comfyanonymous/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-04-23 16:09:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into worksplit-multigpu

Browse Source
This commit is contained in:
Jedrzej Kosinski
2025-03-09 00:00:38 -06:00
parent 6dca17bd2d 7395b0c0d1
commit 6e144b98c4
47 changed files with 1179 additions and 315 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
comfy_extras/nodes_audio.py
View File

@@ -1,3 +1,5 @@
from __future__ import annotations
import torchaudio
import torch
import comfy.model_management
@@ -10,6 +12,7 @@ import random
import hashlib
import node_helpers
from comfy.cli_args import args
from comfy.comfy_types import FileLocator
class EmptyLatentAudio:
def __init__(self):
@@ -164,7 +167,7 @@ class SaveAudio:
def save_audio(self, audio, filename_prefix="ComfyUI", prompt=None, extra_pnginfo=None):
filename_prefix += self.prefix_append
full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir)
results = list()
results: list[FileLocator] = []
metadata = {}
if not args.disable_metadata:

16
comfy_extras/nodes_custom_sampler.py
View File

@@ -454,7 +454,7 @@ class SamplerCustom:
return {"required":
{"model": ("MODEL",),
"add_noise": ("BOOLEAN", {"default": True}),
"noise_seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
"noise_seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff, "control_after_generate": True}),
"cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01}),
"positive": ("CONDITIONING", ),
"negative": ("CONDITIONING", ),
@@ -605,10 +605,16 @@ class DisableNoise:
class RandomNoise(DisableNoise):
@classmethod
def INPUT_TYPES(s):
return {"required":{
"noise_seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff}),
}
}
return {
"required": {
"noise_seed": ("INT", {
"default": 0,
"min": 0,
"max": 0xffffffffffffffff,
"control_after_generate": True,
}),
}
}
def get_noise(self, noise_seed):
return (Noise_RandomNoise(noise_seed),)

77
comfy_extras/nodes_hunyuan.py
View File

@@ -1,4 +1,5 @@
import nodes
import node_helpers
import torch
import comfy.model_management
@@ -38,7 +39,83 @@ class EmptyHunyuanLatentVideo:
latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
return ({"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:
@classmethod
def INPUT_TYPES(s):
return {"required": {
"clip": ("CLIP", ),
"clip_vision_output": ("CLIP_VISION_OUTPUT", ),
"prompt": ("STRING", {"multiline": True, "dynamicPrompts": True}),
"image_interleave": ("INT", {"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."}),
}}
RETURN_TYPES = ("CONDITIONING",)
FUNCTION = "encode"
CATEGORY = "advanced/conditioning"
def encode(self, 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 (clip.encode_from_tokens_scheduled(tokens), )
class HunyuanImageToVideo:
@classmethod
def INPUT_TYPES(s):
return {"required": {"positive": ("CONDITIONING", ),
"vae": ("VAE", ),
"width": ("INT", {"default": 848, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
"height": ("INT", {"default": 480, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
"length": ("INT", {"default": 53, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 4}),
"batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
"guidance_type": (["v1 (concat)", "v2 (replace)"], )
},
"optional": {"start_image": ("IMAGE", ),
}}
RETURN_TYPES = ("CONDITIONING", "LATENT")
RETURN_NAMES = ("positive", "latent")
FUNCTION = "encode"
CATEGORY = "conditioning/video_models"
def encode(self, 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}
else:
cond = {'guiding_frame_index': 0}
latent[:, :, :concat_latent_image.shape[2]] = concat_latent_image
out_latent["noise_mask"] = mask
positive = node_helpers.conditioning_set_values(positive, cond)
out_latent["samples"] = latent
return (positive, out_latent)
NODE_CLASS_MAPPINGS = {
"CLIPTextEncodeHunyuanDiT": CLIPTextEncodeHunyuanDiT,
"TextEncodeHunyuanVideo_ImageToVideo": TextEncodeHunyuanVideo_ImageToVideo,
"EmptyHunyuanLatentVideo": EmptyHunyuanLatentVideo,
"HunyuanImageToVideo": HunyuanImageToVideo,
}

6
comfy_extras/nodes_images.py
View File

@@ -1,3 +1,5 @@
from __future__ import annotations
import nodes
import folder_paths
from comfy.cli_args import args
@@ -9,6 +11,8 @@ import numpy as np
import json
import os
from comfy.comfy_types import FileLocator
MAX_RESOLUTION = nodes.MAX_RESOLUTION
class ImageCrop:
@@ -99,7 +103,7 @@ class SaveAnimatedWEBP:
method = self.methods.get(method)
filename_prefix += self.prefix_append
full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir, images[0].shape[1], images[0].shape[0])
results = list()
results: list[FileLocator] = []
pil_images = []
for image in images:
i = 255. * image.cpu().numpy()

289
comfy_extras/nodes_lt.py
View File

@@ -1,9 +1,14 @@
import io
import nodes
import node_helpers
import torch
import comfy.model_management
import comfy.model_sampling
import comfy.utils
import math
import numpy as np
import av
from comfy.ldm.lightricks.symmetric_patchifier import SymmetricPatchifier, latent_to_pixel_coords
class EmptyLTXVLatentVideo:
@classmethod
@@ -33,7 +38,6 @@ class LTXVImgToVideo:
"height": ("INT", {"default": 512, "min": 64, "max": nodes.MAX_RESOLUTION, "step": 32}),
"length": ("INT", {"default": 97, "min": 9, "max": nodes.MAX_RESOLUTION, "step": 8}),
"batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
"image_noise_scale": ("FLOAT", {"default": 0.15, "min": 0, "max": 1.0, "step": 0.01, "tooltip": "Amount of noise to apply on conditioning image latent."})
}}
RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
@@ -42,16 +46,217 @@ class LTXVImgToVideo:
CATEGORY = "conditioning/video_models"
FUNCTION = "generate"
def generate(self, positive, negative, image, vae, width, height, length, batch_size, image_noise_scale):
def generate(self, positive, negative, image, vae, width, height, length, batch_size):
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)
positive = node_helpers.conditioning_set_values(positive, {"guiding_latent": t, "guiding_latent_noise_scale": image_noise_scale})
negative = node_helpers.conditioning_set_values(negative, {"guiding_latent": t, "guiding_latent_noise_scale": image_noise_scale})
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
return (positive, negative, {"samples": latent}, )
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]] = 0
return (positive, negative, {"samples": latent, "noise_mask": conditioning_latent_frames_mask}, )
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
noise_mask = torch.ones(
(batch_size, 1, latent_length, 1, 1),
dtype=torch.float32,
device=latent_image.device,
)
else:
noise_mask = noise_mask.clone()
return noise_mask
def get_keyframe_idxs(cond):
keyframe_idxs = conditioning_get_any_value(cond, "keyframe_idxs", None)
if keyframe_idxs is None:
return None, 0
num_keyframes = torch.unique(keyframe_idxs[:, 0]).shape[0]
return keyframe_idxs, num_keyframes
class LTXVAddGuide:
@classmethod
def INPUT_TYPES(s):
return {"required": {"positive": ("CONDITIONING", ),
"negative": ("CONDITIONING", ),
"vae": ("VAE",),
"latent": ("LATENT",),
"image": ("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."}),
"frame_idx": ("INT", {"default": 0, "min": -9999, "max": 9999,
"tooltip": "Frame index to start the conditioning at. Must be divisible by 8. " \
"If a frame is not divisible by 8, it will be rounded down to the nearest multiple of 8. " \
"Negative values are counted from the end of the video."}),
"strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01}),
}
}
RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
RETURN_NAMES = ("positive", "negative", "latent")
CATEGORY = "conditioning/video_models"
FUNCTION = "generate"
def __init__(self):
self._num_prefix_frames = 2
self._patchifier = SymmetricPatchifier(1)
def encode(self, 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
def get_latent_index(self, cond, latent_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) * 8 + 1 + frame_idx, 0)
frame_idx = frame_idx // time_scale_factor * time_scale_factor # frame index must be divisible by 8
latent_idx = (frame_idx + time_scale_factor - 1) // time_scale_factor
return frame_idx, latent_idx
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[:, 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})
def append_keyframe(self, positive, negative, frame_idx, latent_image, noise_mask, guiding_latent, strength, scale_factors):
positive = self.add_keyframe_index(positive, frame_idx, guiding_latent, scale_factors)
negative = self.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)
noise_mask = torch.cat([noise_mask, mask], dim=2)
return positive, negative, latent_image, noise_mask
def replace_latent_frames(self, 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
def generate(self, 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 = self.encode(vae, latent_width, latent_height, image, scale_factors)
frame_idx, latent_idx = self.get_latent_index(positive, latent_length, 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(self._num_prefix_frames, t.shape[2])
positive, negative, latent_image, noise_mask = self.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 (positive, negative, {"samples": latent_image, "noise_mask": noise_mask},)
latent_image, noise_mask = self.replace_latent_frames(
latent_image,
noise_mask,
t,
latent_idx,
strength,
)
return (positive, negative, {"samples": latent_image, "noise_mask": noise_mask},)
class LTXVCropGuides:
@classmethod
def INPUT_TYPES(s):
return {"required": {"positive": ("CONDITIONING", ),
"negative": ("CONDITIONING", ),
"latent": ("LATENT",),
}
}
RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
RETURN_NAMES = ("positive", "negative", "latent")
CATEGORY = "conditioning/video_models"
FUNCTION = "crop"
def __init__(self):
self._patchifier = SymmetricPatchifier(1)
def crop(self, 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 (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 (positive, negative, {"samples": latent_image, "noise_mask": noise_mask},)
class LTXVConditioning:
@@ -174,6 +379,77 @@ class LTXVScheduler:
return (sigmas,)
def encode_single_frame(output_file, image_array: np.ndarray, crf):
container = av.open(output_file, "w", format="mp4")
try:
stream = container.add_stream(
"h264", 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 io.BytesIO() as output_file:
encode_single_frame(output_file, image_array, crf)
video_bytes = output_file.getvalue()
with io.BytesIO(video_bytes) as video_file:
image_array = decode_single_frame(video_file)
tensor = torch.tensor(image_array, dtype=image.dtype, device=image.device) / 255.0
return tensor
class LTXVPreprocess:
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"image": ("IMAGE",),
"img_compression": (
"INT",
{
"default": 35,
"min": 0,
"max": 100,
"tooltip": "Amount of compression to apply on image.",
},
),
}
}
FUNCTION = "preprocess"
RETURN_TYPES = ("IMAGE",)
RETURN_NAMES = ("output_image",)
CATEGORY = "image"
def preprocess(self, image, img_compression):
if img_compression > 0:
output_images = []
for i in range(image.shape[0]):
output_images.append(preprocess(image[i], img_compression))
return (torch.stack(output_images),)
NODE_CLASS_MAPPINGS = {
"EmptyLTXVLatentVideo": EmptyLTXVLatentVideo,
@@ -181,4 +457,7 @@ NODE_CLASS_MAPPINGS = {
"ModelSamplingLTXV": ModelSamplingLTXV,
"LTXVConditioning": LTXVConditioning,
"LTXVScheduler": LTXVScheduler,
"LTXVAddGuide": LTXVAddGuide,
"LTXVPreprocess": LTXVPreprocess,
"LTXVCropGuides": LTXVCropGuides,
}

5
comfy_extras/nodes_video.py
View File

@@ -1,9 +1,12 @@
from __future__ import annotations
import os
import av
import torch
import folder_paths
import json
from fractions import Fraction
from comfy.comfy_types import FileLocator
class SaveWEBM:
@@ -62,7 +65,7 @@ class SaveWEBM:
container.mux(stream.encode())
container.close()
results = [{
results: list[FileLocator] = [{
"filename": file,
"subfolder": subfolder,
"type": self.type