ComfyUI version 0.3.44

* update nightly workflow with cu129

* Remove unused file to lower standalone size.

.github/workflows/windows_release_nightly_pytorch.yml

@@ -7,7 +7,7 @@ on:
         description: 'cuda version'
         required: true
         type: string
-        default: "128"
+        default: "129"
 
       python_minor:
         description: 'python minor version'
@@ -19,7 +19,7 @@ on:
         description: 'python patch version'
         required: true
         type: string
-        default: "2"
+        default: "5"
 #  push:
 #    branches:
 #      - master
@@ -53,6 +53,8 @@ jobs:
             ls ../temp_wheel_dir
             ./python.exe -s -m pip install --pre ../temp_wheel_dir/*
             sed -i '1i../ComfyUI' ./python3${{ inputs.python_minor }}._pth
+
+            rm ./Lib/site-packages/torch/lib/dnnl.lib #I don't think this is actually used and I need the space
             cd ..
 
             git clone --depth 1 https://github.com/comfyanonymous/taesd

README.md

@@ -86,6 +86,7 @@ See what ComfyUI can do with the [example workflows](https://comfyanonymous.gith
 - Smart memory management: can automatically run models on GPUs with as low as 1GB vram.
 - Works even if you don't have a GPU with: ```--cpu``` (slow)
 - Can load ckpt, safetensors and diffusers models/checkpoints. Standalone VAEs and CLIP models.
+- Safe loading of ckpt, pt, pth, etc.. files.
 - Embeddings/Textual inversion
 - [Loras (regular, locon and loha)](https://comfyanonymous.github.io/ComfyUI_examples/lora/)
 - [Hypernetworks](https://comfyanonymous.github.io/ComfyUI_examples/hypernetworks/)
@@ -101,7 +102,6 @@ See what ComfyUI can do with the [example workflows](https://comfyanonymous.gith
 - [Model Merging](https://comfyanonymous.github.io/ComfyUI_examples/model_merging/)
 - [LCM models and Loras](https://comfyanonymous.github.io/ComfyUI_examples/lcm/)
 - Latent previews with [TAESD](#how-to-show-high-quality-previews)
-- Starts up very fast.
 - Works fully offline: core will never download anything unless you want to.
 - Optional API nodes to use paid models from external providers through the online [Comfy API](https://docs.comfy.org/tutorials/api-nodes/overview).
 - [Config file](extra_model_paths.yaml.example) to set the search paths for models.
@@ -243,7 +243,7 @@ Nvidia users should install stable pytorch using this command:
 
 This is the command to install pytorch nightly instead which might have performance improvements.
 
-```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu128```
+```pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu129```
 
 #### Troubleshooting
 

comfy/gligen.py

@@ -1,55 +1,10 @@
 import math
 import torch
 from torch import nn
-from .ldm.modules.attention import CrossAttention
-from inspect import isfunction
+from .ldm.modules.attention import CrossAttention, FeedForward
 import comfy.ops
 ops = comfy.ops.manual_cast
 
-def exists(val):
-    return val is not None
-
-
-def uniq(arr):
-    return{el: True for el in arr}.keys()
-
-
-def default(val, d):
-    if exists(val):
-        return val
-    return d() if isfunction(d) else d
-
-
-# feedforward
-class GEGLU(nn.Module):
-    def __init__(self, dim_in, dim_out):
-        super().__init__()
-        self.proj = ops.Linear(dim_in, dim_out * 2)
-
-    def forward(self, x):
-        x, gate = self.proj(x).chunk(2, dim=-1)
-        return x * torch.nn.functional.gelu(gate)
-
-
-class FeedForward(nn.Module):
-    def __init__(self, dim, dim_out=None, mult=4, glu=False, dropout=0.):
-        super().__init__()
-        inner_dim = int(dim * mult)
-        dim_out = default(dim_out, dim)
-        project_in = nn.Sequential(
-            ops.Linear(dim, inner_dim),
-            nn.GELU()
-        ) if not glu else GEGLU(dim, inner_dim)
-
-        self.net = nn.Sequential(
-            project_in,
-            nn.Dropout(dropout),
-            ops.Linear(inner_dim, dim_out)
-        )
-
-    def forward(self, x):
-        return self.net(x)
-
 
 class GatedCrossAttentionDense(nn.Module):
     def __init__(self, query_dim, context_dim, n_heads, d_head):

comfy/k_diffusion/sampling.py

@@ -412,9 +412,13 @@ def sample_lms(model, x, sigmas, extra_args=None, callback=None, disable=None, o
             ds.pop(0)
         if callback is not None:
             callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})
-        cur_order = min(i + 1, order)
-        coeffs = [linear_multistep_coeff(cur_order, sigmas_cpu, i, j) for j in range(cur_order)]
-        x = x + sum(coeff * d for coeff, d in zip(coeffs, reversed(ds)))
+        if sigmas[i + 1] == 0:
+            # Denoising step
+            x = denoised
+        else:
+            cur_order = min(i + 1, order)
+            coeffs = [linear_multistep_coeff(cur_order, sigmas_cpu, i, j) for j in range(cur_order)]
+            x = x + sum(coeff * d for coeff, d in zip(coeffs, reversed(ds)))
     return x
 
 
@@ -1067,7 +1071,9 @@ def sample_ipndm(model, x, sigmas, extra_args=None, callback=None, disable=None,
         d_cur = (x_cur - denoised) / t_cur
 
         order = min(max_order, i+1)
-        if order == 1:      # First Euler step.
+        if t_next == 0:     # Denoising step
+            x_next = denoised
+        elif order == 1:    # First Euler step.
             x_next = x_cur + (t_next - t_cur) * d_cur
         elif order == 2:    # Use one history point.
             x_next = x_cur + (t_next - t_cur) * (3 * d_cur - buffer_model[-1]) / 2
@@ -1085,6 +1091,7 @@ def sample_ipndm(model, x, sigmas, extra_args=None, callback=None, disable=None,
 
     return x_next
 
+
 #From https://github.com/zju-pi/diff-sampler/blob/main/diff-solvers-main/solvers.py
 #under Apache 2 license
 def sample_ipndm_v(model, x, sigmas, extra_args=None, callback=None, disable=None, max_order=4):
@@ -1108,7 +1115,9 @@ def sample_ipndm_v(model, x, sigmas, extra_args=None, callback=None, disable=Non
         d_cur = (x_cur - denoised) / t_cur
 
         order = min(max_order, i+1)
-        if order == 1:      # First Euler step.
+        if t_next == 0:     # Denoising step
+            x_next = denoised
+        elif order == 1:    # First Euler step.
             x_next = x_cur + (t_next - t_cur) * d_cur
         elif order == 2:    # Use one history point.
             h_n = (t_next - t_cur)
@@ -1148,6 +1157,7 @@ def sample_ipndm_v(model, x, sigmas, extra_args=None, callback=None, disable=Non
 
     return x_next
 
+
 #From https://github.com/zju-pi/diff-sampler/blob/main/diff-solvers-main/solvers.py
 #under Apache 2 license
 @torch.no_grad()
@@ -1198,6 +1208,7 @@ def sample_deis(model, x, sigmas, extra_args=None, callback=None, disable=None,
 
     return x_next
 
+
 @torch.no_grad()
 def sample_euler_cfg_pp(model, x, sigmas, extra_args=None, callback=None, disable=None):
     extra_args = {} if extra_args is None else extra_args
@@ -1404,6 +1415,7 @@ def sample_res_multistep_ancestral(model, x, sigmas, extra_args=None, callback=N
 def sample_res_multistep_ancestral_cfg_pp(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None):
     return res_multistep(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, s_noise=s_noise, noise_sampler=noise_sampler, eta=eta, cfg_pp=True)
 
+
 @torch.no_grad()
 def sample_gradient_estimation(model, x, sigmas, extra_args=None, callback=None, disable=None, ge_gamma=2., cfg_pp=False):
     """Gradient-estimation sampler. Paper: https://openreview.net/pdf?id=o2ND9v0CeK"""
@@ -1430,19 +1442,19 @@ def sample_gradient_estimation(model, x, sigmas, extra_args=None, callback=None,
         if callback is not None:
             callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})
         dt = sigmas[i + 1] - sigmas[i]
-        if i == 0:
+        if sigmas[i + 1] == 0:
+            # Denoising step
+            x = denoised
+        else:
             # Euler method
             if cfg_pp:
                 x = denoised + d * sigmas[i + 1]
             else:
                 x = x + d * dt
-        else:
-            # Gradient estimation
-            if cfg_pp:
+
+            if i >= 1:
+                # Gradient estimation
                 d_bar = (ge_gamma - 1) * (d - old_d)
-                x = denoised + d * sigmas[i + 1] + d_bar * dt
-            else:
-                d_bar = ge_gamma * d + (1 - ge_gamma) * old_d
                 x = x + d_bar * dt
         old_d = d
     return x

comfy/model_patcher.py

@@ -379,6 +379,9 @@ class ModelPatcher:
     def set_model_sampler_pre_cfg_function(self, pre_cfg_function, disable_cfg1_optimization=False):
         self.model_options = set_model_options_pre_cfg_function(self.model_options, pre_cfg_function, disable_cfg1_optimization)
 
+    def set_model_sampler_calc_cond_batch_function(self, sampler_calc_cond_batch_function):
+        self.model_options["sampler_calc_cond_batch_function"] = sampler_calc_cond_batch_function
+
     def set_model_unet_function_wrapper(self, unet_wrapper_function: UnetWrapperFunction):
         self.model_options["model_function_wrapper"] = unet_wrapper_function
 

comfy/ops.py

@@ -336,9 +336,12 @@ class fp8_ops(manual_cast):
             return None
 
         def forward_comfy_cast_weights(self, input):
-            out = fp8_linear(self, input)
-            if out is not None:
-                return out
+            try:
+                out = fp8_linear(self, input)
+                if out is not None:
+                    return out
+            except Exception as e:
+                logging.info("Exception during fp8 op: {}".format(e))
 
             weight, bias = cast_bias_weight(self, input)
             return torch.nn.functional.linear(input, weight, bias)

comfy/samplers.py

@@ -373,7 +373,11 @@ def sampling_function(model, x, timestep, uncond, cond, cond_scale, model_option
         uncond_ = uncond
 
     conds = [cond, uncond_]
-    out = calc_cond_batch(model, conds, x, timestep, model_options)
+    if "sampler_calc_cond_batch_function" in model_options:
+        args = {"conds": conds, "input": x, "sigma": timestep, "model": model, "model_options": model_options}
+        out = model_options["sampler_calc_cond_batch_function"](args)
+    else:
+        out = calc_cond_batch(model, conds, x, timestep, model_options)
 
     for fn in model_options.get("sampler_pre_cfg_function", []):
         args = {"conds":conds, "conds_out": out, "cond_scale": cond_scale, "timestep": timestep,

comfy/utils.py

@@ -77,6 +77,7 @@ def load_torch_file(ckpt, safe_load=False, device=None, return_metadata=False):
         if safe_load or ALWAYS_SAFE_LOAD:
             pl_sd = torch.load(ckpt, map_location=device, weights_only=True, **torch_args)
         else:
+            logging.warning("WARNING: loading {} unsafely, upgrade your pytorch to 2.4 or newer to load this file safely.".format(ckpt))
             pl_sd = torch.load(ckpt, map_location=device, pickle_module=comfy.checkpoint_pickle)
         if "state_dict" in pl_sd:
             sd = pl_sd["state_dict"]

comfy_api/input/video_types.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 from abc import ABC, abstractmethod
-from typing import Optional
+from typing import Optional, Union
+import io
 from comfy_api.util import VideoContainer, VideoCodec, VideoComponents
 
 class VideoInput(ABC):
@@ -31,6 +32,22 @@ class VideoInput(ABC):
         """
         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]:

comfy_api/input_impl/video_types.py

@@ -64,6 +64,15 @@ class VideoFromFile(VideoInput):
         """
         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.

comfy_api_nodes/apis/__init__.py

@@ -1,6 +1,6 @@
 # generated by datamodel-codegen:
 #   filename:  filtered-openapi.yaml
-#   timestamp: 2025-05-19T21:38:55+00:00
+#   timestamp: 2025-07-06T09:47:31+00:00
 
 from __future__ import annotations
 
@@ -1355,6 +1355,158 @@ class ModelResponseProperties(BaseModel):
     )
 
 
+class Keyframes(BaseModel):
+    image_url: Optional[str] = None
+
+
+class MoonvalleyPromptResponse(BaseModel):
+    error: Optional[Dict[str, Any]] = None
+    frame_conditioning: Optional[Dict[str, Any]] = None
+    id: Optional[str] = None
+    inference_params: Optional[Dict[str, Any]] = None
+    meta: Optional[Dict[str, Any]] = None
+    model_params: Optional[Dict[str, Any]] = None
+    output_url: Optional[str] = None
+    prompt_text: Optional[str] = None
+    status: Optional[str] = None
+
+
+class MoonvalleyTextToVideoInferenceParams(BaseModel):
+    add_quality_guidance: Optional[bool] = Field(
+        True, description='Whether to add quality guidance'
+    )
+    caching_coefficient: Optional[float] = Field(
+        0.3, description='Caching coefficient for optimization'
+    )
+    caching_cooldown: Optional[int] = Field(
+        3, description='Number of caching cooldown steps'
+    )
+    caching_warmup: Optional[int] = Field(
+        3, description='Number of caching warmup steps'
+    )
+    clip_value: Optional[float] = Field(
+        3, description='CLIP value for generation control'
+    )
+    conditioning_frame_index: Optional[int] = Field(
+        0, description='Index of the conditioning frame'
+    )
+    cooldown_steps: Optional[int] = Field(
+        None, description='Number of cooldown steps (calculated based on num_frames)'
+    )
+    fps: Optional[int] = Field(
+        24, description='Frames per second of the generated video'
+    )
+    guidance_scale: Optional[float] = Field(
+        12.5, description='Guidance scale for generation control'
+    )
+    height: Optional[int] = Field(
+        1080, description='Height of the generated video in pixels'
+    )
+    negative_prompt: Optional[str] = Field(None, description='Negative prompt text')
+    num_frames: Optional[int] = Field(64, description='Number of frames to generate')
+    seed: Optional[int] = Field(
+        None, description='Random seed for generation (default: random)'
+    )
+    shift_value: Optional[float] = Field(
+        3, description='Shift value for generation control'
+    )
+    steps: Optional[int] = Field(80, description='Number of denoising steps')
+    use_guidance_schedule: Optional[bool] = Field(
+        True, description='Whether to use guidance scheduling'
+    )
+    use_negative_prompts: Optional[bool] = Field(
+        False, description='Whether to use negative prompts'
+    )
+    use_timestep_transform: Optional[bool] = Field(
+        True, description='Whether to use timestep transformation'
+    )
+    warmup_steps: Optional[int] = Field(
+        None, description='Number of warmup steps (calculated based on num_frames)'
+    )
+    width: Optional[int] = Field(
+        1920, description='Width of the generated video in pixels'
+    )
+
+
+class MoonvalleyTextToVideoRequest(BaseModel):
+    image_url: Optional[str] = None
+    inference_params: Optional[MoonvalleyTextToVideoInferenceParams] = None
+    prompt_text: Optional[str] = None
+    webhook_url: Optional[str] = None
+
+
+class MoonvalleyUploadFileRequest(BaseModel):
+    file: Optional[StrictBytes] = None
+
+
+class MoonvalleyUploadFileResponse(BaseModel):
+    access_url: Optional[str] = None
+
+
+class MoonvalleyVideoToVideoInferenceParams(BaseModel):
+    add_quality_guidance: Optional[bool] = Field(
+        True, description='Whether to add quality guidance'
+    )
+    caching_coefficient: Optional[float] = Field(
+        0.3, description='Caching coefficient for optimization'
+    )
+    caching_cooldown: Optional[int] = Field(
+        3, description='Number of caching cooldown steps'
+    )
+    caching_warmup: Optional[int] = Field(
+        3, description='Number of caching warmup steps'
+    )
+    clip_value: Optional[float] = Field(
+        3, description='CLIP value for generation control'
+    )
+    conditioning_frame_index: Optional[int] = Field(
+        0, description='Index of the conditioning frame'
+    )
+    cooldown_steps: Optional[int] = Field(
+        None, description='Number of cooldown steps (calculated based on num_frames)'
+    )
+    guidance_scale: Optional[float] = Field(
+        12.5, description='Guidance scale for generation control'
+    )
+    negative_prompt: Optional[str] = Field(None, description='Negative prompt text')
+    seed: Optional[int] = Field(
+        None, description='Random seed for generation (default: random)'
+    )
+    shift_value: Optional[float] = Field(
+        3, description='Shift value for generation control'
+    )
+    steps: Optional[int] = Field(80, description='Number of denoising steps')
+    use_guidance_schedule: Optional[bool] = Field(
+        True, description='Whether to use guidance scheduling'
+    )
+    use_negative_prompts: Optional[bool] = Field(
+        False, description='Whether to use negative prompts'
+    )
+    use_timestep_transform: Optional[bool] = Field(
+        True, description='Whether to use timestep transformation'
+    )
+    warmup_steps: Optional[int] = Field(
+        None, description='Number of warmup steps (calculated based on num_frames)'
+    )
+
+
+class ControlType(str, Enum):
+    motion_control = 'motion_control'
+    pose_control = 'pose_control'
+
+
+class MoonvalleyVideoToVideoRequest(BaseModel):
+    control_type: ControlType = Field(
+        ..., description='Supported types for video control'
+    )
+    inference_params: Optional[MoonvalleyVideoToVideoInferenceParams] = None
+    prompt_text: str = Field(..., description='Describes the video to generate')
+    video_url: str = Field(..., description='Url to control video')
+    webhook_url: Optional[str] = Field(
+        None, description='Optional webhook URL for notifications'
+    )
+
+
 class Moderation(str, Enum):
     low = 'low'
     auto = 'auto'
@@ -3107,6 +3259,23 @@ class LumaUpscaleVideoGenerationRequest(BaseModel):
     resolution: Optional[LumaVideoModelOutputResolution] = None
 
 
+class MoonvalleyImageToVideoRequest(MoonvalleyTextToVideoRequest):
+    keyframes: Optional[Dict[str, Keyframes]] = None
+
+
+class MoonvalleyResizeVideoRequest(MoonvalleyVideoToVideoRequest):
+    frame_position: Optional[List[int]] = Field(None, max_length=2, min_length=2)
+    frame_resolution: Optional[List[int]] = Field(None, max_length=2, min_length=2)
+    scale: Optional[List[int]] = Field(None, max_length=2, min_length=2)
+
+
+class MoonvalleyTextToImageRequest(BaseModel):
+    image_url: Optional[str] = None
+    inference_params: Optional[MoonvalleyTextToVideoInferenceParams] = None
+    prompt_text: Optional[str] = None
+    webhook_url: Optional[str] = None
+
+
 class OutputContent(RootModel[Union[OutputTextContent, OutputAudioContent]]):
     root: Union[OutputTextContent, OutputAudioContent]
 

comfy_api_nodes/nodes_moonvalley.py

@@ -0,0 +1,639 @@
+import logging
+from typing import Any, Callable, Optional, TypeVar
+import random
+import torch
+from comfy_api_nodes.util.validation_utils import get_image_dimensions, validate_image_dimensions, validate_video_dimensions
+
+
+from comfy_api_nodes.apis import (
+    MoonvalleyTextToVideoRequest,
+    MoonvalleyTextToVideoInferenceParams,
+    MoonvalleyVideoToVideoInferenceParams,
+    MoonvalleyVideoToVideoRequest,
+    MoonvalleyPromptResponse
+)
+from comfy_api_nodes.apis.client import (
+    ApiEndpoint,
+    HttpMethod,
+    SynchronousOperation,
+    PollingOperation,
+    EmptyRequest,
+)
+from comfy_api_nodes.apinode_utils import (
+    download_url_to_video_output,
+    upload_images_to_comfyapi,
+    upload_video_to_comfyapi,
+)
+from comfy_api_nodes.mapper_utils import model_field_to_node_input
+
+from comfy_api.input.video_types import VideoInput
+from comfy.comfy_types.node_typing import IO
+from comfy_api.input_impl import VideoFromFile
+import av
+import io
+
+API_UPLOADS_ENDPOINT = "/proxy/moonvalley/uploads"
+API_PROMPTS_ENDPOINT = "/proxy/moonvalley/prompts"
+API_VIDEO2VIDEO_ENDPOINT = "/proxy/moonvalley/prompts/video-to-video"
+API_TXT2VIDEO_ENDPOINT = "/proxy/moonvalley/prompts/text-to-video"
+API_IMG2VIDEO_ENDPOINT = "/proxy/moonvalley/prompts/image-to-video"
+
+MIN_WIDTH = 300
+MIN_HEIGHT = 300
+
+MAX_WIDTH = 10000
+MAX_HEIGHT = 10000
+
+MIN_VID_WIDTH = 300
+MIN_VID_HEIGHT = 300
+
+MAX_VID_WIDTH = 10000
+MAX_VID_HEIGHT = 10000
+
+MAX_VIDEO_SIZE = 1024 * 1024 * 1024  # 1 GB max for in-memory video processing
+
+MOONVALLEY_MAREY_MAX_PROMPT_LENGTH = 5000
+R = TypeVar("R")
+class MoonvalleyApiError(Exception):
+    """Base exception for Moonvalley API errors."""
+    pass
+
+def is_valid_task_creation_response(response: MoonvalleyPromptResponse) -> bool:
+    """Verifies that the initial response contains a task ID."""
+    return bool(response.id)
+
+def validate_task_creation_response(response) -> None:
+    if not is_valid_task_creation_response(response):
+        error_msg = f"Moonvalley Marey API: Initial request failed. Code: {response.code}, Message: {response.message}, Data: {response}"
+        logging.error(error_msg)
+        raise MoonvalleyApiError(error_msg)
+
+def get_video_from_response(response):
+    video = response.output_url
+    logging.info(
+        "Moonvalley Marey API: Task %s succeeded. Video URL: %s", response.id, video
+    )
+    return video
+
+
+def get_video_url_from_response(response) -> Optional[str]:
+    """Returns the first video url from the Moonvalley video generation task result.
+    Will not raise an error if the response is not valid.
+    """
+    if response:
+        return str(get_video_from_response(response))
+    else:
+        return None
+
+
+def poll_until_finished(
+    auth_kwargs: dict[str, str],
+    api_endpoint: ApiEndpoint[Any, R],
+    result_url_extractor: Optional[Callable[[R], str]] = None,
+    node_id: Optional[str] = None,
+) -> R:
+    """Polls the Moonvalley API endpoint until the task reaches a terminal state, then returns the response."""
+    return PollingOperation(
+        poll_endpoint=api_endpoint,
+        completed_statuses=[
+            "completed",
+        ],
+        max_poll_attempts=240,  # 64 minutes with 16s interval
+        poll_interval=16.0,
+        failed_statuses=["error"],
+        status_extractor=lambda response: (
+            response.status
+            if response and response.status
+            else None
+        ),
+        auth_kwargs=auth_kwargs,
+        result_url_extractor=result_url_extractor,
+        node_id=node_id,
+    ).execute()
+
+def validate_prompts(prompt:str, negative_prompt: str, max_length=MOONVALLEY_MAREY_MAX_PROMPT_LENGTH):
+    """Verifies that the prompt isn't empty and that neither prompt is too long."""
+    if not prompt:
+        raise ValueError("Positive prompt is empty")
+    if len(prompt) > max_length:
+        raise ValueError(f"Positive prompt is too long: {len(prompt)} characters")
+    if negative_prompt and len(negative_prompt) > max_length:
+        raise ValueError(
+            f"Negative prompt is too long: {len(negative_prompt)} characters"
+        )
+    return True
+
+def validate_input_media(width, height, with_frame_conditioning, num_frames_in=None):
+        # inference validation
+        # T = num_frames
+        # in all cases, the following must be true: T divisible by 16 and H,W by 8. in addition...
+        # with image conditioning: H*W must be divisible by 8192
+        # without image conditioning: T divisible by 32
+    if num_frames_in and not num_frames_in % 16 == 0 :
+        return False, (
+            "The input video total frame count must be divisible by 16!"
+        )
+
+    if height % 8 != 0 or width % 8 != 0:
+        return False, (
+            f"Height ({height}) and width ({width}) must be " "divisible by 8"
+        )
+
+    if with_frame_conditioning:
+        if (height * width) % 8192 != 0:
+            return False, (
+                f"Height * width ({height * width}) must be "
+                "divisible by 8192 for frame conditioning"
+            )
+    else:
+        if num_frames_in and not num_frames_in % 32 == 0 :
+            return False, (
+                "The input video total frame count must be divisible by 32!"
+            )
+
+
+def validate_input_image(image: torch.Tensor, with_frame_conditioning: bool=False) -> None:
+    """
+    Validates the input image adheres to the expectations of the API:
+    - The image resolution should not be less than 300*300px
+    - The aspect ratio of the image should be between 1:2.5 ~ 2.5:1
+
+    """
+    height, width = get_image_dimensions(image)
+    validate_input_media(width, height, with_frame_conditioning )
+    validate_image_dimensions(image, min_width=300, min_height=300, max_height=MAX_HEIGHT, max_width=MAX_WIDTH)
+
+def validate_input_video(video: VideoInput, num_frames_out: int, with_frame_conditioning: bool=False):
+    try:
+        width, height = video.get_dimensions()
+    except Exception as e:
+        logging.error("Error getting dimensions of video: %s", e)
+        raise ValueError(f"Cannot get video dimensions: {e}") from e
+
+    validate_input_media(width, height, with_frame_conditioning)
+    validate_video_dimensions(video, min_width=MIN_VID_WIDTH, min_height=MIN_VID_HEIGHT, max_width=MAX_VID_WIDTH, max_height=MAX_VID_HEIGHT)
+
+    trimmed_video = validate_input_video_length(video, num_frames_out)
+    return trimmed_video
+
+
+def validate_input_video_length(video: VideoInput, num_frames: int):
+
+    if video.get_duration() > 60:
+        raise MoonvalleyApiError("Input Video lenth should be less than 1min. Please trim.")
+
+    if num_frames == 128:
+       if video.get_duration() < 5:
+           raise MoonvalleyApiError("Input Video length is less than 5s. Please use a video longer than or equal to 5s.")
+       if video.get_duration() > 5:
+        #    trim video to 5s
+        video = trim_video(video, 5)
+    if num_frames == 256:
+        if video.get_duration() < 10:
+            raise MoonvalleyApiError("Input Video length is less than 10s. Please use a video longer than or equal to 10s.")
+        if video.get_duration() > 10:
+            # trim video to 10s
+            video = trim_video(video, 10)
+    return video
+
+def trim_video(video: VideoInput, duration_sec: float) -> VideoInput:
+    """
+    Returns a new VideoInput object trimmed from the beginning to the specified duration,
+    using av to avoid loading entire video into memory.
+
+    Args:
+        video: Input video to trim
+        duration_sec: Duration in seconds to keep from the beginning
+
+    Returns:
+        VideoFromFile object that owns the output buffer
+    """
+    output_buffer = io.BytesIO()
+
+    input_container = None
+    output_container = None
+
+    try:
+        # Get the stream source - this avoids loading entire video into memory
+        # when the source is already a file path
+        input_source = video.get_stream_source()
+
+        # Open containers
+        input_container = av.open(input_source, mode='r')
+        output_container = av.open(output_buffer, mode='w', format='mp4')
+
+        # Set up output streams for re-encoding
+        video_stream = None
+        audio_stream = None
+
+        for stream in input_container.streams:
+            logging.info(f"Found stream: type={stream.type}, class={type(stream)}")
+            if isinstance(stream, av.VideoStream):
+                # Create output video stream with same parameters
+                video_stream = output_container.add_stream('h264', rate=stream.average_rate)
+                video_stream.width = stream.width
+                video_stream.height = stream.height
+                video_stream.pix_fmt = 'yuv420p'
+                logging.info(f"Added video stream: {stream.width}x{stream.height} @ {stream.average_rate}fps")
+            elif isinstance(stream, av.AudioStream):
+                # Create output audio stream with same parameters
+                audio_stream = output_container.add_stream('aac', rate=stream.sample_rate)
+                audio_stream.sample_rate = stream.sample_rate
+                audio_stream.layout = stream.layout
+                logging.info(f"Added audio stream: {stream.sample_rate}Hz, {stream.channels} channels")
+
+        # Calculate target frame count that's divisible by 32
+        fps = input_container.streams.video[0].average_rate
+        estimated_frames = int(duration_sec * fps)
+        target_frames = (estimated_frames // 32) * 32  # Round down to nearest multiple of 32
+
+        if target_frames == 0:
+            raise ValueError("Video too short: need at least 32 frames for Moonvalley")
+
+        frame_count = 0
+        audio_frame_count = 0
+
+        # Decode and re-encode video frames
+        if video_stream:
+            for frame in input_container.decode(video=0):
+                if frame_count >= target_frames:
+                    break
+
+                # Re-encode frame
+                for packet in video_stream.encode(frame):
+                    output_container.mux(packet)
+                frame_count += 1
+
+            # Flush encoder
+            for packet in video_stream.encode():
+                output_container.mux(packet)
+
+            logging.info(f"Encoded {frame_count} video frames (target: {target_frames})")
+
+        # Decode and re-encode audio frames
+        if audio_stream:
+            input_container.seek(0)  # Reset to beginning for audio
+            for frame in input_container.decode(audio=0):
+                if frame.time >= duration_sec:
+                    break
+
+                # Re-encode frame
+                for packet in audio_stream.encode(frame):
+                    output_container.mux(packet)
+                audio_frame_count += 1
+
+            # Flush encoder
+            for packet in audio_stream.encode():
+                output_container.mux(packet)
+
+            logging.info(f"Encoded {audio_frame_count} audio frames")
+
+        # Close containers
+        output_container.close()
+        input_container.close()
+
+
+        # Return as VideoFromFile using the buffer
+        output_buffer.seek(0)
+        return VideoFromFile(output_buffer)
+
+    except Exception as e:
+        # Clean up on error
+        if input_container is not None:
+            input_container.close()
+        if output_container is not None:
+            output_container.close()
+        raise RuntimeError(f"Failed to trim video: {str(e)}") from e
+
+# --- BaseMoonvalleyVideoNode ---
+class BaseMoonvalleyVideoNode:
+    def parseWidthHeightFromRes(self, resolution: str):
+        # Accepts a string like "16:9 (1920 x 1080)" and returns width, height as a dict
+        res_map = {
+            "16:9 (1920 x 1080)": {"width": 1920, "height": 1080},
+            "9:16 (1080 x 1920)": {"width": 1080, "height": 1920},
+            "1:1 (1152 x 1152)": {"width": 1152, "height": 1152},
+            "4:3 (1440 x 1080)": {"width": 1440, "height": 1080},
+            "3:4 (1080 x 1440)": {"width": 1080, "height": 1440},
+            "21:9 (2560 x 1080)": {"width": 2560, "height": 1080},
+        }
+        if resolution in res_map:
+            return res_map[resolution]
+        else:
+            # Default to 1920x1080 if unknown
+            return {"width": 1920, "height": 1080}
+
+    def parseControlParameter(self, value):
+        control_map = {
+            "Motion Transfer": "motion_control",
+            "Canny": "canny_control",
+            "Pose Transfer": "pose_control",
+            "Depth": "depth_control"
+        }
+        if value in control_map:
+            return control_map[value]
+        else:
+            return control_map["Motion Transfer"]
+
+    def get_response(
+        self, task_id: str, auth_kwargs: dict[str, str], node_id: Optional[str] = None
+    ) -> MoonvalleyPromptResponse:
+        return poll_until_finished(
+            auth_kwargs,
+            ApiEndpoint(
+                path=f"{API_PROMPTS_ENDPOINT}/{task_id}",
+                method=HttpMethod.GET,
+                request_model=EmptyRequest,
+                response_model=MoonvalleyPromptResponse,
+            ),
+            result_url_extractor=get_video_url_from_response,
+            node_id=node_id,
+        )
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "prompt": model_field_to_node_input(
+                    IO.STRING, MoonvalleyTextToVideoRequest, "prompt_text",
+                    multiline=True
+                ),
+                "negative_prompt": model_field_to_node_input(
+                    IO.STRING,
+                    MoonvalleyTextToVideoInferenceParams,
+                    "negative_prompt",
+                    multiline=True,
+                    default="gopro, bright, contrast, static, overexposed, bright, vignette, artifacts, still, noise, texture, scanlines, videogame, 360 camera, VR, transition, flare, saturation, distorted, warped, wide angle, contrast, saturated, vibrant, glowing, cross dissolve, texture, videogame, saturation, cheesy, ugly hands, mutated hands, mutant, disfigured, extra fingers, blown out, horrible, blurry, worst quality, bad, transition, dissolve, cross-dissolve, melt, fade in, fade out, wobbly, weird, low quality, plastic, stock footage, video camera, boring, static",
+                ),
+
+                "resolution": (IO.COMBO, {
+                        "options": ["16:9 (1920 x 1080)",
+                                    "9:16 (1080 x 1920)",
+                                    "1:1 (1152 x 1152)",
+                                    "4:3 (1440 x 1080)",
+                                    "3:4 (1080 x 1440)",
+                                    "21:9 (2560 x 1080)"],
+                        "default": "16:9 (1920 x 1080)",
+                        "tooltip": "Resolution of the output video",
+                    }),
+                # "length": (IO.COMBO,{"options":['5s','10s'], "default": '5s'}),
+                "prompt_adherence": model_field_to_node_input(IO.FLOAT,MoonvalleyTextToVideoInferenceParams,"guidance_scale",default=7.0, step=1, min=1, max=20),
+                "seed": model_field_to_node_input(IO.INT,MoonvalleyTextToVideoInferenceParams, "seed", default=random.randint(0, 2**32 - 1), min=0, max=4294967295, step=1, display="number", tooltip="Random seed value", control_after_generate=True),
+                "steps": model_field_to_node_input(IO.INT, MoonvalleyTextToVideoInferenceParams, "steps", default=100, min=1, max=100),
+            },
+            "hidden": {
+                "auth_token": "AUTH_TOKEN_COMFY_ORG",
+                "comfy_api_key": "API_KEY_COMFY_ORG",
+                "unique_id": "UNIQUE_ID",
+            },
+            "optional": {
+                "image": model_field_to_node_input(
+                    IO.IMAGE,
+                    MoonvalleyTextToVideoRequest,
+                    "image_url",
+                    tooltip="The reference image used to generate the video",
+                ),
+            }
+        }
+
+    RETURN_TYPES = ("STRING",)
+    FUNCTION = "generate"
+    CATEGORY = "api node/video/Moonvalley Marey"
+    API_NODE = True
+
+    def generate(self, **kwargs):
+        return None
+
+# --- MoonvalleyImg2VideoNode ---
+class MoonvalleyImg2VideoNode(BaseMoonvalleyVideoNode):
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return super().INPUT_TYPES()
+
+    RETURN_TYPES = ("VIDEO",)
+    RETURN_NAMES = ("video",)
+    DESCRIPTION = "Moonvalley Marey Image to Video Node"
+
+    def generate(self, prompt, negative_prompt, unique_id: Optional[str] = None, **kwargs):
+        image = kwargs.get("image", None)
+        if (image is None):
+            raise MoonvalleyApiError("image is required")
+        total_frames = get_total_frames_from_length()
+
+        validate_input_image(image,True)
+        validate_prompts(prompt, negative_prompt, MOONVALLEY_MAREY_MAX_PROMPT_LENGTH)
+        width_height = self.parseWidthHeightFromRes(kwargs.get("resolution"))
+
+        inference_params=MoonvalleyTextToVideoInferenceParams(
+                    negative_prompt=negative_prompt,
+                    steps=kwargs.get("steps"),
+                    seed=kwargs.get("seed"),
+                    guidance_scale=kwargs.get("prompt_adherence"),
+                    num_frames=total_frames,
+                    width=width_height.get("width"),
+                    height=width_height.get("height"),
+                    use_negative_prompts=True
+                )
+        """Upload image to comfy backend to have a URL available for further processing"""
+        # Get MIME type from tensor - assuming PNG format for image tensors
+        mime_type = "image/png"
+
+        image_url = upload_images_to_comfyapi(image, max_images=1, auth_kwargs=kwargs, mime_type=mime_type)[0]
+
+        request = MoonvalleyTextToVideoRequest(
+                image_url=image_url,
+                prompt_text=prompt,
+                inference_params=inference_params
+            )
+        initial_operation = SynchronousOperation(
+            endpoint=ApiEndpoint(path=API_IMG2VIDEO_ENDPOINT,
+                                 method=HttpMethod.POST,
+                                 request_model=MoonvalleyTextToVideoRequest,
+                                 response_model=MoonvalleyPromptResponse
+                                 ),
+            request=request,
+            auth_kwargs=kwargs,
+        )
+        task_creation_response = initial_operation.execute()
+        validate_task_creation_response(task_creation_response)
+        task_id = task_creation_response.id
+
+        final_response = self.get_response(
+            task_id, auth_kwargs=kwargs, node_id=unique_id
+        )
+        video = download_url_to_video_output(final_response.output_url)
+        return (video, )
+
+# --- MoonvalleyVid2VidNode ---
+class MoonvalleyVideo2VideoNode(BaseMoonvalleyVideoNode):
+    def __init__(self):
+        super().__init__()
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        input_types = super().INPUT_TYPES()
+        for param in ["resolution", "image"]:
+            if param in input_types["required"]:
+                del input_types["required"][param]
+            if param in input_types["optional"]:
+                del input_types["optional"][param]
+        input_types["optional"] = {
+                "video": (IO.VIDEO, {"default": "", "multiline": False, "tooltip": "The reference video used to generate the output video. Input a 5s video for 128 frames and a 10s video for 256 frames. Longer videos will be trimmed automatically."}),
+                "control_type": (
+                    ["Motion Transfer", "Pose Transfer"],
+                    {"default": "Motion Transfer"},
+                ),
+                "motion_intensity": (
+                    "INT",
+                    {
+                        "default": 100,
+                        "step": 1,
+                        "min": 0,
+                        "max": 100,
+                        "tooltip": "Only used if control_type is 'Motion Transfer'",
+                    },
+                )
+            }
+
+        return input_types
+
+    RETURN_TYPES = ("VIDEO",)
+    RETURN_NAMES = ("video",)
+
+    def generate(self, prompt, negative_prompt, unique_id: Optional[str] = None, **kwargs):
+        video = kwargs.get("video")
+        num_frames = get_total_frames_from_length()
+
+        if not video :
+            raise MoonvalleyApiError("video is required")
+
+
+        """Validate video input"""
+        video_url=""
+        if video:
+            validated_video = validate_input_video(video, num_frames, False)
+            video_url = upload_video_to_comfyapi(validated_video, auth_kwargs=kwargs)
+
+        control_type = kwargs.get("control_type")
+        motion_intensity = kwargs.get("motion_intensity")
+
+        """Validate prompts and inference input"""
+        validate_prompts(prompt, negative_prompt)
+        inference_params=MoonvalleyVideoToVideoInferenceParams(
+            negative_prompt=negative_prompt,
+            steps=kwargs.get("steps"),
+            seed=kwargs.get("seed"),
+            guidance_scale=kwargs.get("prompt_adherence"),
+            control_params={'motion_intensity': motion_intensity}
+        )
+
+        control = self.parseControlParameter(control_type)
+
+        request = MoonvalleyVideoToVideoRequest(
+                control_type=control,
+                video_url=video_url,
+                prompt_text=prompt,
+                inference_params=inference_params
+            )
+
+        initial_operation = SynchronousOperation(
+            endpoint=ApiEndpoint(path=API_VIDEO2VIDEO_ENDPOINT,
+                                 method=HttpMethod.POST,
+                                 request_model=MoonvalleyVideoToVideoRequest,
+                                 response_model=MoonvalleyPromptResponse
+                                 ),
+            request=request,
+            auth_kwargs=kwargs,
+        )
+        task_creation_response = initial_operation.execute()
+        validate_task_creation_response(task_creation_response)
+        task_id = task_creation_response.id
+
+        final_response = self.get_response(
+            task_id, auth_kwargs=kwargs, node_id=unique_id
+        )
+
+        video = download_url_to_video_output(final_response.output_url)
+
+        return (video, )
+
+# --- MoonvalleyTxt2VideoNode ---
+class MoonvalleyTxt2VideoNode(BaseMoonvalleyVideoNode):
+    def __init__(self):
+        super().__init__()
+
+    RETURN_TYPES = ("VIDEO",)
+    RETURN_NAMES = ("video",)
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        input_types = super().INPUT_TYPES()
+        # Remove image-specific parameters
+        for param in ["image"]:
+            if param in input_types["optional"]:
+                del input_types["optional"][param]
+        return input_types
+
+    def generate(self, prompt, negative_prompt, unique_id: Optional[str] = None, **kwargs):
+        validate_prompts(prompt, negative_prompt, MOONVALLEY_MAREY_MAX_PROMPT_LENGTH)
+        width_height = self.parseWidthHeightFromRes(kwargs.get("resolution"))
+        num_frames = get_total_frames_from_length()
+
+        inference_params=MoonvalleyTextToVideoInferenceParams(
+                    negative_prompt=negative_prompt,
+                    steps=kwargs.get("steps"),
+                    seed=kwargs.get("seed"),
+                    guidance_scale=kwargs.get("prompt_adherence"),
+                    num_frames=num_frames,
+                    width=width_height.get("width"),
+                    height=width_height.get("height"),
+                )
+        request = MoonvalleyTextToVideoRequest(
+                prompt_text=prompt,
+                inference_params=inference_params
+            )
+
+        initial_operation = SynchronousOperation(
+            endpoint=ApiEndpoint(path=API_TXT2VIDEO_ENDPOINT,
+                                 method=HttpMethod.POST,
+                                 request_model=MoonvalleyTextToVideoRequest,
+                                 response_model=MoonvalleyPromptResponse
+                                 ),
+            request=request,
+            auth_kwargs=kwargs,
+        )
+        task_creation_response = initial_operation.execute()
+        validate_task_creation_response(task_creation_response)
+        task_id = task_creation_response.id
+
+        final_response = self.get_response(
+            task_id, auth_kwargs=kwargs, node_id=unique_id
+        )
+
+        video = download_url_to_video_output(final_response.output_url)
+        return (video, )
+
+
+
+NODE_CLASS_MAPPINGS = {
+    "MoonvalleyImg2VideoNode": MoonvalleyImg2VideoNode,
+    "MoonvalleyTxt2VideoNode": MoonvalleyTxt2VideoNode,
+    # "MoonvalleyVideo2VideoNode": MoonvalleyVideo2VideoNode,
+}
+
+
+NODE_DISPLAY_NAME_MAPPINGS = {
+    "MoonvalleyImg2VideoNode": "Moonvalley Marey Image to Video",
+    "MoonvalleyTxt2VideoNode": "Moonvalley Marey Text to Video",
+    # "MoonvalleyVideo2VideoNode": "Moonvalley Marey Video to Video",
+}
+
+def get_total_frames_from_length(length="5s"):
+    # if length == '5s':
+    #     return 128
+    # elif length == '10s':
+    #     return 256
+    return 128
+    # else:
+    #     raise MoonvalleyApiError("length is required")

comfy_extras/nodes_audio.py

@@ -133,14 +133,6 @@ def save_audio(self, audio, filename_prefix="ComfyUI", format="flac", prompt=Non
             if sample_rate != audio["sample_rate"]:
                 waveform = torchaudio.functional.resample(waveform, audio["sample_rate"], sample_rate)
 
-        # Create in-memory WAV buffer
-        wav_buffer = io.BytesIO()
-        torchaudio.save(wav_buffer, waveform, sample_rate, format="WAV")
-        wav_buffer.seek(0)  # Rewind for reading
-
-        # Use PyAV to convert and add metadata
-        input_container = av.open(wav_buffer)
-
         # Create output with specified format
         output_buffer = io.BytesIO()
         output_container = av.open(output_buffer, mode='w', format=format)
@@ -150,7 +142,6 @@ def save_audio(self, audio, filename_prefix="ComfyUI", format="flac", prompt=Non
             output_container.metadata[key] = value
 
         # Set up the output stream with appropriate properties
-        input_container.streams.audio[0]
         if format == "opus":
             out_stream = output_container.add_stream("libopus", rate=sample_rate)
             if quality == "64k":
@@ -175,18 +166,16 @@ def save_audio(self, audio, filename_prefix="ComfyUI", format="flac", prompt=Non
         else: #format == "flac":
             out_stream = output_container.add_stream("flac", rate=sample_rate)
 
-
-        # Copy frames from input to output
-        for frame in input_container.decode(audio=0):
-            frame.pts = None  # Let PyAV handle timestamps
-            output_container.mux(out_stream.encode(frame))
+        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()
-        input_container.close()
 
         # Write the output to file
         output_buffer.seek(0)

comfy_extras/nodes_images.py

@@ -583,6 +583,49 @@ class GetImageSize:
 
         return width, height, batch_size
 
+class ImageRotate:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": { "image": (IO.IMAGE,),
+                              "rotation": (["none", "90 degrees", "180 degrees", "270 degrees"],),
+                              }}
+    RETURN_TYPES = (IO.IMAGE,)
+    FUNCTION = "rotate"
+
+    CATEGORY = "image/transform"
+
+    def rotate(self, image, rotation):
+        rotate_by = 0
+        if rotation.startswith("90"):
+            rotate_by = 1
+        elif rotation.startswith("180"):
+            rotate_by = 2
+        elif rotation.startswith("270"):
+            rotate_by = 3
+
+        image = torch.rot90(image, k=rotate_by, dims=[2, 1])
+        return (image,)
+
+class ImageFlip:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": { "image": (IO.IMAGE,),
+                              "flip_method": (["x-axis: vertically", "y-axis: horizontally"],),
+                              }}
+    RETURN_TYPES = (IO.IMAGE,)
+    FUNCTION = "flip"
+
+    CATEGORY = "image/transform"
+
+    def flip(self, image, flip_method):
+        if flip_method.startswith("x"):
+            image = torch.flip(image, dims=[1])
+        elif flip_method.startswith("y"):
+            image = torch.flip(image, dims=[2])
+
+        return (image,)
+
+
 NODE_CLASS_MAPPINGS = {
     "ImageCrop": ImageCrop,
     "RepeatImageBatch": RepeatImageBatch,
@@ -594,4 +637,6 @@ NODE_CLASS_MAPPINGS = {
     "ImageStitch": ImageStitch,
     "ResizeAndPadImage": ResizeAndPadImage,
     "GetImageSize": GetImageSize,
+    "ImageRotate": ImageRotate,
+    "ImageFlip": ImageFlip,
 }

comfy_extras/nodes_load_3d.py

@@ -5,6 +5,8 @@ import os
 from comfy.comfy_types import IO
 from comfy_api.input_impl import VideoFromFile
 
+from pathlib import Path
+
 
 def normalize_path(path):
     return path.replace('\\', '/')
@@ -16,7 +18,14 @@ class Load3D():
 
         os.makedirs(input_dir, exist_ok=True)
 
-        files = [normalize_path(os.path.join("3d", f)) for f in os.listdir(input_dir) if f.endswith(('.gltf', '.glb', '.obj', '.fbx', '.stl'))]
+        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 {"required": {
             "model_file": (sorted(files), {"file_upload": True}),
@@ -61,7 +70,14 @@ class Load3DAnimation():
 
         os.makedirs(input_dir, exist_ok=True)
 
-        files = [normalize_path(os.path.join("3d", f)) for f in os.listdir(input_dir) if f.endswith(('.gltf', '.glb', '.fbx'))]
+        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 {"required": {
             "model_file": (sorted(files), {"file_upload": True}),

comfy_extras/nodes_lt.py

@@ -134,8 +134,8 @@ class LTXVAddGuide:
         _, 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:
-            frame_idx = frame_idx // time_scale_factor * time_scale_factor # frame index must be divisible by 8
+        if guide_length > 1 and frame_idx != 0:
+            frame_idx = (frame_idx - 1) // time_scale_factor * time_scale_factor + 1 # frame index - 1 must be divisible by 8 or frame_idx == 0
 
         latent_idx = (frame_idx + time_scale_factor - 1) // time_scale_factor
 
@@ -144,7 +144,7 @@ class LTXVAddGuide:
     def add_keyframe_index(self, cond, frame_idx, guiding_latent, scale_factors):
         keyframe_idxs, _ = get_keyframe_idxs(cond)
         _, latent_coords = self._patchifier.patchify(guiding_latent)
-        pixel_coords = latent_to_pixel_coords(latent_coords, scale_factors, True)
+        pixel_coords = latent_to_pixel_coords(latent_coords, scale_factors, causal_fix=frame_idx == 0)  # we need the causal fix only if we're placing the new latents at index 0
         pixel_coords[:, 0] += frame_idx
         if keyframe_idxs is None:
             keyframe_idxs = pixel_coords

comfy_extras/nodes_mask.py

@@ -152,7 +152,7 @@ class ImageColorToMask:
     def image_to_mask(self, image, color):
         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]
-        mask = torch.where(temp == color, 255, 0).float()
+        mask = torch.where(temp == color, 1.0, 0).float()
         return (mask,)
 
 class SolidMask:

comfy_extras/nodes_slg.py

@@ -78,7 +78,75 @@ class SkipLayerGuidanceDiT:
 
         return (m, )
 
+class SkipLayerGuidanceDiTSimple:
+    '''
+    Simple version of the SkipLayerGuidanceDiT node that only modifies the uncond pass.
+    '''
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {"model": ("MODEL", ),
+                             "double_layers": ("STRING", {"default": "7, 8, 9", "multiline": False}),
+                             "single_layers": ("STRING", {"default": "7, 8, 9", "multiline": False}),
+                             "start_percent": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001}),
+                             "end_percent": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.001}),
+                                }}
+    RETURN_TYPES = ("MODEL",)
+    FUNCTION = "skip_guidance"
+    EXPERIMENTAL = True
+
+    DESCRIPTION = "Simple version of the SkipLayerGuidanceDiT node that only modifies the uncond pass."
+
+    CATEGORY = "advanced/guidance"
+
+    def skip_guidance(self, 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 (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 (m, )
 
 NODE_CLASS_MAPPINGS = {
     "SkipLayerGuidanceDiT": SkipLayerGuidanceDiT,
+    "SkipLayerGuidanceDiTSimple": SkipLayerGuidanceDiTSimple,
 }

comfyui_version.py

@@ -1,3 +1,3 @@
 # This file is automatically generated by the build process when version is
 # updated in pyproject.toml.
-__version__ = "0.3.43"
+__version__ = "0.3.44"

nodes.py

@@ -2310,6 +2310,7 @@ def init_builtin_api_nodes():
         "nodes_pika.py",
         "nodes_runway.py",
         "nodes_tripo.py",
+        "nodes_moonvalley.py",
         "nodes_rodin.py",
         "nodes_gemini.py",
     ]

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ComfyUI"
-version = "0.3.43"
+version = "0.3.44"
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.9"

requirements.txt

@@ -1,6 +1,6 @@
 comfyui-frontend-package==1.23.4
-comfyui-workflow-templates==0.1.31
-comfyui-embedded-docs==0.2.3
+comfyui-workflow-templates==0.1.35
+comfyui-embedded-docs==0.2.4
 torch
 torchsde
 torchvision