tuple(range(1, len(half_eps.shape))), keepdim=True
+                    )
+                    if new_pos_norm >= max_new_norm:
+                        half_eps = half_eps * (max_new_norm / new_pos_norm)
+            else:
+                cond_eps, uncond_eps = cond_denoised[:, :in_channels], uncond_denoised[:, :in_channels]
+                cond_rest, _ = cond_denoised[:, in_channels:], uncond_denoised[:, in_channels:]
+                half_eps = cond_eps
+                half_rest = cond_rest
+
+            cfg_result = torch.cat([half_eps, half_rest], dim=1)
+
+            # cfg_result = uncond_denoised + (cond_denoised - uncond_denoised) * cond_scale
+
+            return x_orig - cfg_result
+
+        m = model.clone()
+        m.set_model_sampler_cfg_function(renorm_cfg_func)
+        return io.NodeOutput(m)
+
+
+class CLIPTextEncodeLumina2(io.ComfyNode):
+    SYSTEM_PROMPT = {
+        "superior": "You are an assistant designed to generate superior images with the superior "
+            "degree of image-text alignment based on textual prompts or user prompts.",
+        "alignment": "You are an assistant designed to generate high-quality images with the "
+            "highest degree of image-text alignment based on textual prompts."
+    }
+    SYSTEM_PROMPT_TIP = "Lumina2 provide two types of system prompts:" \
+        "Superior: You are an assistant designed to generate superior images with the superior " \
+        "degree of image-text alignment based on textual prompts or user prompts. " \
+        "Alignment: You are an assistant designed to generate high-quality images with the highest " \
+        "degree of image-text alignment based on textual prompts."
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeLumina2_V3",
+            display_name="CLIP Text Encode for Lumina2 _V3",
+            category="conditioning",
+            description="Encodes a system prompt and a user prompt using a CLIP model into an embedding "
+                        "that can be used to guide the diffusion model towards generating specific images.",
+            inputs=[
+                io.Combo.Input("system_prompt", options=list(cls.SYSTEM_PROMPT.keys()), tooltip=cls.SYSTEM_PROMPT_TIP),
+                io.String.Input("user_prompt", multiline=True, dynamic_prompts=True, tooltip="The text to be encoded."),
+                io.Clip.Input("clip", tooltip="The CLIP model used for encoding the text."),
+            ],
+            outputs=[
+                io.Conditioning.Output(tooltip="A conditioning containing the embedded text used to guide the diffusion model."),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, system_prompt, user_prompt, clip):
+        if clip is None:
+            raise RuntimeError(
+                "ERROR: clip input is invalid: None\n\n"
+                "If the clip is from a checkpoint loader node your checkpoint does not contain a valid clip or text encoder model."
+            )
+        system_prompt = cls.SYSTEM_PROMPT[system_prompt]
+        prompt = f'{system_prompt} <Prompt Start> {user_prompt}'
+        tokens = clip.tokenize(prompt)
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CLIPTextEncodeLumina2,
+    RenormCFG,
+]

comfy_extras/v3/nodes_mahiro.py

@@ -0,0 +1,51 @@
+from __future__ import annotations
+
+import torch
+import torch.nn.functional as F
+
+from comfy_api.latest import io
+
+
+class Mahiro(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Mahiro_V3",
+            display_name="Mahiro is so cute that she deserves a better guidance function!! (。・ω・。) _V3",
+            category="_for_testing",
+            description="Modify the guidance to scale more on the 'direction' of the positive prompt rather than the difference between the negative prompt.",
+            is_experimental=True,
+            inputs=[
+                io.Model.Input("model")
+            ],
+            outputs=[
+                io.Model.Output(display_name="patched_model")
+            ]
+        )
+
+    @classmethod
+    def execute(cls, model):
+        m = model.clone()
+        def mahiro_normd(args):
+            scale: float = args['cond_scale']
+            cond_p: torch.Tensor = args['cond_denoised']
+            uncond_p: torch.Tensor = args['uncond_denoised']
+            #naive leap
+            leap = cond_p * scale
+            #sim with uncond leap
+            u_leap = uncond_p * scale
+            cfg = args["denoised"]
+            merge = (leap + cfg) / 2
+            normu = torch.sqrt(u_leap.abs()) * u_leap.sign()
+            normm = torch.sqrt(merge.abs()) * merge.sign()
+            sim = F.cosine_similarity(normu, normm).mean()
+            simsc = 2 * (sim+1)
+            wm = (simsc*cfg + (4-simsc)*leap) / 4
+            return wm
+        m.set_model_sampler_post_cfg_function(mahiro_normd)
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    Mahiro,
+]

comfy_extras/v3/nodes_mask.py

@@ -0,0 +1,437 @@
+from __future__ import annotations
+
+import numpy as np
+import scipy.ndimage
+import torch
+
+import comfy.utils
+import node_helpers
+import nodes
+from comfy_api.latest import io, ui
+
+
+def composite(destination, source, x, y, mask=None, multiplier=8, resize_source=False):
+    source = source.to(destination.device)
+    if resize_source:
+        source = torch.nn.functional.interpolate(
+            source, size=(destination.shape[2], destination.shape[3]), mode="bilinear"
+        )
+
+    source = comfy.utils.repeat_to_batch_size(source, destination.shape[0])
+
+    x = max(-source.shape[3] * multiplier, min(x, destination.shape[3] * multiplier))
+    y = max(-source.shape[2] * multiplier, min(y, destination.shape[2] * multiplier))
+
+    left, top = (x // multiplier, y // multiplier)
+    right, bottom = (
+        left + source.shape[3],
+        top + source.shape[2],
+    )
+
+    if mask is None:
+        mask = torch.ones_like(source)
+    else:
+        mask = mask.to(destination.device, copy=True)
+        mask = torch.nn.functional.interpolate(
+            mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])),
+            size=(source.shape[2], source.shape[3]),
+            mode="bilinear",
+        )
+        mask = comfy.utils.repeat_to_batch_size(mask, source.shape[0])
+
+    # calculate the bounds of the source that will be overlapping the destination
+    # this prevents the source trying to overwrite latent pixels that are out of bounds
+    # of the destination
+    visible_width, visible_height = (
+        destination.shape[3] - left + min(0, x),
+        destination.shape[2] - top + min(0, y),
+    )
+
+    mask = mask[:, :, :visible_height, :visible_width]
+    inverse_mask = torch.ones_like(mask) - mask
+
+    source_portion = mask * source[:, :, :visible_height, :visible_width]
+    destination_portion = inverse_mask * destination[:, :, top:bottom, left:right]
+
+    destination[:, :, top:bottom, left:right] = source_portion + destination_portion
+    return destination
+
+
+class LatentCompositeMasked(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LatentCompositeMasked_V3",
+            display_name="Latent Composite Masked _V3",
+            category="latent",
+            inputs=[
+                io.Latent.Input("destination"),
+                io.Latent.Input("source"),
+                io.Int.Input("x", default=0, min=0, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("y", default=0, min=0, max=nodes.MAX_RESOLUTION, step=8),
+                io.Boolean.Input("resize_source", default=False),
+                io.Mask.Input("mask", optional=True),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, destination, source, x, y, resize_source, mask=None) -> io.NodeOutput:
+        output = destination.copy()
+        destination_samples = destination["samples"].clone()
+        source_samples = source["samples"]
+        output["samples"] = composite(destination_samples, source_samples, x, y, mask, 8, resize_source)
+        return io.NodeOutput(output)
+
+
+class ImageCompositeMasked(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageCompositeMasked_V3",
+            display_name="Image Composite Masked _V3",
+            category="image",
+            inputs=[
+                io.Image.Input("destination"),
+                io.Image.Input("source"),
+                io.Int.Input("x", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("y", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Boolean.Input("resize_source", default=False),
+                io.Mask.Input("mask", optional=True),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, destination, source, x, y, resize_source, mask=None) -> io.NodeOutput:
+        destination, source = node_helpers.image_alpha_fix(destination, source)
+        destination = destination.clone().movedim(-1, 1)
+        output = composite(destination, source.movedim(-1, 1), x, y, mask, 1, resize_source).movedim(1, -1)
+        return io.NodeOutput(output)
+
+
+class MaskToImage(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="MaskToImage_V3",
+            display_name="Convert Mask to Image _V3",
+            category="mask",
+            inputs=[
+                io.Mask.Input("mask"),
+            ],
+            outputs=[io.Image.Output()],
+        )
+
+    @classmethod
+    def execute(cls, mask) -> io.NodeOutput:
+        return io.NodeOutput(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])).movedim(1, -1).expand(-1, -1, -1, 3))
+
+
+class ImageToMask(io.ComfyNode):
+    CHANNELS = ["red", "green", "blue", "alpha"]
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageToMask_V3",
+            display_name="Convert Image to Mask _V3",
+            category="mask",
+            inputs=[
+                io.Image.Input("image"),
+                io.Combo.Input("channel", options=cls.CHANNELS),
+            ],
+            outputs=[io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, channel) -> io.NodeOutput:
+        return io.NodeOutput(image[:, :, :, cls.CHANNELS.index(channel)])
+
+
+class ImageColorToMask(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageColorToMask_V3",
+            display_name="Image Color to Mask _V3",
+            category="mask",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("color", default=0, min=0, max=0xFFFFFF),
+            ],
+            outputs=[io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, image, color) -> io.NodeOutput:
+        temp = (torch.clamp(image, 0, 1.0) * 255.0).round().to(torch.int)
+        temp = (
+            torch.bitwise_left_shift(temp[:, :, :, 0], 16)
+            + torch.bitwise_left_shift(temp[:, :, :, 1], 8)
+            + temp[:, :, :, 2]
+        )
+        return io.NodeOutput(torch.where(temp == color, 1.0, 0).float())
+
+
+class SolidMask(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SolidMask_V3",
+            display_name="Solid Mask _V3",
+            category="mask",
+            inputs=[
+                io.Float.Input("value", default=1.0, min=0.0, max=1.0, step=0.01),
+                io.Int.Input("width", default=512, min=1, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("height", default=512, min=1, max=nodes.MAX_RESOLUTION),
+            ],
+            outputs=[io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value, width, height) -> io.NodeOutput:
+        return io.NodeOutput(torch.full((1, height, width), value, dtype=torch.float32, device="cpu"))
+
+
+class InvertMask(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="InvertMask_V3",
+            display_name="Invert Mask _V3",
+            category="mask",
+            inputs=[
+                io.Mask.Input("mask"),
+            ],
+            outputs=[io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, mask) -> io.NodeOutput:
+        return io.NodeOutput(1.0 - mask)
+
+
+class CropMask(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CropMask_V3",
+            display_name="Crop Mask _V3",
+            category="mask",
+            inputs=[
+                io.Mask.Input("mask"),
+                io.Int.Input("x", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("y", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("width", default=512, min=1, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("height", default=512, min=1, max=nodes.MAX_RESOLUTION),
+            ],
+            outputs=[io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, mask, x, y, width, height) -> io.NodeOutput:
+        mask = mask.reshape((-1, mask.shape[-2], mask.shape[-1]))
+        return io.NodeOutput(mask[:, y : y + height, x : x + width])
+
+
+class MaskComposite(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="MaskComposite_V3",
+            display_name="Mask Composite _V3",
+            category="mask",
+            inputs=[
+                io.Mask.Input("destination"),
+                io.Mask.Input("source"),
+                io.Int.Input("x", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("y", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Combo.Input("operation", options=["multiply", "add", "subtract", "and", "or", "xor"]),
+            ],
+            outputs=[io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, destination, source, x, y, operation) -> io.NodeOutput:
+        output = destination.reshape((-1, destination.shape[-2], destination.shape[-1])).clone()
+        source = source.reshape((-1, source.shape[-2], source.shape[-1]))
+
+        left, top = (
+            x,
+            y,
+        )
+        right, bottom = (
+            min(left + source.shape[-1], destination.shape[-1]),
+            min(top + source.shape[-2], destination.shape[-2]),
+        )
+        visible_width, visible_height = (
+            right - left,
+            bottom - top,
+        )
+
+        source_portion = source[:, :visible_height, :visible_width]
+        destination_portion = output[:, top:bottom, left:right]
+
+        if operation == "multiply":
+            output[:, top:bottom, left:right] = destination_portion * source_portion
+        elif operation == "add":
+            output[:, top:bottom, left:right] = destination_portion + source_portion
+        elif operation == "subtract":
+            output[:, top:bottom, left:right] = destination_portion - source_portion
+        elif operation == "and":
+            output[:, top:bottom, left:right] = torch.bitwise_and(
+                destination_portion.round().bool(), source_portion.round().bool()
+            ).float()
+        elif operation == "or":
+            output[:, top:bottom, left:right] = torch.bitwise_or(
+                destination_portion.round().bool(), source_portion.round().bool()
+            ).float()
+        elif operation == "xor":
+            output[:, top:bottom, left:right] = torch.bitwise_xor(
+                destination_portion.round().bool(), source_portion.round().bool()
+            ).float()
+
+        return io.NodeOutput(torch.clamp(output, 0.0, 1.0))
+
+
+class FeatherMask(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="FeatherMask_V3",
+            display_name="Feather Mask _V3",
+            category="mask",
+            inputs=[
+                io.Mask.Input("mask"),
+                io.Int.Input("left", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("top", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("right", default=0, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("bottom", default=0, min=0, max=nodes.MAX_RESOLUTION),
+            ],
+            outputs=[io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, mask, left, top, right, bottom) -> io.NodeOutput:
+        output = mask.reshape((-1, mask.shape[-2], mask.shape[-1])).clone()
+
+        left = min(left, output.shape[-1])
+        right = min(right, output.shape[-1])
+        top = min(top, output.shape[-2])
+        bottom = min(bottom, output.shape[-2])
+
+        for x in range(left):
+            feather_rate = (x + 1.0) / left
+            output[:, :, x] *= feather_rate
+
+        for x in range(right):
+            feather_rate = (x + 1) / right
+            output[:, :, -x] *= feather_rate
+
+        for y in range(top):
+            feather_rate = (y + 1) / top
+            output[:, y, :] *= feather_rate
+
+        for y in range(bottom):
+            feather_rate = (y + 1) / bottom
+            output[:, -y, :] *= feather_rate
+
+        return io.NodeOutput(output)
+
+
+class GrowMask(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="GrowMask_V3",
+            display_name="Grow Mask _V3",
+            category="mask",
+            inputs=[
+                io.Mask.Input("mask"),
+                io.Int.Input("expand", default=0, min=-nodes.MAX_RESOLUTION, max=nodes.MAX_RESOLUTION),
+                io.Boolean.Input("tapered_corners", default=True),
+            ],
+            outputs=[io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, mask, expand, tapered_corners) -> io.NodeOutput:
+        c = 0 if tapered_corners else 1
+        kernel = np.array([[c, 1, c], [1, 1, 1], [c, 1, c]])
+        mask = mask.reshape((-1, mask.shape[-2], mask.shape[-1]))
+        out = []
+        for m in mask:
+            output = m.numpy()
+            for _ in range(abs(expand)):
+                if expand < 0:
+                    output = scipy.ndimage.grey_erosion(output, footprint=kernel)
+                else:
+                    output = scipy.ndimage.grey_dilation(output, footprint=kernel)
+            output = torch.from_numpy(output)
+            out.append(output)
+        return io.NodeOutput(torch.stack(out, dim=0))
+
+
+class ThresholdMask(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ThresholdMask_V3",
+            display_name="Threshold Mask _V3",
+            category="mask",
+            inputs=[
+                io.Mask.Input("mask"),
+                io.Float.Input("value", default=0.5, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[io.Mask.Output()],
+        )
+
+    @classmethod
+    def execute(cls, mask, value) -> io.NodeOutput:
+        return io.NodeOutput((mask > value).float())
+
+
+# Mask Preview - original implement from
+# https://github.com/cubiq/ComfyUI_essentials/blob/9d9f4bedfc9f0321c19faf71855e228c93bd0dc9/mask.py#L81
+# upstream requested in https://github.com/Kosinkadink/rfcs/blob/main/rfcs/0000-corenodes.md#preview-nodes
+class MaskPreview(io.ComfyNode):
+    """Mask Preview - original implement in ComfyUI_essentials.
+
+    https://github.com/cubiq/ComfyUI_essentials/blob/9d9f4bedfc9f0321c19faf71855e228c93bd0dc9/mask.py#L81
+    Upstream requested in https://github.com/Kosinkadink/rfcs/blob/main/rfcs/0000-corenodes.md#preview-nodes
+    """
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="MaskPreview_V3",
+            display_name="Preview Mask _V3",
+            category="mask",
+            inputs=[
+                io.Mask.Input("masks"),
+            ],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, masks):
+        return io.NodeOutput(ui=ui.PreviewMask(masks))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CropMask,
+    FeatherMask,
+    GrowMask,
+    ImageColorToMask,
+    ImageCompositeMasked,
+    ImageToMask,
+    InvertMask,
+    LatentCompositeMasked,
+    MaskComposite,
+    MaskPreview,
+    MaskToImage,
+    SolidMask,
+    ThresholdMask,
+]

comfy_extras/v3/nodes_mochi.py

@@ -0,0 +1,38 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.model_management
+import nodes
+from comfy_api.latest import io
+
+
+class EmptyMochiLatentVideo(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="EmptyMochiLatentVideo_V3",
+            category="latent/video",
+            inputs=[
+                io.Int.Input("width", default=848, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("height", default=480, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("length", default=25, min=7, max=nodes.MAX_RESOLUTION, step=6),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, width, height, length, batch_size=1):
+        latent = torch.zeros(
+            [batch_size, 12, ((length - 1) // 6) + 1, height // 8, width // 8],
+            device=comfy.model_management.intermediate_device(),
+        )
+        return io.NodeOutput({"samples": latent})
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    EmptyMochiLatentVideo,
+]

comfy_extras/v3/nodes_model_advanced.py

@@ -0,0 +1,387 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.latent_formats
+import comfy.model_sampling
+import comfy.sd
+import node_helpers
+import nodes
+from comfy_api.latest import io
+
+
+class LCM(comfy.model_sampling.EPS):
+    def calculate_denoised(self, sigma, model_output, model_input):
+        timestep = self.timestep(sigma).view(sigma.shape[:1] + (1,) * (model_output.ndim - 1))
+        sigma = sigma.view(sigma.shape[:1] + (1,) * (model_output.ndim - 1))
+        x0 = model_input - model_output * sigma
+
+        sigma_data = 0.5
+        scaled_timestep = timestep * 10.0 # timestep_scaling
+
+        c_skip = sigma_data**2 / (scaled_timestep**2 + sigma_data**2)
+        c_out = scaled_timestep / (scaled_timestep**2 + sigma_data**2) ** 0.5
+
+        return c_out * x0 + c_skip * model_input
+
+
+class ModelSamplingDiscreteDistilled(comfy.model_sampling.ModelSamplingDiscrete):
+    original_timesteps = 50
+
+    def __init__(self, model_config=None, zsnr=None):
+        super().__init__(model_config, zsnr=zsnr)
+
+        self.skip_steps = self.num_timesteps // self.original_timesteps
+
+        sigmas_valid = torch.zeros((self.original_timesteps), dtype=torch.float32)
+        for x in range(self.original_timesteps):
+            sigmas_valid[self.original_timesteps - 1 - x] = self.sigmas[self.num_timesteps - 1 - x * self.skip_steps]
+
+        self.set_sigmas(sigmas_valid)
+
+    def timestep(self, sigma):
+        log_sigma = sigma.log()
+        dists = log_sigma.to(self.log_sigmas.device) - self.log_sigmas[:, None]
+        return (dists.abs().argmin(dim=0).view(sigma.shape) * self.skip_steps + (self.skip_steps - 1)).to(sigma.device)
+
+    def sigma(self, timestep):
+        t = torch.clamp(
+            ((timestep.float().to(self.log_sigmas.device) - (self.skip_steps - 1)) / self.skip_steps).float(),
+            min=0,
+            max=(len(self.sigmas) - 1),
+        )
+        low_idx = t.floor().long()
+        high_idx = t.ceil().long()
+        w = t.frac()
+        log_sigma = (1 - w) * self.log_sigmas[low_idx] + w * self.log_sigmas[high_idx]
+        return log_sigma.exp().to(timestep.device)
+
+
+class ModelSamplingDiscrete(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSamplingDiscrete_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Combo.Input("sampling", options=["eps", "v_prediction", "lcm", "x0", "img_to_img"]),
+                io.Boolean.Input("zsnr", default=False),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, sampling, zsnr):
+        m = model.clone()
+
+        sampling_base = comfy.model_sampling.ModelSamplingDiscrete
+        if sampling == "eps":
+            sampling_type = comfy.model_sampling.EPS
+        elif sampling == "v_prediction":
+            sampling_type = comfy.model_sampling.V_PREDICTION
+        elif sampling == "lcm":
+            sampling_type = LCM
+            sampling_base = ModelSamplingDiscreteDistilled
+        elif sampling == "x0":
+            sampling_type = comfy.model_sampling.X0
+        elif sampling == "img_to_img":
+            sampling_type = comfy.model_sampling.IMG_TO_IMG
+
+        class ModelSamplingAdvanced(sampling_base, sampling_type):
+            pass
+
+        model_sampling = ModelSamplingAdvanced(model.model.model_config, zsnr=zsnr)
+
+        m.add_object_patch("model_sampling", model_sampling)
+        return io.NodeOutput(m)
+
+
+class ModelSamplingStableCascade(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSamplingStableCascade_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("shift", default=2.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, shift):
+        m = model.clone()
+
+        sampling_base = comfy.model_sampling.StableCascadeSampling
+        sampling_type = comfy.model_sampling.EPS
+
+        class ModelSamplingAdvanced(sampling_base, sampling_type):
+            pass
+
+        model_sampling = ModelSamplingAdvanced(model.model.model_config)
+        model_sampling.set_parameters(shift)
+        m.add_object_patch("model_sampling", model_sampling)
+        return io.NodeOutput(m)
+
+
+class ModelSamplingSD3(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSamplingSD3_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("shift", default=3.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, shift, multiplier: int | float = 1000):
+        m = model.clone()
+
+        sampling_base = comfy.model_sampling.ModelSamplingDiscreteFlow
+        sampling_type = comfy.model_sampling.CONST
+
+        class ModelSamplingAdvanced(sampling_base, sampling_type):
+            pass
+
+        model_sampling = ModelSamplingAdvanced(model.model.model_config)
+        model_sampling.set_parameters(shift=shift, multiplier=multiplier)
+        m.add_object_patch("model_sampling", model_sampling)
+        return io.NodeOutput(m)
+
+
+class ModelSamplingAuraFlow(ModelSamplingSD3):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSamplingAuraFlow_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("shift", default=1.73, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, shift, multiplier: int | float = 1.0):
+        return super().execute(model, shift, multiplier)
+
+
+class ModelSamplingFlux(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSamplingFlux_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("max_shift", default=1.15, min=0.0, max=100.0, step=0.01),
+                io.Float.Input("base_shift", default=0.5, min=0.0, max=100.0, step=0.01),
+                io.Int.Input("width", default=1024, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("height", default=1024, min=16, max=nodes.MAX_RESOLUTION, step=8),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, max_shift, base_shift, width, height):
+        m = model.clone()
+
+        x1 = 256
+        x2 = 4096
+        mm = (max_shift - base_shift) / (x2 - x1)
+        b = base_shift - mm * x1
+        shift = (width * height / (8 * 8 * 2 * 2)) * mm + b
+
+        sampling_base = comfy.model_sampling.ModelSamplingFlux
+        sampling_type = comfy.model_sampling.CONST
+
+        class ModelSamplingAdvanced(sampling_base, sampling_type):
+            pass
+
+        model_sampling = ModelSamplingAdvanced(model.model.model_config)
+        model_sampling.set_parameters(shift=shift)
+        m.add_object_patch("model_sampling", model_sampling)
+        return io.NodeOutput(m)
+
+
+class ModelSamplingContinuousEDM(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSamplingContinuousEDM_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Combo.Input(
+                    "sampling", options=["v_prediction", "edm", "edm_playground_v2.5", "eps", "cosmos_rflow"]
+                ),
+                io.Float.Input("sigma_max", default=120.0, min=0.0, max=1000.0, step=0.001, round=False),
+                io.Float.Input("sigma_min", default=0.002, min=0.0, max=1000.0, step=0.001, round=False),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, sampling, sigma_max, sigma_min):
+        m = model.clone()
+
+        sampling_base = comfy.model_sampling.ModelSamplingContinuousEDM
+        latent_format = None
+        sigma_data = 1.0
+        if sampling == "eps":
+            sampling_type = comfy.model_sampling.EPS
+        elif sampling == "edm":
+            sampling_type = comfy.model_sampling.EDM
+            sigma_data = 0.5
+        elif sampling == "v_prediction":
+            sampling_type = comfy.model_sampling.V_PREDICTION
+        elif sampling == "edm_playground_v2.5":
+            sampling_type = comfy.model_sampling.EDM
+            sigma_data = 0.5
+            latent_format = comfy.latent_formats.SDXL_Playground_2_5()
+        elif sampling == "cosmos_rflow":
+            sampling_type = comfy.model_sampling.COSMOS_RFLOW
+            sampling_base = comfy.model_sampling.ModelSamplingCosmosRFlow
+
+        class ModelSamplingAdvanced(sampling_base, sampling_type):
+            pass
+
+        model_sampling = ModelSamplingAdvanced(model.model.model_config)
+        model_sampling.set_parameters(sigma_min, sigma_max, sigma_data)
+        m.add_object_patch("model_sampling", model_sampling)
+        if latent_format is not None:
+            m.add_object_patch("latent_format", latent_format)
+        return io.NodeOutput(m)
+
+
+class ModelSamplingContinuousV(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSamplingContinuousV_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Combo.Input("sampling", options=["v_prediction"]),
+                io.Float.Input("sigma_max", default=500.0, min=0.0, max=1000.0, step=0.001, round=False),
+                io.Float.Input("sigma_min", default=0.03, min=0.0, max=1000.0, step=0.001, round=False),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, sampling, sigma_max, sigma_min):
+        m = model.clone()
+
+        sigma_data = 1.0
+        if sampling == "v_prediction":
+            sampling_type = comfy.model_sampling.V_PREDICTION
+
+        class ModelSamplingAdvanced(comfy.model_sampling.ModelSamplingContinuousV, sampling_type):
+            pass
+
+        model_sampling = ModelSamplingAdvanced(model.model.model_config)
+        model_sampling.set_parameters(sigma_min, sigma_max, sigma_data)
+        m.add_object_patch("model_sampling", model_sampling)
+        return io.NodeOutput(m)
+
+
+class RescaleCFG(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RescaleCFG_V3",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("multiplier", default=0.7, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, multiplier):
+        def rescale_cfg(args):
+            cond = args["cond"]
+            uncond = args["uncond"]
+            cond_scale = args["cond_scale"]
+            sigma = args["sigma"]
+            sigma = sigma.view(sigma.shape[:1] + (1,) * (cond.ndim - 1))
+            x_orig = args["input"]
+
+            #rescale cfg has to be done on v-pred model output
+            x = x_orig / (sigma * sigma + 1.0)
+            cond = ((x - (x_orig - cond)) * (sigma ** 2 + 1.0) ** 0.5) / (sigma)
+            uncond = ((x - (x_orig - uncond)) * (sigma ** 2 + 1.0) ** 0.5) / (sigma)
+
+            #rescalecfg
+            x_cfg = uncond + cond_scale * (cond - uncond)
+            ro_pos = torch.std(cond, dim=(1,2,3), keepdim=True)
+            ro_cfg = torch.std(x_cfg, dim=(1,2,3), keepdim=True)
+
+            x_rescaled = x_cfg * (ro_pos / ro_cfg)
+            x_final = multiplier * x_rescaled + (1.0 - multiplier) * x_cfg
+
+            return x_orig - (x - x_final * sigma / (sigma * sigma + 1.0) ** 0.5)
+
+        m = model.clone()
+        m.set_model_sampler_cfg_function(rescale_cfg)
+        return io.NodeOutput(m)
+
+
+class ModelComputeDtype(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelComputeDtype_V3",
+            category="advanced/debug/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Combo.Input("dtype", options=["default", "fp32", "fp16", "bf16"]),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, dtype):
+        m = model.clone()
+        m.set_model_compute_dtype(node_helpers.string_to_torch_dtype(dtype))
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    ModelSamplingAuraFlow,
+    ModelComputeDtype,
+    ModelSamplingContinuousEDM,
+    ModelSamplingContinuousV,
+    ModelSamplingDiscrete,
+    ModelSamplingFlux,
+    ModelSamplingSD3,
+    ModelSamplingStableCascade,
+    RescaleCFG,
+]

comfy_extras/v3/nodes_model_downscale.py

@@ -0,0 +1,68 @@
+from __future__ import annotations
+
+import comfy.utils
+from comfy_api.latest import io
+
+
+class PatchModelAddDownscale(io.ComfyNode):
+    UPSCALE_METHODS = ["bicubic", "nearest-exact", "bilinear", "area", "bislerp"]
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PatchModelAddDownscale_V3",
+            display_name="PatchModelAddDownscale (Kohya Deep Shrink) _V3",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Int.Input("block_number", default=3, min=1, max=32, step=1),
+                io.Float.Input("downscale_factor", default=2.0, min=0.1, max=9.0, step=0.001),
+                io.Float.Input("start_percent", default=0.0, min=0.0, max=1.0, step=0.001),
+                io.Float.Input("end_percent", default=0.35, min=0.0, max=1.0, step=0.001),
+                io.Boolean.Input("downscale_after_skip", default=True),
+                io.Combo.Input("downscale_method", options=cls.UPSCALE_METHODS),
+                io.Combo.Input("upscale_method", options=cls.UPSCALE_METHODS),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(
+        cls, model, block_number, downscale_factor, start_percent, end_percent, downscale_after_skip, downscale_method, upscale_method
+    ):
+        model_sampling = model.get_model_object("model_sampling")
+        sigma_start = model_sampling.percent_to_sigma(start_percent)
+        sigma_end = model_sampling.percent_to_sigma(end_percent)
+
+        def input_block_patch(h, transformer_options):
+            if transformer_options["block"][1] == block_number:
+                sigma = transformer_options["sigmas"][0].item()
+                if sigma <= sigma_start and sigma >= sigma_end:
+                    h = comfy.utils.common_upscale(
+                        h,
+                        round(h.shape[-1] * (1.0 / downscale_factor)),
+                        round(h.shape[-2] * (1.0 / downscale_factor)),
+                        downscale_method,
+                        "disabled",
+                    )
+            return h
+
+        def output_block_patch(h, hsp, transformer_options):
+            if h.shape[2] != hsp.shape[2]:
+                h = comfy.utils.common_upscale(h, hsp.shape[-1], hsp.shape[-2], upscale_method, "disabled")
+            return h, hsp
+
+        m = model.clone()
+        if downscale_after_skip:
+            m.set_model_input_block_patch_after_skip(input_block_patch)
+        else:
+            m.set_model_input_block_patch(input_block_patch)
+        m.set_model_output_block_patch(output_block_patch)
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    PatchModelAddDownscale,
+]

comfy_extras/v3/nodes_model_merging.py

@@ -0,0 +1,422 @@
+from __future__ import annotations
+
+import json
+import os
+
+import torch
+
+import comfy.model_base
+import comfy.model_management
+import comfy.model_sampling
+import comfy.sd
+import comfy.utils
+import folder_paths
+from comfy.cli_args import args
+from comfy_api.latest import io
+
+
+def save_checkpoint(model, clip=None, vae=None, clip_vision=None, filename_prefix=None, output_dir=None, prompt=None, extra_pnginfo=None):
+    full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, output_dir)
+    prompt_info = ""
+    if prompt is not None:
+        prompt_info = json.dumps(prompt)
+
+    metadata = {}
+
+    enable_modelspec = True
+    if isinstance(model.model, comfy.model_base.SDXL):
+        if isinstance(model.model, comfy.model_base.SDXL_instructpix2pix):
+            metadata["modelspec.architecture"] = "stable-diffusion-xl-v1-edit"
+        else:
+            metadata["modelspec.architecture"] = "stable-diffusion-xl-v1-base"
+    elif isinstance(model.model, comfy.model_base.SDXLRefiner):
+        metadata["modelspec.architecture"] = "stable-diffusion-xl-v1-refiner"
+    elif isinstance(model.model, comfy.model_base.SVD_img2vid):
+        metadata["modelspec.architecture"] = "stable-video-diffusion-img2vid-v1"
+    elif isinstance(model.model, comfy.model_base.SD3):
+        metadata["modelspec.architecture"] = "stable-diffusion-v3-medium" #TODO: other SD3 variants
+    else:
+        enable_modelspec = False
+
+    if enable_modelspec:
+        metadata["modelspec.sai_model_spec"] = "1.0.0"
+        metadata["modelspec.implementation"] = "sgm"
+        metadata["modelspec.title"] = "{} {}".format(filename, counter)
+
+    #TODO:
+    # "stable-diffusion-v1", "stable-diffusion-v1-inpainting", "stable-diffusion-v2-512",
+    # "stable-diffusion-v2-768-v", "stable-diffusion-v2-unclip-l", "stable-diffusion-v2-unclip-h",
+    # "v2-inpainting"
+
+    extra_keys = {}
+    model_sampling = model.get_model_object("model_sampling")
+    if isinstance(model_sampling, comfy.model_sampling.ModelSamplingContinuousEDM):
+        if isinstance(model_sampling, comfy.model_sampling.V_PREDICTION):
+            extra_keys["edm_vpred.sigma_max"] = torch.tensor(model_sampling.sigma_max).float()
+            extra_keys["edm_vpred.sigma_min"] = torch.tensor(model_sampling.sigma_min).float()
+
+    if model.model.model_type == comfy.model_base.ModelType.EPS:
+        metadata["modelspec.predict_key"] = "epsilon"
+    elif model.model.model_type == comfy.model_base.ModelType.V_PREDICTION:
+        metadata["modelspec.predict_key"] = "v"
+        extra_keys["v_pred"] = torch.tensor([])
+        if getattr(model_sampling, "zsnr", False):
+            extra_keys["ztsnr"] = torch.tensor([])
+
+    if not args.disable_metadata:
+        metadata["prompt"] = prompt_info
+        if extra_pnginfo is not None:
+            for x in extra_pnginfo:
+                metadata[x] = json.dumps(extra_pnginfo[x])
+
+    output_checkpoint = f"{filename}_{counter:05}_.safetensors"
+    output_checkpoint = os.path.join(full_output_folder, output_checkpoint)
+
+    comfy.sd.save_checkpoint(output_checkpoint, model, clip, vae, clip_vision, metadata=metadata, extra_keys=extra_keys)
+
+
+class ModelMergeSimple(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelMergeSimple_V3",
+            category="advanced/model_merging",
+            inputs=[
+                io.Model.Input("model1"),
+                io.Model.Input("model2"),
+                io.Float.Input("ratio", default=1.0, min=0.0, max=1.0, step=0.01)
+            ],
+            outputs=[
+                io.Model.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, model1, model2, ratio):
+        m = model1.clone()
+        kp = model2.get_key_patches("diffusion_model.")
+        for k in kp:
+            m.add_patches({k: kp[k]}, 1.0 - ratio, ratio)
+        return io.NodeOutput(m)
+
+
+class ModelSubtract(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelMergeSubtract_V3",
+            category="advanced/model_merging",
+            inputs=[
+                io.Model.Input("model1"),
+                io.Model.Input("model2"),
+                io.Float.Input("multiplier", default=1.0, min=-10.0, max=10.0, step=0.01)
+            ],
+            outputs=[
+                io.Model.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, model1, model2, multiplier):
+        m = model1.clone()
+        kp = model2.get_key_patches("diffusion_model.")
+        for k in kp:
+            m.add_patches({k: kp[k]}, - multiplier, multiplier)
+        return io.NodeOutput(m)
+
+
+class ModelAdd(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelMergeAdd_V3",
+            category="advanced/model_merging",
+            inputs=[
+                io.Model.Input("model1"),
+                io.Model.Input("model2")
+            ],
+            outputs=[
+                io.Model.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, model1, model2):
+        m = model1.clone()
+        kp = model2.get_key_patches("diffusion_model.")
+        for k in kp:
+            m.add_patches({k: kp[k]}, 1.0, 1.0)
+        return io.NodeOutput(m)
+
+
+class CLIPMergeSimple(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPMergeSimple_V3",
+            category="advanced/model_merging",
+            inputs=[
+                io.Clip.Input("clip1"),
+                io.Clip.Input("clip2"),
+                io.Float.Input("ratio", default=1.0, min=0.0, max=1.0, step=0.01)
+            ],
+            outputs=[
+                io.Clip.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, clip1, clip2, ratio):
+        m = clip1.clone()
+        kp = clip2.get_key_patches()
+        for k in kp:
+            if k.endswith(".position_ids") or k.endswith(".logit_scale"):
+                continue
+            m.add_patches({k: kp[k]}, 1.0 - ratio, ratio)
+        return io.NodeOutput(m)
+
+
+class CLIPSubtract(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPMergeSubtract_V3",
+            category="advanced/model_merging",
+            inputs=[
+                io.Clip.Input("clip1"),
+                io.Clip.Input("clip2"),
+                io.Float.Input("multiplier", default=1.0, min=-10.0, max=10.0, step=0.01)
+            ],
+            outputs=[
+                io.Clip.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, clip1, clip2, multiplier):
+        m = clip1.clone()
+        kp = clip2.get_key_patches()
+        for k in kp:
+            if k.endswith(".position_ids") or k.endswith(".logit_scale"):
+                continue
+            m.add_patches({k: kp[k]}, - multiplier, multiplier)
+        return io.NodeOutput(m)
+
+
+class CLIPAdd(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPMergeAdd_V3",
+            category="advanced/model_merging",
+            inputs=[
+                io.Clip.Input("clip1"),
+                io.Clip.Input("clip2")
+            ],
+            outputs=[
+                io.Clip.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, clip1, clip2):
+        m = clip1.clone()
+        kp = clip2.get_key_patches()
+        for k in kp:
+            if k.endswith(".position_ids") or k.endswith(".logit_scale"):
+                continue
+            m.add_patches({k: kp[k]}, 1.0, 1.0)
+        return io.NodeOutput(m)
+
+
+class ModelMergeBlocks(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelMergeBlocks_V3",
+            category="advanced/model_merging",
+            inputs=[
+                io.Model.Input("model1"),
+                io.Model.Input("model2"),
+                io.Float.Input("input", default=1.0, min=0.0, max=1.0, step=0.01),
+                io.Float.Input("middle", default=1.0, min=0.0, max=1.0, step=0.01),
+                io.Float.Input("out", default=1.0, min=0.0, max=1.0, step=0.01)
+            ],
+            outputs=[
+                io.Model.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, model1, model2, **kwargs):
+        m = model1.clone()
+        kp = model2.get_key_patches("diffusion_model.")
+        default_ratio = next(iter(kwargs.values()))
+
+        for k in kp:
+            ratio = default_ratio
+            k_unet = k[len("diffusion_model."):]
+
+            last_arg_size = 0
+            for arg in kwargs:
+                if k_unet.startswith(arg) and last_arg_size < len(arg):
+                    ratio = kwargs[arg]
+                    last_arg_size = len(arg)
+
+            m.add_patches({k: kp[k]}, 1.0 - ratio, ratio)
+        return io.NodeOutput(m)
+
+
+class CheckpointSave(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CheckpointSave_V3",
+            display_name="Save Checkpoint _V3",
+            category="advanced/model_merging",
+            is_output_node=True,
+            inputs=[
+                io.Model.Input("model"),
+                io.Clip.Input("clip"),
+                io.Vae.Input("vae"),
+                io.String.Input("filename_prefix", default="checkpoints/ComfyUI")
+            ],
+            outputs=[],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo]
+        )
+
+    @classmethod
+    def execute(cls, model, clip, vae, filename_prefix):
+        save_checkpoint(model, clip=clip, vae=vae, filename_prefix=filename_prefix, output_dir=folder_paths.get_output_directory(), prompt=cls.hidden.prompt, extra_pnginfo=cls.hidden.extra_pnginfo)
+        return io.NodeOutput()
+
+
+class CLIPSave(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPSave_V3",
+            category="advanced/model_merging",
+            is_output_node=True,
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("filename_prefix", default="clip/ComfyUI")
+            ],
+            outputs=[],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo]
+        )
+
+    @classmethod
+    def execute(cls, clip, filename_prefix):
+        prompt_info = ""
+        if cls.hidden.prompt is not None:
+            prompt_info = json.dumps(cls.hidden.prompt)
+
+        metadata = {}
+        if not args.disable_metadata:
+            metadata["format"] = "pt"
+            metadata["prompt"] = prompt_info
+            if cls.hidden.extra_pnginfo is not None:
+                for x in cls.hidden.extra_pnginfo:
+                    metadata[x] = json.dumps(cls.hidden.extra_pnginfo[x])
+
+        comfy.model_management.load_models_gpu([clip.load_model()], force_patch_weights=True)
+        clip_sd = clip.get_sd()
+
+        for prefix in ["clip_l.", "clip_g.", "clip_h.", "t5xxl.", "pile_t5xl.", "mt5xl.", "umt5xxl.", "t5base.", "gemma2_2b.", "llama.", "hydit_clip.", ""]:
+            k = list(filter(lambda a: a.startswith(prefix), clip_sd.keys()))
+            current_clip_sd = {}
+            for x in k:
+                current_clip_sd[x] = clip_sd.pop(x)
+            if len(current_clip_sd) == 0:
+                continue
+
+            p = prefix[:-1]
+            replace_prefix = {}
+            filename_prefix_ = filename_prefix
+            if len(p) > 0:
+                filename_prefix_ = "{}_{}".format(filename_prefix_, p)
+                replace_prefix[prefix] = ""
+            replace_prefix["transformer."] = ""
+
+            full_output_folder, filename, counter, subfolder, filename_prefix_ = folder_paths.get_save_image_path(filename_prefix_, folder_paths.get_output_directory())
+
+            output_checkpoint = f"{filename}_{counter:05}_.safetensors"
+            output_checkpoint = os.path.join(full_output_folder, output_checkpoint)
+
+            current_clip_sd = comfy.utils.state_dict_prefix_replace(current_clip_sd, replace_prefix)
+
+            comfy.utils.save_torch_file(current_clip_sd, output_checkpoint, metadata=metadata)
+        return io.NodeOutput()
+
+
+class VAESave(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="VAESave_V3",
+            category="advanced/model_merging",
+            is_output_node=True,
+            inputs=[
+                io.Vae.Input("vae"),
+                io.String.Input("filename_prefix", default="vae/ComfyUI_vae")
+            ],
+            outputs=[],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo]
+        )
+
+    @classmethod
+    def execute(cls, vae, filename_prefix):
+        full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, folder_paths.get_output_directory())
+        prompt_info = ""
+        if cls.hidden.prompt is not None:
+            prompt_info = json.dumps(cls.hidden.prompt)
+
+        metadata = {}
+        if not args.disable_metadata:
+            metadata["prompt"] = prompt_info
+            if cls.hidden.extra_pnginfo is not None:
+                for x in cls.hidden.extra_pnginfo:
+                    metadata[x] = json.dumps(cls.hidden.extra_pnginfo[x])
+
+        output_checkpoint = f"{filename}_{counter:05}_.safetensors"
+        output_checkpoint = os.path.join(full_output_folder, output_checkpoint)
+
+        comfy.utils.save_torch_file(vae.get_sd(), output_checkpoint, metadata=metadata)
+        return io.NodeOutput()
+
+
+class ModelSave(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ModelSave_V3",
+            category="advanced/model_merging",
+            is_output_node=True,
+            inputs=[
+                io.Model.Input("model"),
+                io.String.Input("filename_prefix", default="diffusion_models/ComfyUI")
+            ],
+            outputs=[],
+            hidden=[io.Hidden.prompt, io.Hidden.extra_pnginfo]
+        )
+
+    @classmethod
+    def execute(cls, model, filename_prefix):
+        save_checkpoint(model, filename_prefix=filename_prefix, output_dir=folder_paths.get_output_directory(), prompt=cls.hidden.prompt, extra_pnginfo=cls.hidden.extra_pnginfo)
+        return io.NodeOutput()
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CheckpointSave,
+    CLIPAdd,
+    CLIPMergeSimple,
+    CLIPSave,
+    CLIPSubtract,
+    ModelAdd,
+    ModelMergeBlocks,
+    ModelMergeSimple,
+    ModelSave,
+    ModelSubtract,
+    VAESave,
+]

comfy_extras/v3/nodes_model_merging_model_specific.py

@@ -0,0 +1,399 @@
+from __future__ import annotations
+
+from comfy_api.latest import io
+from comfy_extras.v3.nodes_model_merging import ModelMergeBlocks
+
+
+class ModelMergeSD1(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("time_embed.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("label_emb.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(12):
+            inputs.append(io.Float.Input(f"input_blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        for i in range(3):
+            inputs.append(io.Float.Input(f"middle_block.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        for i in range(12):
+            inputs.append(io.Float.Input(f"output_blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("out.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeSD1_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeSDXL(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("time_embed.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("label_emb.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(9):
+            inputs.append(io.Float.Input(f"input_blocks.{i}", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        for i in range(3):
+            inputs.append(io.Float.Input(f"middle_block.{i}", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        for i in range(9):
+            inputs.append(io.Float.Input(f"output_blocks.{i}", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("out.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeSDXL_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeSD3_2B(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("pos_embed.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("x_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("context_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("y_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedder.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(24):
+            inputs.append(io.Float.Input(f"joint_blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("final_layer.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeSD3_2B_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeAuraflow(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("init_x_linear.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("positional_encoding", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("cond_seq_linear.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("register_tokens", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedder.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(4):
+            inputs.append(io.Float.Input(f"double_layers.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        for i in range(32):
+            inputs.append(io.Float.Input(f"single_layers.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.extend([
+            io.Float.Input("modF.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("final_linear.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ])
+
+        return io.Schema(
+            node_id="ModelMergeAuraflow_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeFlux1(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("img_in.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("time_in.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("guidance_in", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("vector_in.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("txt_in.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(19):
+            inputs.append(io.Float.Input(f"double_blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        for i in range(38):
+            inputs.append(io.Float.Input(f"single_blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("final_layer.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeFlux1_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeSD35_Large(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("pos_embed.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("x_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("context_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("y_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedder.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(38):
+            inputs.append(io.Float.Input(f"joint_blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("final_layer.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeSD35_Large_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeMochiPreview(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("pos_frequencies.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t5_y_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t5_yproj.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(48):
+            inputs.append(io.Float.Input(f"blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("final_layer.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeMochiPreview_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeLTXV(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("patchify_proj.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("adaln_single.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("caption_projection.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(28):
+            inputs.append(io.Float.Input(f"transformer_blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.extend([
+            io.Float.Input("scale_shift_table", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("proj_out.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ])
+
+        return io.Schema(
+            node_id="ModelMergeLTXV_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeCosmos7B(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("pos_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("extra_pos_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("x_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("affline_norm.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(28):
+            inputs.append(io.Float.Input(f"blocks.block{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("final_layer.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeCosmos7B_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeCosmos14B(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("pos_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("extra_pos_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("x_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("affline_norm.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(36):
+            inputs.append(io.Float.Input(f"blocks.block{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("final_layer.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeCosmos14B_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeWAN2_1(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("patch_embedding.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("time_embedding.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("time_projection.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("text_embedding.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("img_emb.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(40):
+            inputs.append(io.Float.Input(f"blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("head.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeWAN2_1_V3",
+            category="advanced/model_merging/model_specific",
+            description="1.3B model has 30 blocks, 14B model has 40 blocks. Image to video model has the extra img_emb.",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeCosmosPredict2_2B(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("pos_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("x_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedding_norm.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(28):
+            inputs.append(io.Float.Input(f"blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("final_layer.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeCosmosPredict2_2B_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+class ModelMergeCosmosPredict2_14B(ModelMergeBlocks):
+    @classmethod
+    def define_schema(cls):
+        inputs = [
+            io.Model.Input("model1"),
+            io.Model.Input("model2"),
+            io.Float.Input("pos_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("x_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedder.", default=1.0, min=0.0, max=1.0, step=0.01),
+            io.Float.Input("t_embedding_norm.", default=1.0, min=0.0, max=1.0, step=0.01)
+        ]
+
+        for i in range(36):
+            inputs.append(io.Float.Input(f"blocks.{i}.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        inputs.append(io.Float.Input("final_layer.", default=1.0, min=0.0, max=1.0, step=0.01))
+
+        return io.Schema(
+            node_id="ModelMergeCosmosPredict2_14B_V3",
+            category="advanced/model_merging/model_specific",
+            inputs=inputs,
+            outputs=[
+                io.Model.Output(),
+            ]
+        )
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    ModelMergeAuraflow,
+    ModelMergeCosmos14B,
+    ModelMergeCosmos7B,
+    ModelMergeCosmosPredict2_14B,
+    ModelMergeCosmosPredict2_2B,
+    ModelMergeFlux1,
+    ModelMergeLTXV,
+    ModelMergeMochiPreview,
+    ModelMergeSD1,
+    ModelMergeSD3_2B,
+    ModelMergeSD35_Large,
+    ModelMergeSDXL,
+    ModelMergeWAN2_1,
+]

comfy_extras/v3/nodes_morphology.py

@@ -0,0 +1,108 @@
+from __future__ import annotations
+
+import kornia.color
+import torch
+from kornia.morphology import (
+    bottom_hat,
+    closing,
+    dilation,
+    erosion,
+    gradient,
+    opening,
+    top_hat,
+)
+
+import comfy.model_management
+from comfy_api.latest import io
+
+
+class Morphology(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="Morphology_V3",
+            display_name="ImageMorphology _V3",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image"),
+                io.Combo.Input("operation", options=["erode", "dilate", "open", "close", "gradient", "bottom_hat", "top_hat"]),
+                io.Int.Input("kernel_size", default=3, min=3, max=999, step=1),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image, operation, kernel_size):
+        device = comfy.model_management.get_torch_device()
+        kernel = torch.ones(kernel_size, kernel_size, device=device)
+        image_k = image.to(device).movedim(-1, 1)
+        if operation == "erode":
+            output = erosion(image_k, kernel)
+        elif operation == "dilate":
+            output = dilation(image_k, kernel)
+        elif operation == "open":
+            output = opening(image_k, kernel)
+        elif operation == "close":
+            output = closing(image_k, kernel)
+        elif operation == "gradient":
+            output = gradient(image_k, kernel)
+        elif operation == "top_hat":
+            output = top_hat(image_k, kernel)
+        elif operation == "bottom_hat":
+            output = bottom_hat(image_k, kernel)
+        else:
+            raise ValueError(f"Invalid operation {operation} for morphology. Must be one of 'erode', 'dilate', 'open', 'close', 'gradient', 'tophat', 'bottomhat'")
+        return io.NodeOutput(output.to(comfy.model_management.intermediate_device()).movedim(1, -1))
+
+
+class ImageRGBToYUV(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageRGBToYUV_V3",
+            category="image/batch",
+            inputs=[
+                io.Image.Input("image"),
+            ],
+            outputs=[
+                io.Image.Output(display_name="Y"),
+                io.Image.Output(display_name="U"),
+                io.Image.Output(display_name="V"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image):
+        out = kornia.color.rgb_to_ycbcr(image.movedim(-1, 1)).movedim(1, -1)
+        return io.NodeOutput(out[..., 0:1].expand_as(image), out[..., 1:2].expand_as(image), out[..., 2:3].expand_as(image))
+
+
+class ImageYUVToRGB(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageYUVToRGB_V3",
+            category="image/batch",
+            inputs=[
+                io.Image.Input("Y"),
+                io.Image.Input("U"),
+                io.Image.Input("V"),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, Y, U, V):
+        image = torch.cat([torch.mean(Y, dim=-1, keepdim=True), torch.mean(U, dim=-1, keepdim=True), torch.mean(V, dim=-1, keepdim=True)], dim=-1)
+        return io.NodeOutput(kornia.color.ycbcr_to_rgb(image.movedim(-1, 1)).movedim(1, -1))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    ImageRGBToYUV,
+    ImageYUVToRGB,
+    Morphology,
+]

comfy_extras/v3/nodes_optimalsteps.py

@@ -0,0 +1,64 @@
+from __future__ import annotations
+
+import numpy as np
+import torch
+
+from comfy_api.latest import io
+
+# from https://github.com/bebebe666/OptimalSteps
+
+
+def loglinear_interp(t_steps, num_steps):
+    """Performs log-linear interpolation of a given array of decreasing numbers."""
+    xs = np.linspace(0, 1, len(t_steps))
+    ys = np.log(t_steps[::-1])
+
+    new_xs = np.linspace(0, 1, num_steps)
+    new_ys = np.interp(new_xs, xs, ys)
+
+    return np.exp(new_ys)[::-1].copy()
+
+
+NOISE_LEVELS = {
+    "FLUX": [0.9968, 0.9886, 0.9819, 0.975, 0.966, 0.9471, 0.9158, 0.8287, 0.5512, 0.2808, 0.001],
+    "Wan": [1.0, 0.997, 0.995, 0.993, 0.991, 0.989, 0.987, 0.985, 0.98, 0.975, 0.973, 0.968, 0.96, 0.946, 0.927, 0.902, 0.864, 0.776, 0.539, 0.208, 0.001],
+    "Chroma": [0.992, 0.99, 0.988, 0.985, 0.982, 0.978, 0.973, 0.968, 0.961, 0.953, 0.943, 0.931, 0.917, 0.9, 0.881, 0.858, 0.832, 0.802, 0.769, 0.731, 0.69, 0.646, 0.599, 0.55, 0.501, 0.451, 0.402, 0.355, 0.311, 0.27, 0.232, 0.199, 0.169, 0.143, 0.12, 0.101, 0.084, 0.07, 0.058, 0.048, 0.001],
+}
+
+
+class OptimalStepsScheduler(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="OptimalStepsScheduler_V3",
+            category="sampling/custom_sampling/schedulers",
+            inputs=[
+                io.Combo.Input("model_type", options=["FLUX", "Wan", "Chroma"]),
+                io.Int.Input("steps", default=20, min=3, max=1000),
+                io.Float.Input("denoise", default=1.0, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[
+                io.Sigmas.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model_type, steps, denoise):
+        total_steps = steps
+        if denoise < 1.0:
+            if denoise <= 0.0:
+                return io.NodeOutput(torch.FloatTensor([]))
+            total_steps = round(steps * denoise)
+
+        sigmas = NOISE_LEVELS[model_type][:]
+        if (steps + 1) != len(sigmas):
+            sigmas = loglinear_interp(sigmas, steps + 1)
+
+        sigmas = sigmas[-(total_steps + 1):]
+        sigmas[-1] = 0
+        return io.NodeOutput(torch.FloatTensor(sigmas))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    OptimalStepsScheduler,
+]

comfy_extras/v3/nodes_pag.py

@@ -0,0 +1,62 @@
+from __future__ import annotations
+
+import comfy.model_patcher
+import comfy.samplers
+from comfy_api.latest import io
+
+#Modified/simplified version of the node from: https://github.com/pamparamm/sd-perturbed-attention
+#If you want the one with more options see the above repo.
+
+#My modified one here is more basic but has fewer chances of breaking with ComfyUI updates.
+
+
+class PerturbedAttentionGuidance(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PerturbedAttentionGuidance_V3",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("scale", default=3.0, min=0.0, max=100.0, step=0.01, round=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, scale):
+        unet_block = "middle"
+        unet_block_id = 0
+        m = model.clone()
+
+        def perturbed_attention(q, k, v, extra_options, mask=None):
+            return v
+
+        def post_cfg_function(args):
+            model = args["model"]
+            cond_pred = args["cond_denoised"]
+            cond = args["cond"]
+            cfg_result = args["denoised"]
+            sigma = args["sigma"]
+            model_options = args["model_options"].copy()
+            x = args["input"]
+
+            if scale == 0:
+                return cfg_result
+
+            # Replace Self-attention with PAG
+            model_options = comfy.model_patcher.set_model_options_patch_replace(model_options, perturbed_attention, "attn1", unet_block, unet_block_id)
+            (pag,) = comfy.samplers.calc_cond_batch(model, [cond], x, sigma, model_options)
+
+            return cfg_result + (cond_pred - pag) * scale
+
+        m.set_model_sampler_post_cfg_function(post_cfg_function)
+
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    PerturbedAttentionGuidance,
+]

comfy_extras/v3/nodes_perpneg.py

@@ -0,0 +1,114 @@
+from __future__ import annotations
+
+import math
+
+import torch
+
+import comfy.model_management
+import comfy.sampler_helpers
+import comfy.samplers
+import comfy.utils
+import node_helpers
+from comfy_api.latest import io
+
+
+def perp_neg(x, noise_pred_pos, noise_pred_neg, noise_pred_nocond, neg_scale, cond_scale):
+    pos = noise_pred_pos - noise_pred_nocond
+    neg = noise_pred_neg - noise_pred_nocond
+
+    perp = neg - ((torch.mul(neg, pos).sum())/(torch.norm(pos)**2)) * pos
+    perp_neg = perp * neg_scale
+    return noise_pred_nocond + cond_scale*(pos - perp_neg)
+
+
+class Guider_PerpNeg(comfy.samplers.CFGGuider):
+    def set_conds(self, positive, negative, empty_negative_prompt):
+        empty_negative_prompt = node_helpers.conditioning_set_values(empty_negative_prompt, {"prompt_type": "negative"})
+        self.inner_set_conds({"positive": positive, "empty_negative_prompt": empty_negative_prompt, "negative": negative})
+
+    def set_cfg(self, cfg, neg_scale):
+        self.cfg = cfg
+        self.neg_scale = neg_scale
+
+    def predict_noise(self, x, timestep, model_options={}, seed=None):
+        # in CFGGuider.predict_noise, we call sampling_function(), which uses cfg_function() to compute pos & neg
+        # but we'd rather do a single batch of sampling pos, neg, and empty, so we call calc_cond_batch([pos,neg,empty]) directly
+
+        positive_cond = self.conds.get("positive", None)
+        negative_cond = self.conds.get("negative", None)
+        empty_cond = self.conds.get("empty_negative_prompt", None)
+
+        if not model_options.get("disable_cfg1_optimization", False):
+            if math.isclose(self.neg_scale, 0.0):
+                negative_cond = None
+                if math.isclose(self.cfg, 1.0):
+                    empty_cond = None
+
+        conds = [positive_cond, negative_cond, empty_cond]
+
+        out = comfy.samplers.calc_cond_batch(self.inner_model, conds, x, timestep, model_options)
+
+        # Apply pre_cfg_functions since sampling_function() is skipped
+        for fn in model_options.get("sampler_pre_cfg_function", []):
+            args = {"conds":conds, "conds_out": out, "cond_scale": self.cfg, "timestep": timestep,
+                    "input": x, "sigma": timestep, "model": self.inner_model, "model_options": model_options}
+            out = fn(args)
+
+        noise_pred_pos, noise_pred_neg, noise_pred_empty = out
+        cfg_result = perp_neg(x, noise_pred_pos, noise_pred_neg, noise_pred_empty, self.neg_scale, self.cfg)
+
+        # normally this would be done in cfg_function, but we skipped
+        # that for efficiency: we can compute the noise predictions in
+        # a single call to calc_cond_batch() (rather than two)
+        # so we replicate the hook here
+        for fn in model_options.get("sampler_post_cfg_function", []):
+            args = {
+                "denoised": cfg_result,
+                "cond": positive_cond,
+                "uncond": negative_cond,
+                "cond_scale": self.cfg,
+                "model": self.inner_model,
+                "uncond_denoised": noise_pred_neg,
+                "cond_denoised": noise_pred_pos,
+                "sigma": timestep,
+                "model_options": model_options,
+                "input": x,
+                # not in the original call in samplers.py:cfg_function, but made available for future hooks
+                "empty_cond": empty_cond,
+                "empty_cond_denoised": noise_pred_empty,}
+            cfg_result = fn(args)
+
+        return cfg_result
+
+
+class PerpNegGuider(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PerpNegGuider_V3",
+            category="_for_testing",
+            inputs=[
+                io.Model.Input("model"),
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Conditioning.Input("empty_conditioning"),
+                io.Float.Input("cfg", default=8.0, min=0.0, max=100.0, step=0.1, round=0.01),
+                io.Float.Input("neg_scale", default=1.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.Guider.Output(),
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model, positive, negative, empty_conditioning, cfg, neg_scale):
+        guider = Guider_PerpNeg(model)
+        guider.set_conds(positive, negative, empty_conditioning)
+        guider.set_cfg(cfg, neg_scale)
+        return io.NodeOutput(guider)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    PerpNegGuider,
+]

comfy_extras/v3/nodes_photomaker.py

@@ -0,0 +1,205 @@
+from __future__ import annotations
+
+import torch
+import torch.nn as nn
+
+import comfy.clip_model
+import comfy.clip_vision
+import comfy.model_management
+import comfy.ops
+import comfy.utils
+import folder_paths
+from comfy_api.latest import io
+
+# code for model from:
+# https://github.com/TencentARC/PhotoMaker/blob/main/photomaker/model.py under Apache License Version 2.0
+VISION_CONFIG_DICT = {
+    "hidden_size": 1024,
+    "image_size": 224,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768,
+    "hidden_act": "quick_gelu",
+    "model_type": "clip_vision_model",
+}
+
+class MLP(nn.Module):
+    def __init__(self, in_dim, out_dim, hidden_dim, use_residual=True, operations=comfy.ops):
+        super().__init__()
+        if use_residual:
+            assert in_dim == out_dim
+        self.layernorm = operations.LayerNorm(in_dim)
+        self.fc1 = operations.Linear(in_dim, hidden_dim)
+        self.fc2 = operations.Linear(hidden_dim, out_dim)
+        self.use_residual = use_residual
+        self.act_fn = nn.GELU()
+
+    def forward(self, x):
+        residual = x
+        x = self.layernorm(x)
+        x = self.fc1(x)
+        x = self.act_fn(x)
+        x = self.fc2(x)
+        if self.use_residual:
+            x = x + residual
+        return x
+
+
+class FuseModule(nn.Module):
+    def __init__(self, embed_dim, operations):
+        super().__init__()
+        self.mlp1 = MLP(embed_dim * 2, embed_dim, embed_dim, use_residual=False, operations=operations)
+        self.mlp2 = MLP(embed_dim, embed_dim, embed_dim, use_residual=True, operations=operations)
+        self.layer_norm = operations.LayerNorm(embed_dim)
+
+    def fuse_fn(self, prompt_embeds, id_embeds):
+        stacked_id_embeds = torch.cat([prompt_embeds, id_embeds], dim=-1)
+        stacked_id_embeds = self.mlp1(stacked_id_embeds) + prompt_embeds
+        stacked_id_embeds = self.mlp2(stacked_id_embeds)
+        stacked_id_embeds = self.layer_norm(stacked_id_embeds)
+        return stacked_id_embeds
+
+    def forward(
+        self,
+        prompt_embeds,
+        id_embeds,
+        class_tokens_mask,
+    ) -> torch.Tensor:
+        # id_embeds shape: [b, max_num_inputs, 1, 2048]
+        id_embeds = id_embeds.to(prompt_embeds.dtype)
+        num_inputs = class_tokens_mask.sum().unsqueeze(0) # TODO: check for training case
+        batch_size, max_num_inputs = id_embeds.shape[:2]
+        # seq_length: 77
+        seq_length = prompt_embeds.shape[1]
+        # flat_id_embeds shape: [b*max_num_inputs, 1, 2048]
+        flat_id_embeds = id_embeds.view(
+            -1, id_embeds.shape[-2], id_embeds.shape[-1]
+        )
+        # valid_id_mask [b*max_num_inputs]
+        valid_id_mask = (
+            torch.arange(max_num_inputs, device=flat_id_embeds.device)[None, :]
+            < num_inputs[:, None]
+        )
+        valid_id_embeds = flat_id_embeds[valid_id_mask.flatten()]
+
+        prompt_embeds = prompt_embeds.view(-1, prompt_embeds.shape[-1])
+        class_tokens_mask = class_tokens_mask.view(-1)
+        valid_id_embeds = valid_id_embeds.view(-1, valid_id_embeds.shape[-1])
+        # slice out the image token embeddings
+        image_token_embeds = prompt_embeds[class_tokens_mask]
+        stacked_id_embeds = self.fuse_fn(image_token_embeds, valid_id_embeds)
+        assert class_tokens_mask.sum() == stacked_id_embeds.shape[0], f"{class_tokens_mask.sum()} != {stacked_id_embeds.shape[0]}"
+        prompt_embeds.masked_scatter_(class_tokens_mask[:, None], stacked_id_embeds.to(prompt_embeds.dtype))
+        return prompt_embeds.view(batch_size, seq_length, -1)
+
+
+class PhotoMakerIDEncoder(comfy.clip_model.CLIPVisionModelProjection):
+    def __init__(self):
+        self.load_device = comfy.model_management.text_encoder_device()
+        offload_device = comfy.model_management.text_encoder_offload_device()
+        dtype = comfy.model_management.text_encoder_dtype(self.load_device)
+
+        super().__init__(VISION_CONFIG_DICT, dtype, offload_device, comfy.ops.manual_cast)
+        self.visual_projection_2 = comfy.ops.manual_cast.Linear(1024, 1280, bias=False)
+        self.fuse_module = FuseModule(2048, comfy.ops.manual_cast)
+
+    def forward(self, id_pixel_values, prompt_embeds, class_tokens_mask):
+        b, num_inputs, c, h, w = id_pixel_values.shape
+        id_pixel_values = id_pixel_values.view(b * num_inputs, c, h, w)
+
+        shared_id_embeds = self.vision_model(id_pixel_values)[2]
+        id_embeds = self.visual_projection(shared_id_embeds)
+        id_embeds_2 = self.visual_projection_2(shared_id_embeds)
+
+        id_embeds = id_embeds.view(b, num_inputs, 1, -1)
+        id_embeds_2 = id_embeds_2.view(b, num_inputs, 1, -1)
+
+        id_embeds = torch.cat((id_embeds, id_embeds_2), dim=-1)
+        return self.fuse_module(prompt_embeds, id_embeds, class_tokens_mask)
+
+
+class PhotoMakerLoader(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PhotoMakerLoader_V3",
+            category="_for_testing/photomaker",
+            inputs=[
+                io.Combo.Input("photomaker_model_name", options=folder_paths.get_filename_list("photomaker")),
+            ],
+            outputs=[
+                io.Photomaker.Output(),
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, photomaker_model_name):
+        photomaker_model_path = folder_paths.get_full_path_or_raise("photomaker", photomaker_model_name)
+        photomaker_model = PhotoMakerIDEncoder()
+        data = comfy.utils.load_torch_file(photomaker_model_path, safe_load=True)
+        if "id_encoder" in data:
+            data = data["id_encoder"]
+        photomaker_model.load_state_dict(data)
+        return io.NodeOutput(photomaker_model)
+
+
+class PhotoMakerEncode(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PhotoMakerEncode_V3",
+            category="_for_testing/photomaker",
+            inputs=[
+                io.Photomaker.Input("photomaker"),
+                io.Image.Input("image"),
+                io.Clip.Input("clip"),
+                io.String.Input("text", multiline=True, dynamic_prompts=True, default="photograph of photomaker"),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, photomaker, image, clip, text):
+        special_token = "photomaker"
+        pixel_values = comfy.clip_vision.clip_preprocess(image.to(photomaker.load_device)).float()
+        try:
+            index = text.split(" ").index(special_token) + 1
+        except ValueError:
+            index = -1
+        tokens = clip.tokenize(text, return_word_ids=True)
+        out_tokens = {}
+        for k in tokens:
+            out_tokens[k] = []
+            for t in tokens[k]:
+                f = list(filter(lambda x: x[2] != index, t))
+                while len(f) < len(t):
+                    f.append(t[-1])
+                out_tokens[k].append(f)
+
+        cond, pooled = clip.encode_from_tokens(out_tokens, return_pooled=True)
+
+        if index > 0:
+            token_index = index - 1
+            num_id_images = 1
+            class_tokens_mask = [True if token_index <= i < token_index+num_id_images else False for i in range(77)]
+            out = photomaker(
+                id_pixel_values=pixel_values.unsqueeze(0), prompt_embeds=cond.to(photomaker.load_device),
+                class_tokens_mask=torch.tensor(class_tokens_mask, dtype=torch.bool, device=photomaker.load_device).unsqueeze(0),
+            )
+        else:
+            out = cond
+
+        return io.NodeOutput([[out, {"pooled_output": pooled}]])
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    PhotoMakerEncode,
+    PhotoMakerLoader,
+]

comfy_extras/v3/nodes_pixart.py

@@ -0,0 +1,33 @@
+from __future__ import annotations
+
+import nodes
+from comfy_api.latest import io
+
+
+class CLIPTextEncodePixArtAlpha(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodePixArtAlpha_V3",
+            category="advanced/conditioning",
+            description="Encodes text and sets the resolution conditioning for PixArt Alpha. Does not apply to PixArt Sigma.",
+            inputs=[
+                io.Int.Input("width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.Int.Input("height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+                io.String.Input("text", multiline=True, dynamic_prompts=True),
+                io.Clip.Input("clip"),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, width, height, text, clip):
+        tokens = clip.tokenize(text)
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens, add_dict={"width": width, "height": height}))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CLIPTextEncodePixArtAlpha,
+]

comfy_extras/v3/nodes_post_processing.py

@@ -0,0 +1,255 @@
+from __future__ import annotations
+
+import math
+
+import numpy as np
+import torch
+import torch.nn.functional as F
+from PIL import Image
+
+import comfy.model_management
+import comfy.utils
+import node_helpers
+from comfy_api.latest import io
+
+
+class Blend(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageBlend_V3",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image1"),
+                io.Image.Input("image2"),
+                io.Float.Input("blend_factor", default=0.5, min=0.0, max=1.0, step=0.01),
+                io.Combo.Input("blend_mode", options=["normal", "multiply", "screen", "overlay", "soft_light", "difference"]),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image1: torch.Tensor, image2: torch.Tensor, blend_factor: float, blend_mode: str):
+        image1, image2 = node_helpers.image_alpha_fix(image1, image2)
+        image2 = image2.to(image1.device)
+        if image1.shape != image2.shape:
+            image2 = image2.permute(0, 3, 1, 2)
+            image2 = comfy.utils.common_upscale(
+                image2, image1.shape[2], image1.shape[1], upscale_method="bicubic", crop="center"
+            )
+            image2 = image2.permute(0, 2, 3, 1)
+
+        blended_image = cls.blend_mode(image1, image2, blend_mode)
+        blended_image = image1 * (1 - blend_factor) + blended_image * blend_factor
+        blended_image = torch.clamp(blended_image, 0, 1)
+        return io.NodeOutput(blended_image)
+
+    @classmethod
+    def blend_mode(cls, img1, img2, mode):
+        if mode == "normal":
+            return img2
+        elif mode == "multiply":
+            return img1 * img2
+        elif mode == "screen":
+            return 1 - (1 - img1) * (1 - img2)
+        elif mode == "overlay":
+            return torch.where(img1 <= 0.5, 2 * img1 * img2, 1 - 2 * (1 - img1) * (1 - img2))
+        elif mode == "soft_light":
+            return torch.where(img2 <= 0.5, img1 - (1 - 2 * img2) * img1 * (1 - img1), img1 + (2 * img2 - 1) * (cls.g(img1) - img1))
+        elif mode == "difference":
+            return img1 - img2
+        raise ValueError(f"Unsupported blend mode: {mode}")
+
+    @classmethod
+    def g(cls, x):
+        return torch.where(x <= 0.25, ((16 * x - 12) * x + 4) * x, torch.sqrt(x))
+
+
+class Blur(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageBlur_V3",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("blur_radius", default=1, min=1, max=31, step=1),
+                io.Float.Input("sigma", default=1.0, min=0.1, max=10.0, step=0.1),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image: torch.Tensor, blur_radius: int, sigma: float):
+        if blur_radius == 0:
+            return io.NodeOutput(image)
+
+        image = image.to(comfy.model_management.get_torch_device())
+        batch_size, height, width, channels = image.shape
+
+        kernel_size = blur_radius * 2 + 1
+        kernel = gaussian_kernel(kernel_size, sigma, device=image.device).repeat(channels, 1, 1).unsqueeze(1)
+
+        image = image.permute(0, 3, 1, 2) # Torch wants (B, C, H, W) we use (B, H, W, C)
+        padded_image = F.pad(image, (blur_radius,blur_radius,blur_radius,blur_radius), "reflect")
+        blurred = F.conv2d(padded_image, kernel, padding=kernel_size // 2, groups=channels)[:,:,blur_radius:-blur_radius, blur_radius:-blur_radius]
+        blurred = blurred.permute(0, 2, 3, 1)
+
+        return io.NodeOutput(blurred.to(comfy.model_management.intermediate_device()))
+
+
+def gaussian_kernel(kernel_size: int, sigma: float, device=None):
+    x, y = torch.meshgrid(torch.linspace(-1, 1, kernel_size, device=device), torch.linspace(-1, 1, kernel_size, device=device), indexing="ij")
+    d = torch.sqrt(x * x + y * y)
+    g = torch.exp(-(d * d) / (2.0 * sigma * sigma))
+    return g / g.sum()
+
+
+class Quantize(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageQuantize_V3",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("colors", default=256, min=1, max=256, step=1),
+                io.Combo.Input("dither", options=["none", "floyd-steinberg", "bayer-2", "bayer-4", "bayer-8", "bayer-16"]),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
+
+    @staticmethod
+    def bayer(im, pal_im, order):
+        def normalized_bayer_matrix(n):
+            if n == 0:
+                return np.zeros((1,1), "float32")
+            q = 4 ** n
+            m = q * normalized_bayer_matrix(n - 1)
+            return np.bmat(((m-1.5, m+0.5), (m+1.5, m-0.5))) / q
+
+        num_colors = len(pal_im.getpalette()) // 3
+        spread = 2 * 256 / num_colors
+        bayer_n = int(math.log2(order))
+        bayer_matrix = torch.from_numpy(spread * normalized_bayer_matrix(bayer_n) + 0.5)
+
+        result = torch.from_numpy(np.array(im).astype(np.float32))
+        tw = math.ceil(result.shape[0] / bayer_matrix.shape[0])
+        th = math.ceil(result.shape[1] / bayer_matrix.shape[1])
+        tiled_matrix = bayer_matrix.tile(tw, th).unsqueeze(-1)
+        result.add_(tiled_matrix[:result.shape[0],:result.shape[1]]).clamp_(0, 255)
+        result = result.to(dtype=torch.uint8)
+
+        im = Image.fromarray(result.cpu().numpy())
+        return im.quantize(palette=pal_im, dither=Image.Dither.NONE)
+
+    @classmethod
+    def execute(cls, image: torch.Tensor, colors: int, dither: str):
+        batch_size, height, width, _ = image.shape
+        result = torch.zeros_like(image)
+
+        for b in range(batch_size):
+            im = Image.fromarray((image[b] * 255).to(torch.uint8).numpy(), mode='RGB')
+
+            pal_im = im.quantize(colors=colors) # Required as described in https://github.com/python-pillow/Pillow/issues/5836
+
+            if dither == "none":
+                quantized_image = im.quantize(palette=pal_im, dither=Image.Dither.NONE)
+            elif dither == "floyd-steinberg":
+                quantized_image = im.quantize(palette=pal_im, dither=Image.Dither.FLOYDSTEINBERG)
+            elif dither.startswith("bayer"):
+                order = int(dither.split('-')[-1])
+                quantized_image = cls.bayer(im, pal_im, order)
+
+            quantized_array = torch.tensor(np.array(quantized_image.convert("RGB"))).float() / 255
+            result[b] = quantized_array
+
+        return io.NodeOutput(result)
+
+
+class Sharpen(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageSharpen_V3",
+            category="image/postprocessing",
+            inputs=[
+                io.Image.Input("image"),
+                io.Int.Input("sharpen_radius", default=1, min=1, max=31, step=1),
+                io.Float.Input("sigma", default=1.0, min=0.1, max=10.0, step=0.01),
+                io.Float.Input("alpha", default=1.0, min=0.0, max=5.0, step=0.01),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image: torch.Tensor, sharpen_radius: int, sigma:float, alpha: float):
+        if sharpen_radius == 0:
+            return io.NodeOutput(image)
+
+        batch_size, height, width, channels = image.shape
+        image = image.to(comfy.model_management.get_torch_device())
+
+        kernel_size = sharpen_radius * 2 + 1
+        kernel = gaussian_kernel(kernel_size, sigma, device=image.device) * -(alpha*10)
+        center = kernel_size // 2
+        kernel[center, center] = kernel[center, center] - kernel.sum() + 1.0
+        kernel = kernel.repeat(channels, 1, 1).unsqueeze(1)
+
+        tensor_image = image.permute(0, 3, 1, 2) # Torch wants (B, C, H, W) we use (B, H, W, C)
+        tensor_image = F.pad(tensor_image, (sharpen_radius,sharpen_radius,sharpen_radius,sharpen_radius), "reflect")
+        sharpened = F.conv2d(tensor_image, kernel, padding=center, groups=channels)[:,:,sharpen_radius:-sharpen_radius, sharpen_radius:-sharpen_radius]
+        sharpened = sharpened.permute(0, 2, 3, 1)
+
+        result = torch.clamp(sharpened, 0, 1)
+
+        return io.NodeOutput(result.to(comfy.model_management.intermediate_device()))
+
+
+class ImageScaleToTotalPixels(io.ComfyNode):
+    upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "lanczos"]
+    crop_methods = ["disabled", "center"]
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="ImageScaleToTotalPixels_V3",
+            category="image/upscaling",
+            inputs=[
+                io.Image.Input("image"),
+                io.Combo.Input("upscale_method", options=cls.upscale_methods),
+                io.Float.Input("megapixels", default=1.0, min=0.01, max=16.0, step=0.01),
+            ],
+            outputs=[
+                io.Image.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image, upscale_method, megapixels):
+        samples = image.movedim(-1,1)
+        total = int(megapixels * 1024 * 1024)
+
+        scale_by = math.sqrt(total / (samples.shape[3] * samples.shape[2]))
+        width = round(samples.shape[3] * scale_by)
+        height = round(samples.shape[2] * scale_by)
+
+        s = comfy.utils.common_upscale(samples, width, height, upscale_method, "disabled")
+        return io.NodeOutput(s.movedim(1,-1))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    Blend,
+    Blur,
+    ImageScaleToTotalPixels,
+    Quantize,
+    Sharpen,
+]

comfy_extras/v3/nodes_preview_any.py

@@ -0,0 +1,47 @@
+from __future__ import annotations
+
+import json
+
+from comfy_api.latest import io, ui
+
+
+class PreviewAny(io.ComfyNode):
+    """Originally implement from https://github.com/rgthree/rgthree-comfy/blob/main/py/display_any.py
+
+    upstream requested in https://github.com/Kosinkadink/rfcs/blob/main/rfcs/0000-corenodes.md#preview-nodes"""
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PreviewAny_V3",  # frontend expects "PreviewAny" to work
+            display_name="Preview Any _V3",  # frontend ignores "display_name" for this node
+            description="Preview any type of data by converting it to a readable text format.",
+            category="utils",
+            inputs=[
+                io.AnyType.Input("source"),  # TODO: does not work currently, as `io.AnyType` does not define __ne__
+            ],
+            is_output_node=True,
+        )
+
+    @classmethod
+    def execute(cls, source=None) -> io.NodeOutput:
+        value = "None"
+        if isinstance(source, str):
+            value = source
+        elif isinstance(source, (int, float, bool)):
+            value = str(source)
+        elif source is not None:
+            try:
+                value = json.dumps(source)
+            except Exception:
+                try:
+                    value = str(source)
+                except Exception:
+                    value = "source exists, but could not be serialized."
+
+        return io.NodeOutput(ui=ui.PreviewText(value))
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    PreviewAny,
+]

comfy_extras/v3/nodes_primitive.py

@@ -0,0 +1,104 @@
+from __future__ import annotations
+
+import sys
+
+from comfy_api.latest import io
+
+
+class String(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PrimitiveString_V3",
+            display_name="String _V3",
+            category="utils/primitive",
+            inputs=[
+                io.String.Input("value"),
+            ],
+            outputs=[io.String.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: str) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+class StringMultiline(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PrimitiveStringMultiline_V3",
+            display_name="String (Multiline) _V3",
+            category="utils/primitive",
+            inputs=[
+                io.String.Input("value", multiline=True),
+            ],
+            outputs=[io.String.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: str) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+class Int(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PrimitiveInt_V3",
+            display_name="Int _V3",
+            category="utils/primitive",
+            inputs=[
+                io.Int.Input("value", min=-sys.maxsize, max=sys.maxsize, control_after_generate=True),
+            ],
+            outputs=[io.Int.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: int) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+class Float(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PrimitiveFloat_V3",
+            display_name="Float _V3",
+            category="utils/primitive",
+            inputs=[
+                io.Float.Input("value", min=-sys.maxsize, max=sys.maxsize),
+            ],
+            outputs=[io.Float.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: float) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+class Boolean(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="PrimitiveBoolean_V3",
+            display_name="Boolean _V3",
+            category="utils/primitive",
+            inputs=[
+                io.Boolean.Input("value"),
+            ],
+            outputs=[io.Boolean.Output()],
+        )
+
+    @classmethod
+    def execute(cls, value: bool) -> io.NodeOutput:
+        return io.NodeOutput(value)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    String,
+    StringMultiline,
+    Int,
+    Float,
+    Boolean,
+]

comfy_extras/v3/nodes_rebatch.py

@@ -0,0 +1,148 @@
+from __future__ import annotations
+
+import torch
+
+from comfy_api.latest import io
+
+
+class ImageRebatch(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RebatchImages_V3",
+            display_name="Rebatch Images _V3",
+            category="image/batch",
+            is_input_list=True,
+            inputs=[
+                io.Image.Input("images"),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Image.Output(display_name="IMAGE", is_output_list=True),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, images, batch_size):
+        batch_size = batch_size[0]
+
+        output_list = []
+        all_images = []
+        for img in images:
+            for i in range(img.shape[0]):
+                all_images.append(img[i:i+1])
+
+        for i in range(0, len(all_images), batch_size):
+            output_list.append(torch.cat(all_images[i:i+batch_size], dim=0))
+
+        return io.NodeOutput(output_list)
+
+
+class LatentRebatch(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RebatchLatents_V3",
+            display_name="Rebatch Latents _V3",
+            category="latent/batch",
+            is_input_list=True,
+            inputs=[
+                io.Latent.Input("latents"),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Latent.Output(is_output_list=True),
+            ],
+        )
+
+    @staticmethod
+    def get_batch(latents, list_ind, offset):
+        """prepare a batch out of the list of latents"""
+        samples = latents[list_ind]['samples']
+        shape = samples.shape
+        mask = latents[list_ind]['noise_mask'] if 'noise_mask' in latents[list_ind] else torch.ones((shape[0], 1, shape[2]*8, shape[3]*8), device='cpu')
+        if mask.shape[-1] != shape[-1] * 8 or mask.shape[-2] != shape[-2]:
+            torch.nn.functional.interpolate(mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])), size=(shape[-2]*8, shape[-1]*8), mode="bilinear")
+        if mask.shape[0] < samples.shape[0]:
+            mask = mask.repeat((shape[0] - 1) // mask.shape[0] + 1, 1, 1, 1)[:shape[0]]
+        if 'batch_index' in latents[list_ind]:
+            batch_inds = latents[list_ind]['batch_index']
+        else:
+            batch_inds = [x+offset for x in range(shape[0])]
+        return samples, mask, batch_inds
+
+    @staticmethod
+    def get_slices(indexable, num, batch_size):
+        """divides an indexable object into num slices of length batch_size, and a remainder"""
+        slices = []
+        for i in range(num):
+            slices.append(indexable[i*batch_size:(i+1)*batch_size])
+        if num * batch_size < len(indexable):
+            return slices, indexable[num * batch_size:]
+        else:
+            return slices, None
+
+    @staticmethod
+    def slice_batch(batch, num, batch_size):
+        result = [LatentRebatch.get_slices(x, num, batch_size) for x in batch]
+        return list(zip(*result))
+
+    @staticmethod
+    def cat_batch(batch1, batch2):
+        if batch1[0] is None:
+            return batch2
+        result = [torch.cat((b1, b2)) if torch.is_tensor(b1) else b1 + b2 for b1, b2 in zip(batch1, batch2)]
+        return result
+
+    @classmethod
+    def execute(cls, latents, batch_size):
+        batch_size = batch_size[0]
+
+        output_list = []
+        current_batch = (None, None, None)
+        processed = 0
+
+        for i in range(len(latents)):
+            # fetch new entry of list
+            #samples, masks, indices = self.get_batch(latents, i)
+            next_batch = cls.get_batch(latents, i, processed)
+            processed += len(next_batch[2])
+            # set to current if current is None
+            if current_batch[0] is None:
+                current_batch = next_batch
+            # add previous to list if dimensions do not match
+            elif next_batch[0].shape[-1] != current_batch[0].shape[-1] or next_batch[0].shape[-2] != current_batch[0].shape[-2]:
+                sliced, _ = cls.slice_batch(current_batch, 1, batch_size)
+                output_list.append({'samples': sliced[0][0], 'noise_mask': sliced[1][0], 'batch_index': sliced[2][0]})
+                current_batch = next_batch
+            # cat if everything checks out
+            else:
+                current_batch = cls.cat_batch(current_batch, next_batch)
+
+            # add to list if dimensions gone above target batch size
+            if current_batch[0].shape[0] > batch_size:
+                num = current_batch[0].shape[0] // batch_size
+                sliced, remainder = cls.slice_batch(current_batch, num, batch_size)
+
+                for i in range(num):
+                    output_list.append({'samples': sliced[0][i], 'noise_mask': sliced[1][i], 'batch_index': sliced[2][i]})
+
+                current_batch = remainder
+
+        #add remainder
+        if current_batch[0] is not None:
+            sliced, _ = cls.slice_batch(current_batch, 1, batch_size)
+            output_list.append({'samples': sliced[0][0], 'noise_mask': sliced[1][0], 'batch_index': sliced[2][0]})
+
+        #get rid of empty masks
+        for s in output_list:
+            if s['noise_mask'].mean() == 1.0:
+                del s['noise_mask']
+
+        return io.NodeOutput(output_list)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    ImageRebatch,
+    LatentRebatch,
+]

comfy_extras/v3/nodes_sag.py

@@ -0,0 +1,191 @@
+from __future__ import annotations
+
+import math
+
+import torch
+import torch.nn.functional as F
+from einops import rearrange, repeat
+from torch import einsum
+
+import comfy.samplers
+from comfy.ldm.modules.attention import optimized_attention
+from comfy_api.latest import io
+
+
+# from comfy/ldm/modules/attention.py
+# but modified to return attention scores as well as output
+def attention_basic_with_sim(q, k, v, heads, mask=None, attn_precision=None):
+    b, _, dim_head = q.shape
+    dim_head //= heads
+    scale = dim_head ** -0.5
+
+    h = heads
+    q, k, v = map(
+        lambda t: t.unsqueeze(3)
+        .reshape(b, -1, heads, dim_head)
+        .permute(0, 2, 1, 3)
+        .reshape(b * heads, -1, dim_head)
+        .contiguous(),
+        (q, k, v),
+    )
+
+    # force cast to fp32 to avoid overflowing
+    if attn_precision == torch.float32:
+        sim = einsum('b i d, b j d -> b i j', q.float(), k.float()) * scale
+    else:
+        sim = einsum('b i d, b j d -> b i j', q, k) * scale
+
+    del q, k
+
+    if mask is not None:
+        mask = rearrange(mask, 'b ... -> b (...)')
+        max_neg_value = -torch.finfo(sim.dtype).max
+        mask = repeat(mask, 'b j -> (b h) () j', h=h)
+        sim.masked_fill_(~mask, max_neg_value)
+
+    # attention, what we cannot get enough of
+    sim = sim.softmax(dim=-1)
+
+    out = einsum('b i j, b j d -> b i d', sim.to(v.dtype), v)
+    out = (
+        out.unsqueeze(0)
+        .reshape(b, heads, -1, dim_head)
+        .permute(0, 2, 1, 3)
+        .reshape(b, -1, heads * dim_head)
+    )
+    return out, sim
+
+
+def create_blur_map(x0, attn, sigma=3.0, threshold=1.0):
+    # reshape and GAP the attention map
+    _, hw1, hw2 = attn.shape
+    b, _, lh, lw = x0.shape
+    attn = attn.reshape(b, -1, hw1, hw2)
+    # Global Average Pool
+    mask = attn.mean(1, keepdim=False).sum(1, keepdim=False) > threshold
+
+    total = mask.shape[-1]
+    x = round(math.sqrt((lh / lw) * total))
+    xx = None
+    for i in range(0, math.floor(math.sqrt(total) / 2)):
+        for j in [(x + i), max(1, x - i)]:
+            if total % j == 0:
+                xx = j
+                break
+        if xx is not None:
+            break
+
+    x = xx
+    y = total // x
+
+    # Reshape
+    mask = (
+        mask.reshape(b, x, y)
+        .unsqueeze(1)
+        .type(attn.dtype)
+    )
+    # Upsample
+    mask = F.interpolate(mask, (lh, lw))
+
+    blurred = gaussian_blur_2d(x0, kernel_size=9, sigma=sigma)
+    blurred = blurred * mask + x0 * (1 - mask)
+    return blurred
+
+
+def gaussian_blur_2d(img, kernel_size, sigma):
+    ksize_half = (kernel_size - 1) * 0.5
+
+    x = torch.linspace(-ksize_half, ksize_half, steps=kernel_size)
+
+    pdf = torch.exp(-0.5 * (x / sigma).pow(2))
+
+    x_kernel = pdf / pdf.sum()
+    x_kernel = x_kernel.to(device=img.device, dtype=img.dtype)
+
+    kernel2d = torch.mm(x_kernel[:, None], x_kernel[None, :])
+    kernel2d = kernel2d.expand(img.shape[-3], 1, kernel2d.shape[0], kernel2d.shape[1])
+
+    padding = [kernel_size // 2, kernel_size // 2, kernel_size // 2, kernel_size // 2]
+
+    img = F.pad(img, padding, mode="reflect")
+    return F.conv2d(img, kernel2d, groups=img.shape[-3])
+
+
+class SelfAttentionGuidance(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SelfAttentionGuidance_V3",
+            display_name="Self-Attention Guidance _V3",
+            category="_for_testing",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("scale", default=0.5, min=-2.0, max=5.0, step=0.01),
+                io.Float.Input("blur_sigma", default=2.0, min=0.0, max=10.0, step=0.1),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model, scale, blur_sigma):
+        m = model.clone()
+
+        attn_scores = None
+
+        # TODO: make this work properly with chunked batches
+        #       currently, we can only save the attn from one UNet call
+        def attn_and_record(q, k, v, extra_options):
+            nonlocal attn_scores
+            # if uncond, save the attention scores
+            heads = extra_options["n_heads"]
+            cond_or_uncond = extra_options["cond_or_uncond"]
+            b = q.shape[0] // len(cond_or_uncond)
+            if 1 in cond_or_uncond:
+                uncond_index = cond_or_uncond.index(1)
+                # do the entire attention operation, but save the attention scores to attn_scores
+                (out, sim) = attention_basic_with_sim(q, k, v, heads=heads, attn_precision=extra_options["attn_precision"])
+                # when using a higher batch size, I BELIEVE the result batch dimension is [uc1, ... ucn, c1, ... cn]
+                n_slices = heads * b
+                attn_scores = sim[n_slices * uncond_index:n_slices * (uncond_index+1)]
+                return out
+            else:
+                return optimized_attention(q, k, v, heads=heads, attn_precision=extra_options["attn_precision"])
+
+        def post_cfg_function(args):
+            nonlocal attn_scores
+            uncond_attn = attn_scores
+
+            sag_scale = scale
+            sag_sigma = blur_sigma
+            sag_threshold = 1.0
+            model = args["model"]
+            uncond_pred = args["uncond_denoised"]
+            uncond = args["uncond"]
+            cfg_result = args["denoised"]
+            sigma = args["sigma"]
+            model_options = args["model_options"]
+            x = args["input"]
+            if min(cfg_result.shape[2:]) <= 4: #skip when too small to add padding
+                return cfg_result
+
+            # create the adversarially blurred image
+            degraded = create_blur_map(uncond_pred, uncond_attn, sag_sigma, sag_threshold)
+            degraded_noised = degraded + x - uncond_pred
+            # call into the UNet
+            (sag,) = comfy.samplers.calc_cond_batch(model, [uncond], degraded_noised, sigma, model_options)
+            return cfg_result + (degraded - sag) * sag_scale
+
+        m.set_model_sampler_post_cfg_function(post_cfg_function, disable_cfg1_optimization=True)
+
+        # from diffusers:
+        # unet.mid_block.attentions[0].transformer_blocks[0].attn1.patch
+        m.set_model_attn1_replace(attn_and_record, "middle", 0, 0)
+
+        return io.NodeOutput(m)
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    SelfAttentionGuidance,
+]

comfy_extras/v3/nodes_sd3.py

@@ -0,0 +1,145 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.model_management
+import comfy.sd
+import folder_paths
+import nodes
+from comfy_api.latest import io
+from comfy_extras.v3.nodes_slg import SkipLayerGuidanceDiT
+
+
+class TripleCLIPLoader(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="TripleCLIPLoader_V3",
+            category="advanced/loaders",
+            description="[Recipes]\n\nsd3: clip-l, clip-g, t5",
+            inputs=[
+                io.Combo.Input("clip_name1", options=folder_paths.get_filename_list("text_encoders")),
+                io.Combo.Input("clip_name2", options=folder_paths.get_filename_list("text_encoders")),
+                io.Combo.Input("clip_name3", options=folder_paths.get_filename_list("text_encoders")),
+            ],
+            outputs=[
+                io.Clip.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, clip_name1: str, clip_name2: str, clip_name3: str):
+        clip_path1 = folder_paths.get_full_path_or_raise("text_encoders", clip_name1)
+        clip_path2 = folder_paths.get_full_path_or_raise("text_encoders", clip_name2)
+        clip_path3 = folder_paths.get_full_path_or_raise("text_encoders", clip_name3)
+        clip = comfy.sd.load_clip(
+            ckpt_paths=[clip_path1, clip_path2, clip_path3],
+            embedding_directory=folder_paths.get_folder_paths("embeddings"),
+        )
+        return io.NodeOutput(clip)
+
+
+class EmptySD3LatentImage(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="EmptySD3LatentImage_V3",
+            category="latent/sd3",
+            inputs=[
+                io.Int.Input("width", default=1024, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("height", default=1024, min=16, max=nodes.MAX_RESOLUTION, step=16),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Latent.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, width: int, height: int, batch_size=1):
+        latent = torch.zeros(
+            [batch_size, 16, height // 8, width // 8], device=comfy.model_management.intermediate_device()
+        )
+        return io.NodeOutput({"samples":latent})
+
+
+class CLIPTextEncodeSD3(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeSD3_V3",
+            category="advanced/conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("clip_l", multiline=True, dynamic_prompts=True),
+                io.String.Input("clip_g", multiline=True, dynamic_prompts=True),
+                io.String.Input("t5xxl", multiline=True, dynamic_prompts=True),
+                io.Combo.Input("empty_padding", options=["none", "empty_prompt"]),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, clip, clip_l, clip_g, t5xxl, empty_padding: str):
+        no_padding = empty_padding == "none"
+
+        tokens = clip.tokenize(clip_g)
+        if len(clip_g) == 0 and no_padding:
+            tokens["g"] = []
+
+        if len(clip_l) == 0 and no_padding:
+            tokens["l"] = []
+        else:
+            tokens["l"] = clip.tokenize(clip_l)["l"]
+
+        if len(t5xxl) == 0 and no_padding:
+            tokens["t5xxl"] =  []
+        else:
+            tokens["t5xxl"] = clip.tokenize(t5xxl)["t5xxl"]
+        if len(tokens["l"]) != len(tokens["g"]):
+            empty = clip.tokenize("")
+            while len(tokens["l"]) < len(tokens["g"]):
+                tokens["l"] += empty["l"]
+            while len(tokens["l"]) > len(tokens["g"]):
+                tokens["g"] += empty["g"]
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens))
+
+
+class SkipLayerGuidanceSD3(SkipLayerGuidanceDiT):
+    """
+    Enhance guidance towards detailed dtructure by having another set of CFG negative with skipped layers.
+    Inspired by Perturbed Attention Guidance (https://arxiv.org/abs/2403.17377)
+    Experimental implementation by Dango233@StabilityAI.
+    """
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SkipLayerGuidanceSD3_V3",
+            category="advanced/guidance",
+            inputs=[
+                io.Model.Input("model"),
+                io.String.Input("layers", default="7, 8, 9", multiline=False),
+                io.Float.Input("scale", default=3.0, min=0.0, max=10.0, step=0.1),
+                io.Float.Input("start_percent", default=0.01, min=0.0, max=1.0, step=0.001),
+                io.Float.Input("end_percent", default=0.15, min=0.0, max=1.0, step=0.001),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+            is_experimental=True,
+        )
+
+    @classmethod
+    def execute(cls, model, layers: str, scale: float, start_percent: float, end_percent: float):
+        return super().execute(
+            model=model, scale=scale, start_percent=start_percent, end_percent=end_percent, double_layers=layers
+        )
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CLIPTextEncodeSD3,
+    EmptySD3LatentImage,
+    SkipLayerGuidanceSD3,
+    TripleCLIPLoader,
+]

comfy_extras/v3/nodes_sdupscale.py

@@ -0,0 +1,58 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.utils
+from comfy_api.latest import io
+
+
+class SD_4XUpscale_Conditioning(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SD_4XUpscale_Conditioning_V3",
+            category="conditioning/upscale_diffusion",
+            inputs=[
+                io.Image.Input("images"),
+                io.Conditioning.Input("positive"),
+                io.Conditioning.Input("negative"),
+                io.Float.Input("scale_ratio", default=4.0, min=0.0, max=10.0, step=0.01),
+                io.Float.Input("noise_augmentation", default=0.0, min=0.0, max=1.0, step=0.001),
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, images, positive, negative, scale_ratio, noise_augmentation):
+        width = max(1, round(images.shape[-2] * scale_ratio))
+        height = max(1, round(images.shape[-3] * scale_ratio))
+
+        pixels = comfy.utils.common_upscale(
+            (images.movedim(-1,1) * 2.0) - 1.0, width // 4, height // 4, "bilinear", "center"
+        )
+
+        out_cp = []
+        out_cn = []
+
+        for t in positive:
+            n = [t[0], t[1].copy()]
+            n[1]['concat_image'] = pixels
+            n[1]['noise_augmentation'] = noise_augmentation
+            out_cp.append(n)
+
+        for t in negative:
+            n = [t[0], t[1].copy()]
+            n[1]['concat_image'] = pixels
+            n[1]['noise_augmentation'] = noise_augmentation
+            out_cn.append(n)
+
+        latent = torch.zeros([images.shape[0], 4, height // 4, width // 4])
+        return io.NodeOutput(out_cp, out_cn, {"samples":latent})
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    SD_4XUpscale_Conditioning,
+]

comfy_extras/v3/nodes_slg.py

@@ -0,0 +1,173 @@
+from __future__ import annotations
+
+import re
+
+import comfy.model_patcher
+import comfy.samplers
+from comfy_api.latest import io
+
+
+class SkipLayerGuidanceDiT(io.ComfyNode):
+    """
+    Enhance guidance towards detailed dtructure by having another set of CFG negative with skipped layers.
+    Inspired by Perturbed Attention Guidance (https://arxiv.org/abs/2403.17377)
+    Original experimental implementation for SD3 by Dango233@StabilityAI.
+    """
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SkipLayerGuidanceDiT_V3",
+            category="advanced/guidance",
+            description="Generic version of SkipLayerGuidance node that can be used on every DiT model.",
+            is_experimental=True,
+            inputs=[
+                io.Model.Input("model"),
+                io.String.Input("double_layers", default="7, 8, 9"),
+                io.String.Input("single_layers", default="7, 8, 9"),
+                io.Float.Input("scale", default=3.0, min=0.0, max=10.0, step=0.1),
+                io.Float.Input("start_percent", default=0.01, min=0.0, max=1.0, step=0.001),
+                io.Float.Input("end_percent", default=0.15, min=0.0, max=1.0, step=0.001),
+                io.Float.Input("rescaling_scale", default=0.0, min=0.0, max=10.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, scale, start_percent, end_percent, double_layers="", single_layers="", rescaling_scale=0):
+        # check if layer is comma separated integers
+        def skip(args, extra_args):
+            return args
+
+        model_sampling = model.get_model_object("model_sampling")
+        sigma_start = model_sampling.percent_to_sigma(start_percent)
+        sigma_end = model_sampling.percent_to_sigma(end_percent)
+
+        double_layers = re.findall(r"\d+", double_layers)
+        double_layers = [int(i) for i in double_layers]
+
+        single_layers = re.findall(r"\d+", single_layers)
+        single_layers = [int(i) for i in single_layers]
+
+        if len(double_layers) == 0 and len(single_layers) == 0:
+            return io.NodeOutput(model)
+
+        def post_cfg_function(args):
+            model = args["model"]
+            cond_pred = args["cond_denoised"]
+            cond = args["cond"]
+            cfg_result = args["denoised"]
+            sigma = args["sigma"]
+            x = args["input"]
+            model_options = args["model_options"].copy()
+
+            for layer in double_layers:
+                model_options = comfy.model_patcher.set_model_options_patch_replace(
+                    model_options, skip, "dit", "double_block", layer
+                )
+
+            for layer in single_layers:
+                model_options = comfy.model_patcher.set_model_options_patch_replace(
+                    model_options, skip, "dit", "single_block", layer
+                )
+
+            model_sampling.percent_to_sigma(start_percent)
+
+            sigma_ = sigma[0].item()
+            if scale > 0 and sigma_ >= sigma_end and sigma_ <= sigma_start:
+                (slg,) = comfy.samplers.calc_cond_batch(model, [cond], x, sigma, model_options)
+                cfg_result = cfg_result + (cond_pred - slg) * scale
+                if rescaling_scale != 0:
+                    factor = cond_pred.std() / cfg_result.std()
+                    factor = rescaling_scale * factor + (1 - rescaling_scale)
+                    cfg_result *= factor
+
+            return cfg_result
+
+        m = model.clone()
+        m.set_model_sampler_post_cfg_function(post_cfg_function)
+
+        return io.NodeOutput(m)
+
+
+class SkipLayerGuidanceDiTSimple(io.ComfyNode):
+    """Simple version of the SkipLayerGuidanceDiT node that only modifies the uncond pass."""
+
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SkipLayerGuidanceDiTSimple_V3",
+            category="advanced/guidance",
+            description="Simple version of the SkipLayerGuidanceDiT node that only modifies the uncond pass.",
+            is_experimental=True,
+            inputs=[
+                io.Model.Input("model"),
+                io.String.Input("double_layers", default="7, 8, 9"),
+                io.String.Input("single_layers", default="7, 8, 9"),
+                io.Float.Input("start_percent", default=0.0, min=0.0, max=1.0, step=0.001),
+                io.Float.Input("end_percent", default=1.0, min=0.0, max=1.0, step=0.001),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, start_percent, end_percent, double_layers="", single_layers=""):
+        def skip(args, extra_args):
+            return args
+
+        model_sampling = model.get_model_object("model_sampling")
+        sigma_start = model_sampling.percent_to_sigma(start_percent)
+        sigma_end = model_sampling.percent_to_sigma(end_percent)
+
+        double_layers = re.findall(r"\d+", double_layers)
+        double_layers = [int(i) for i in double_layers]
+
+        single_layers = re.findall(r"\d+", single_layers)
+        single_layers = [int(i) for i in single_layers]
+
+        if len(double_layers) == 0 and len(single_layers) == 0:
+            return io.NodeOutput(model)
+
+        def calc_cond_batch_function(args):
+            x = args["input"]
+            model = args["model"]
+            conds = args["conds"]
+            sigma = args["sigma"]
+
+            model_options = args["model_options"]
+            slg_model_options = model_options.copy()
+
+            for layer in double_layers:
+                slg_model_options = comfy.model_patcher.set_model_options_patch_replace(
+                    slg_model_options, skip, "dit", "double_block", layer
+                )
+
+            for layer in single_layers:
+                slg_model_options = comfy.model_patcher.set_model_options_patch_replace(
+                    slg_model_options, skip, "dit", "single_block", layer
+                )
+
+            cond, uncond = conds
+            sigma_ = sigma[0].item()
+            if sigma_ >= sigma_end and sigma_ <= sigma_start and uncond is not None:
+                cond_out, _ = comfy.samplers.calc_cond_batch(model, [cond, None], x, sigma, model_options)
+                _, uncond_out = comfy.samplers.calc_cond_batch(model, [None, uncond], x, sigma, slg_model_options)
+                out = [cond_out, uncond_out]
+            else:
+                out = comfy.samplers.calc_cond_batch(model, conds, x, sigma, model_options)
+
+            return out
+
+        m = model.clone()
+        m.set_model_sampler_calc_cond_batch_function(calc_cond_batch_function)
+
+        return io.NodeOutput(m)
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    SkipLayerGuidanceDiT,
+    SkipLayerGuidanceDiTSimple,
+]

comfy_extras/v3/nodes_stable3d.py

@@ -0,0 +1,165 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.utils
+import nodes
+from comfy_api.latest import io
+
+
+def camera_embeddings(elevation, azimuth):
+    elevation = torch.as_tensor([elevation])
+    azimuth = torch.as_tensor([azimuth])
+    embeddings = torch.stack(
+        [
+                torch.deg2rad(
+                    (90 - elevation) - 90
+                ),  # Zero123 polar is 90-elevation
+                torch.sin(torch.deg2rad(azimuth)),
+                torch.cos(torch.deg2rad(azimuth)),
+                torch.deg2rad(
+                    90 - torch.full_like(elevation, 0)
+                ),
+        ], dim=-1).unsqueeze(1)
+
+    return embeddings
+
+
+class StableZero123_Conditioning(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StableZero123_Conditioning_V3",
+            category="conditioning/3d_models",
+            inputs=[
+                io.ClipVision.Input("clip_vision"),
+                io.Image.Input("init_image"),
+                io.Vae.Input("vae"),
+                io.Int.Input("width", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("height", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+                io.Float.Input("elevation", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
+                io.Float.Input("azimuth", default=0.0, min=-180.0, max=180.0, step=0.1, round=False)
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent")
+            ]
+        )
+
+    @classmethod
+    def execute(cls, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth):
+        output = clip_vision.encode_image(init_image)
+        pooled = output.image_embeds.unsqueeze(0)
+        pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
+        encode_pixels = pixels[:,:,:,:3]
+        t = vae.encode(encode_pixels)
+        cam_embeds = camera_embeddings(elevation, azimuth)
+        cond = torch.cat([pooled, cam_embeds.to(pooled.device).repeat((pooled.shape[0], 1, 1))], dim=-1)
+
+        positive = [[cond, {"concat_latent_image": t}]]
+        negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]]
+        latent = torch.zeros([batch_size, 4, height // 8, width // 8])
+        return io.NodeOutput(positive, negative, {"samples":latent})
+
+
+class StableZero123_Conditioning_Batched(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StableZero123_Conditioning_Batched_V3",
+            category="conditioning/3d_models",
+            inputs=[
+                io.ClipVision.Input("clip_vision"),
+                io.Image.Input("init_image"),
+                io.Vae.Input("vae"),
+                io.Int.Input("width", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("height", default=256, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+                io.Float.Input("elevation", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
+                io.Float.Input("azimuth", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
+                io.Float.Input("elevation_batch_increment", default=0.0, min=-180.0, max=180.0, step=0.1, round=False),
+                io.Float.Input("azimuth_batch_increment", default=0.0, min=-180.0, max=180.0, step=0.1, round=False)
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent")
+            ]
+        )
+
+    @classmethod
+    def execute(cls, clip_vision, init_image, vae, width, height, batch_size, elevation, azimuth, elevation_batch_increment, azimuth_batch_increment):
+        output = clip_vision.encode_image(init_image)
+        pooled = output.image_embeds.unsqueeze(0)
+        pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
+        encode_pixels = pixels[:,:,:,:3]
+        t = vae.encode(encode_pixels)
+
+        cam_embeds = []
+        for i in range(batch_size):
+            cam_embeds.append(camera_embeddings(elevation, azimuth))
+            elevation += elevation_batch_increment
+            azimuth += azimuth_batch_increment
+
+        cam_embeds = torch.cat(cam_embeds, dim=0)
+        cond = torch.cat([comfy.utils.repeat_to_batch_size(pooled, batch_size), cam_embeds], dim=-1)
+
+        positive = [[cond, {"concat_latent_image": t}]]
+        negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t)}]]
+        latent = torch.zeros([batch_size, 4, height // 8, width // 8])
+        return io.NodeOutput(positive, negative, {"samples":latent, "batch_index": [0] * batch_size})
+
+
+class SV3D_Conditioning(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SV3D_Conditioning_V3",
+            category="conditioning/3d_models",
+            inputs=[
+                io.ClipVision.Input("clip_vision"),
+                io.Image.Input("init_image"),
+                io.Vae.Input("vae"),
+                io.Int.Input("width", default=576, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("height", default=576, min=16, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("video_frames", default=21, min=1, max=4096),
+                io.Float.Input("elevation", default=0.0, min=-90.0, max=90.0, step=0.1, round=False)
+            ],
+            outputs=[
+                io.Conditioning.Output(display_name="positive"),
+                io.Conditioning.Output(display_name="negative"),
+                io.Latent.Output(display_name="latent")
+            ]
+        )
+
+    @classmethod
+    def execute(cls, clip_vision, init_image, vae, width, height, video_frames, elevation):
+        output = clip_vision.encode_image(init_image)
+        pooled = output.image_embeds.unsqueeze(0)
+        pixels = comfy.utils.common_upscale(init_image.movedim(-1,1), width, height, "bilinear", "center").movedim(1,-1)
+        encode_pixels = pixels[:,:,:,:3]
+        t = vae.encode(encode_pixels)
+
+        azimuth = 0
+        azimuth_increment = 360 / (max(video_frames, 2) - 1)
+
+        elevations = []
+        azimuths = []
+        for i in range(video_frames):
+            elevations.append(elevation)
+            azimuths.append(azimuth)
+            azimuth += azimuth_increment
+
+        positive = [[pooled, {"concat_latent_image": t, "elevation": elevations, "azimuth": azimuths}]]
+        negative = [[torch.zeros_like(pooled), {"concat_latent_image": torch.zeros_like(t), "elevation": elevations, "azimuth": azimuths}]]
+        latent = torch.zeros([video_frames, 4, height // 8, width // 8])
+        return io.NodeOutput(positive, negative, {"samples":latent})
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    StableZero123_Conditioning,
+    StableZero123_Conditioning_Batched,
+    SV3D_Conditioning,
+]

comfy_extras/v3/nodes_stable_cascade.py

@@ -0,0 +1,143 @@
+"""
+This file is part of ComfyUI.
+Copyright (C) 2024 Stability AI
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
+"""
+
+import torch
+
+import comfy.utils
+import nodes
+from comfy_api.latest import io
+
+
+class StableCascade_EmptyLatentImage(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StableCascade_EmptyLatentImage_V3",
+            category="latent/stable_cascade",
+            inputs=[
+                io.Int.Input("width", default=1024, min=256, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("height", default=1024, min=256, max=nodes.MAX_RESOLUTION, step=8),
+                io.Int.Input("compression", default=42, min=4, max=128, step=1),
+                io.Int.Input("batch_size", default=1, min=1, max=4096),
+            ],
+            outputs=[
+                io.Latent.Output(display_name="stage_c"),
+                io.Latent.Output(display_name="stage_b"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, width, height, compression, batch_size=1):
+        c_latent = torch.zeros([batch_size, 16, height // compression, width // compression])
+        b_latent = torch.zeros([batch_size, 4, height // 4, width // 4])
+        return io.NodeOutput({"samples": c_latent}, {"samples": b_latent})
+
+
+class StableCascade_StageC_VAEEncode(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StableCascade_StageC_VAEEncode_V3",
+            category="latent/stable_cascade",
+            inputs=[
+                io.Image.Input("image"),
+                io.Vae.Input("vae"),
+                io.Int.Input("compression", default=42, min=4, max=128, step=1),
+            ],
+            outputs=[
+                io.Latent.Output(display_name="stage_c"),
+                io.Latent.Output(display_name="stage_b"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image, vae, compression):
+        width = image.shape[-2]
+        height = image.shape[-3]
+        out_width = (width // compression) * vae.downscale_ratio
+        out_height = (height // compression) * vae.downscale_ratio
+
+        s = comfy.utils.common_upscale(image.movedim(-1, 1), out_width, out_height, "bicubic", "center").movedim(1, -1)
+
+        c_latent = vae.encode(s[:, :, :, :3])
+        b_latent = torch.zeros([c_latent.shape[0], 4, (height // 8) * 2, (width // 8) * 2])
+        return io.NodeOutput({"samples": c_latent}, {"samples": b_latent})
+
+
+class StableCascade_StageB_Conditioning(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StableCascade_StageB_Conditioning_V3",
+            category="conditioning/stable_cascade",
+            inputs=[
+                io.Conditioning.Input("conditioning"),
+                io.Latent.Input("stage_c"),
+            ],
+            outputs=[
+                io.Conditioning.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, conditioning, stage_c):
+        c = []
+        for t in conditioning:
+            d = t[1].copy()
+            d["stable_cascade_prior"] = stage_c["samples"]
+            n = [t[0], d]
+            c.append(n)
+        return io.NodeOutput(c)
+
+
+class StableCascade_SuperResolutionControlnet(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StableCascade_SuperResolutionControlnet_V3",
+            category="_for_testing/stable_cascade",
+            is_experimental=True,
+            inputs=[
+                io.Image.Input("image"),
+                io.Vae.Input("vae"),
+            ],
+            outputs=[
+                io.Image.Output(display_name="controlnet_input"),
+                io.Latent.Output(display_name="stage_c"),
+                io.Latent.Output(display_name="stage_b"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, image, vae):
+        width = image.shape[-2]
+        height = image.shape[-3]
+        batch_size = image.shape[0]
+        controlnet_input = vae.encode(image[:, :, :, :3]).movedim(1, -1)
+
+        c_latent = torch.zeros([batch_size, 16, height // 16, width // 16])
+        b_latent = torch.zeros([batch_size, 4, height // 2, width // 2])
+        return io.NodeOutput(controlnet_input, {"samples": c_latent}, {"samples": b_latent})
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    StableCascade_EmptyLatentImage,
+    StableCascade_StageB_Conditioning,
+    StableCascade_StageC_VAEEncode,
+    StableCascade_SuperResolutionControlnet,
+]

comfy_extras/v3/nodes_string.py

@@ -0,0 +1,380 @@
+from __future__ import annotations
+
+import re
+
+from comfy_api.latest import io
+
+
+class StringConcatenate(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StringConcatenate_V3",
+            display_name="Concatenate _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string_a", multiline=True),
+                io.String.Input("string_b", multiline=True),
+                io.String.Input("delimiter", multiline=False, default="")
+            ],
+            outputs=[
+                io.String.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string_a, string_b, delimiter):
+        return io.NodeOutput(delimiter.join((string_a, string_b)))
+
+
+class StringSubstring(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StringSubstring_V3",
+            display_name="Substring _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string", multiline=True),
+                io.Int.Input("start"),
+                io.Int.Input("end")
+            ],
+            outputs=[
+                io.String.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string, start, end):
+        return io.NodeOutput(string[start:end])
+
+
+class StringLength(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StringLength_V3",
+            display_name="Length _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string", multiline=True)
+            ],
+            outputs=[
+                io.Int.Output(display_name="length")
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string):
+        return io.NodeOutput(len(string))
+
+
+class CaseConverter(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CaseConverter_V3",
+            display_name="Case Converter _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string", multiline=True),
+                io.Combo.Input("mode", options=["UPPERCASE", "lowercase", "Capitalize", "Title Case"])
+            ],
+            outputs=[
+                io.String.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string, mode):
+        if mode == "UPPERCASE":
+            result = string.upper()
+        elif mode == "lowercase":
+            result = string.lower()
+        elif mode == "Capitalize":
+            result = string.capitalize()
+        elif mode == "Title Case":
+            result = string.title()
+        else:
+            result = string
+
+        return io.NodeOutput(result)
+
+
+class StringTrim(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StringTrim_V3",
+            display_name="Trim _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string", multiline=True),
+                io.Combo.Input("mode", options=["Both", "Left", "Right"])
+            ],
+            outputs=[
+                io.String.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string, mode):
+        if mode == "Both":
+            result = string.strip()
+        elif mode == "Left":
+            result = string.lstrip()
+        elif mode == "Right":
+            result = string.rstrip()
+        else:
+            result = string
+
+        return io.NodeOutput(result)
+
+
+class StringReplace(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StringReplace_V3",
+            display_name="Replace _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string", multiline=True),
+                io.String.Input("find", multiline=True),
+                io.String.Input("replace", multiline=True)
+            ],
+            outputs=[
+                io.String.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string, find, replace):
+        return io.NodeOutput(string.replace(find, replace))
+
+
+class StringContains(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StringContains_V3",
+            display_name="Contains _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string", multiline=True),
+                io.String.Input("substring", multiline=True),
+                io.Boolean.Input("case_sensitive", default=True)
+            ],
+            outputs=[
+                io.Boolean.Output(display_name="contains")
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string, substring, case_sensitive):
+        if case_sensitive:
+            contains = substring in string
+        else:
+            contains = substring.lower() in string.lower()
+
+        return io.NodeOutput(contains)
+
+
+class StringCompare(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="StringCompare_V3",
+            display_name="Compare _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string_a", multiline=True),
+                io.String.Input("string_b", multiline=True),
+                io.Combo.Input("mode", options=["Starts With", "Ends With", "Equal"]),
+                io.Boolean.Input("case_sensitive", default=True)
+            ],
+            outputs=[
+                io.Boolean.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string_a, string_b, mode, case_sensitive):
+        if case_sensitive:
+            a = string_a
+            b = string_b
+        else:
+            a = string_a.lower()
+            b = string_b.lower()
+
+        if mode == "Equal":
+            return io.NodeOutput(a == b)
+        elif mode == "Starts With":
+            return io.NodeOutput(a.startswith(b))
+        elif mode == "Ends With":
+            return io.NodeOutput(a.endswith(b))
+
+
+class RegexMatch(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RegexMatch_V3",
+            display_name="Regex Match _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string", multiline=True),
+                io.String.Input("regex_pattern", multiline=True),
+                io.Boolean.Input("case_insensitive", default=True),
+                io.Boolean.Input("multiline", default=False),
+                io.Boolean.Input("dotall", default=False)
+            ],
+            outputs=[
+                io.Boolean.Output(display_name="matches")
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string, regex_pattern, case_insensitive, multiline, dotall):
+        flags = 0
+
+        if case_insensitive:
+            flags |= re.IGNORECASE
+        if multiline:
+            flags |= re.MULTILINE
+        if dotall:
+            flags |= re.DOTALL
+
+        try:
+            match = re.search(regex_pattern, string, flags)
+            result = match is not None
+
+        except re.error:
+            result = False
+
+        return io.NodeOutput(result)
+
+
+class RegexExtract(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RegexExtract_V3",
+            display_name="Regex Extract _V3",
+            category="utils/string",
+            inputs=[
+                io.String.Input("string", multiline=True),
+                io.String.Input("regex_pattern", multiline=True),
+                io.Combo.Input("mode", options=["First Match", "All Matches", "First Group", "All Groups"]),
+                io.Boolean.Input("case_insensitive", default=True),
+                io.Boolean.Input("multiline", default=False),
+                io.Boolean.Input("dotall", default=False),
+                io.Int.Input("group_index", default=1, min=0, max=100)
+            ],
+            outputs=[
+                io.String.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string, regex_pattern, mode, case_insensitive, multiline, dotall, group_index):
+        join_delimiter = "\n"
+
+        flags = 0
+        if case_insensitive:
+            flags |= re.IGNORECASE
+        if multiline:
+            flags |= re.MULTILINE
+        if dotall:
+            flags |= re.DOTALL
+
+        try:
+            if mode == "First Match":
+                match = re.search(regex_pattern, string, flags)
+                if match:
+                    result = match.group(0)
+                else:
+                    result = ""
+
+            elif mode == "All Matches":
+                matches = re.findall(regex_pattern, string, flags)
+                if matches:
+                    if isinstance(matches[0], tuple):
+                        result = join_delimiter.join([m[0] for m in matches])
+                    else:
+                        result = join_delimiter.join(matches)
+                else:
+                    result = ""
+
+            elif mode == "First Group":
+                match = re.search(regex_pattern, string, flags)
+                if match and len(match.groups()) >= group_index:
+                    result = match.group(group_index)
+                else:
+                    result = ""
+
+            elif mode == "All Groups":
+                matches = re.finditer(regex_pattern, string, flags)
+                results = []
+                for match in matches:
+                    if match.groups() and len(match.groups()) >= group_index:
+                        results.append(match.group(group_index))
+                result = join_delimiter.join(results)
+            else:
+                result = ""
+
+        except re.error:
+            result = ""
+
+        return io.NodeOutput(result)
+
+
+class RegexReplace(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RegexReplace_V3",
+            display_name="Regex Replace _V3",
+            category="utils/string",
+            description="Find and replace text using regex patterns.",
+            inputs=[
+                io.String.Input("string", multiline=True),
+                io.String.Input("regex_pattern", multiline=True),
+                io.String.Input("replace", multiline=True),
+                io.Boolean.Input("case_insensitive", default=True, optional=True),
+                io.Boolean.Input("multiline", default=False, optional=True),
+                io.Boolean.Input("dotall", default=False, optional=True, tooltip="When enabled, the dot (.) character will match any character including newline characters. When disabled, dots won't match newlines."),
+                io.Int.Input("count", default=0, min=0, max=100, optional=True, tooltip="Maximum number of replacements to make. Set to 0 to replace all occurrences (default). Set to 1 to replace only the first match, 2 for the first two matches, etc.")
+            ],
+            outputs=[
+                io.String.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, string, regex_pattern, replace, case_insensitive=True, multiline=False, dotall=False, count=0):
+        flags = 0
+
+        if case_insensitive:
+            flags |= re.IGNORECASE
+        if multiline:
+            flags |= re.MULTILINE
+        if dotall:
+            flags |= re.DOTALL
+        result = re.sub(regex_pattern, replace, string, count=count, flags=flags)
+        return io.NodeOutput(result)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    CaseConverter,
+    RegexExtract,
+    RegexMatch,
+    RegexReplace,
+    StringCompare,
+    StringConcatenate,
+    StringContains,
+    StringLength,
+    StringReplace,
+    StringSubstring,
+    StringTrim,
+]

comfy_extras/v3/nodes_tcfg.py

@@ -0,0 +1,70 @@
+"""TCFG: Tangential Damping Classifier-free Guidance - (arXiv: https://arxiv.org/abs/2503.18137)"""
+
+from __future__ import annotations
+
+import torch
+
+from comfy_api.latest import io
+
+
+def score_tangential_damping(cond_score: torch.Tensor, uncond_score: torch.Tensor) -> torch.Tensor:
+    """Drop tangential components from uncond score to align with cond score."""
+    # (B, 1, ...)
+    batch_num = cond_score.shape[0]
+    cond_score_flat = cond_score.reshape(batch_num, 1, -1).float()
+    uncond_score_flat = uncond_score.reshape(batch_num, 1, -1).float()
+
+    # Score matrix A (B, 2, ...)
+    score_matrix = torch.cat((uncond_score_flat, cond_score_flat), dim=1)
+    try:
+        _, _, Vh = torch.linalg.svd(score_matrix, full_matrices=False)
+    except RuntimeError:
+        # Fallback to CPU
+        _, _, Vh = torch.linalg.svd(score_matrix.cpu(), full_matrices=False)
+
+    # Drop the tangential components
+    v1 = Vh[:, 0:1, :].to(uncond_score_flat.device)  # (B, 1, ...)
+    uncond_score_td = (uncond_score_flat @ v1.transpose(-2, -1)) * v1
+    return uncond_score_td.reshape_as(uncond_score).to(uncond_score.dtype)
+
+
+class TCFG(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="TCFG_V3",
+            display_name="Tangential Damping CFG _V3",
+            category="advanced/guidance",
+            description="TCFG – Tangential Damping CFG (2503.18137)\n\nRefine the uncond (negative) to align with the cond (positive) for improving quality.",
+            inputs=[
+                io.Model.Input("model"),
+            ],
+            outputs=[
+                io.Model.Output(display_name="patched_model"),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model):
+        m = model.clone()
+
+        def tangential_damping_cfg(args):
+            #  Assume [cond, uncond, ...]
+            x = args["input"]
+            conds_out = args["conds_out"]
+            if len(conds_out) <= 1 or None in args["conds"][:2]:
+                # Skip when either cond or uncond is None
+                return conds_out
+            cond_pred = conds_out[0]
+            uncond_pred = conds_out[1]
+            uncond_td = score_tangential_damping(x - cond_pred, x - uncond_pred)
+            uncond_pred_td = x - uncond_td
+            return [cond_pred, uncond_pred_td] + conds_out[2:]
+
+        m.set_model_sampler_pre_cfg_function(tangential_damping_cfg)
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    TCFG,
+]

comfy_extras/v3/nodes_tomesd.py

@@ -0,0 +1,190 @@
+"""Taken from: https://github.com/dbolya/tomesd"""
+
+from __future__ import annotations
+
+import math
+from typing import Callable, Tuple
+
+import torch
+
+from comfy_api.latest import io
+
+
+def do_nothing(x: torch.Tensor, mode:str=None):
+    return x
+
+
+def mps_gather_workaround(input, dim, index):
+    if input.shape[-1] == 1:
+        return torch.gather(
+            input.unsqueeze(-1),
+            dim - 1 if dim < 0 else dim,
+            index.unsqueeze(-1)
+        ).squeeze(-1)
+    return torch.gather(input, dim, index)
+
+
+def bipartite_soft_matching_random2d(
+    metric: torch.Tensor,w: int, h: int, sx: int, sy: int, r: int, no_rand: bool = False
+) -> Tuple[Callable, Callable]:
+    """
+    Partitions the tokens into src and dst and merges r tokens from src to dst.
+    Dst tokens are partitioned by choosing one randomy in each (sx, sy) region.
+    Args:
+     - metric [B, N, C]: metric to use for similarity
+     - w: image width in tokens
+     - h: image height in tokens
+     - sx: stride in the x dimension for dst, must divide w
+     - sy: stride in the y dimension for dst, must divide h
+     - r: number of tokens to remove (by merging)
+     - no_rand: if true, disable randomness (use top left corner only)
+    """
+    B, N, _ = metric.shape
+
+    if r <= 0 or w == 1 or h == 1:
+        return do_nothing, do_nothing
+
+    gather = mps_gather_workaround if metric.device.type == "mps" else torch.gather
+
+    with torch.no_grad():
+        hsy, wsx = h // sy, w // sx
+
+        # For each sy by sx kernel, randomly assign one token to be dst and the rest src
+        if no_rand:
+            rand_idx = torch.zeros(hsy, wsx, 1, device=metric.device, dtype=torch.int64)
+        else:
+            rand_idx = torch.randint(sy*sx, size=(hsy, wsx, 1), device=metric.device)
+
+        # The image might not divide sx and sy, so we need to work on a view of the top left if the idx buffer instead
+        idx_buffer_view = torch.zeros(hsy, wsx, sy*sx, device=metric.device, dtype=torch.int64)
+        idx_buffer_view.scatter_(dim=2, index=rand_idx, src=-torch.ones_like(rand_idx, dtype=rand_idx.dtype))
+        idx_buffer_view = idx_buffer_view.view(hsy, wsx, sy, sx).transpose(1, 2).reshape(hsy * sy, wsx * sx)
+
+        # Image is not divisible by sx or sy so we need to move it into a new buffer
+        if (hsy * sy) < h or (wsx * sx) < w:
+            idx_buffer = torch.zeros(h, w, device=metric.device, dtype=torch.int64)
+            idx_buffer[:(hsy * sy), :(wsx * sx)] = idx_buffer_view
+        else:
+            idx_buffer = idx_buffer_view
+
+        # We set dst tokens to be -1 and src to be 0, so an argsort gives us dst|src indices
+        rand_idx = idx_buffer.reshape(1, -1, 1).argsort(dim=1)
+
+        # We're finished with these
+        del idx_buffer, idx_buffer_view
+
+        # rand_idx is currently dst|src, so split them
+        num_dst = hsy * wsx
+        a_idx = rand_idx[:, num_dst:, :] # src
+        b_idx = rand_idx[:, :num_dst, :] # dst
+
+        def split(x):
+            C = x.shape[-1]
+            src = gather(x, dim=1, index=a_idx.expand(B, N - num_dst, C))
+            dst = gather(x, dim=1, index=b_idx.expand(B, num_dst, C))
+            return src, dst
+
+        # Cosine similarity between A and B
+        metric = metric / metric.norm(dim=-1, keepdim=True)
+        a, b = split(metric)
+        scores = a @ b.transpose(-1, -2)
+
+        # Can't reduce more than the # tokens in src
+        r = min(a.shape[1], r)
+
+        # Find the most similar greedily
+        node_max, node_idx = scores.max(dim=-1)
+        edge_idx = node_max.argsort(dim=-1, descending=True)[..., None]
+
+        unm_idx = edge_idx[..., r:, :]  # Unmerged Tokens
+        src_idx = edge_idx[..., :r, :]  # Merged Tokens
+        dst_idx = gather(node_idx[..., None], dim=-2, index=src_idx)
+
+    def merge(x: torch.Tensor, mode="mean") -> torch.Tensor:
+        src, dst = split(x)
+        n, t1, c = src.shape
+
+        unm = gather(src, dim=-2, index=unm_idx.expand(n, t1 - r, c))
+        src = gather(src, dim=-2, index=src_idx.expand(n, r, c))
+        dst = dst.scatter_reduce(-2, dst_idx.expand(n, r, c), src, reduce=mode)
+
+        return torch.cat([unm, dst], dim=1)
+
+    def unmerge(x: torch.Tensor) -> torch.Tensor:
+        unm_len = unm_idx.shape[1]
+        unm, dst = x[..., :unm_len, :], x[..., unm_len:, :]
+        _, _, c = unm.shape
+
+        src = gather(dst, dim=-2, index=dst_idx.expand(B, r, c))
+
+        # Combine back to the original shape
+        out = torch.zeros(B, N, c, device=x.device, dtype=x.dtype)
+        out.scatter_(dim=-2, index=b_idx.expand(B, num_dst, c), src=dst)
+        out.scatter_(dim=-2, index=gather(a_idx.expand(B, a_idx.shape[1], 1), dim=1, index=unm_idx).expand(B, unm_len, c), src=unm)
+        out.scatter_(dim=-2, index=gather(a_idx.expand(B, a_idx.shape[1], 1), dim=1, index=src_idx).expand(B, r, c), src=src)
+
+        return out
+
+    return merge, unmerge
+
+
+def get_functions(x, ratio, original_shape):
+    b, c, original_h, original_w = original_shape
+    original_tokens = original_h * original_w
+    downsample = int(math.ceil(math.sqrt(original_tokens // x.shape[1])))
+    stride_x = 2
+    stride_y = 2
+    max_downsample = 1
+
+    if downsample <= max_downsample:
+        w = int(math.ceil(original_w / downsample))
+        h = int(math.ceil(original_h / downsample))
+        r = int(x.shape[1] * ratio)
+        no_rand = False
+        m, u = bipartite_soft_matching_random2d(x, w, h, stride_x, stride_y, r, no_rand)
+        return m, u
+
+    def nothing(y):
+        return y
+
+    return nothing, nothing
+
+
+class TomePatchModel(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="TomePatchModel_V3",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("ratio", default=0.3, min=0.0, max=1.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
+
+    @classmethod
+    def execute(cls, model, ratio):
+        u = None
+
+        def tomesd_m(q, k, v, extra_options):
+            nonlocal u
+            #NOTE: In the reference code get_functions takes x (input of the transformer block) as the argument instead of q
+            #however from my basic testing it seems that using q instead gives better results
+            m, u = get_functions(q, ratio, extra_options["original_shape"])
+            return m(q), k, v
+
+        def tomesd_u(n, extra_options):
+            return u(n)
+
+        m = model.clone()
+        m.set_model_attn1_patch(tomesd_m)
+        m.set_model_attn1_output_patch(tomesd_u)
+        return io.NodeOutput(m)
+
+
+NODES_LIST: list[type[io.ComfyNode]] = [
+    TomePatchModel,
+]