Core nodes (7): BlendVideoChunks, BlendLatentChunks, ConcatVideoChunks, ExtractVideoChunk, GetFrameByIndex, GetFrameRange, VideoChunkPlanner Wan-specific nodes (2): WanChunkedI2VSampler (all-in-one with FLF/multi-keyframe), WanVideoChunkCalculator Rolling-reference approach solves context window reversal in I2V models.
10 lines
330 B
TOML
10 lines
330 B
TOML
[project]
|
|
name = "ComfyUI_VideoChunkTools"
|
|
version = "1.0.0"
|
|
description = "ComfyUI nodes for generating long videos by splitting into overlapping chunks with rolling reference frames."
|
|
license = {text = "MIT"}
|
|
requires-python = ">=3.10"
|
|
|
|
[project.urls]
|
|
Repository = "https://github.com/gregtee2/ComfyUI_VideoChunkTools"
|