- Initial context windowing with FreeNoise noise shuffling mainly for vid2vid and pose2vid pipelines for longer generations, haven't figured it out for img2vid yet
- GGUF models and tiled encoding for I2V and pose pipelines (thanks to MinusZoneAI)
- sageattention support (Linux only) for a speed boost, I experienced ~20-30% increase with it, stacks with fp8 fast mode, doesn't need compiling
- Support CogVideoX-Fun 1.1 and it's pose models with additional control strenght and application step settings, this model's input does NOT have to be just dwpose skeletons, just about anything can work
- Support LoRAs
https://github.com/kijai/ComfyUI-CogVideoXWrapper/tree/main
打开工作流
下载
节点信息
Primitive Nodes (1)
CLIPLoader
Custom Nodes (16)
AddLabel
CogVideoControlImageEncode
CogVideoDecode
CogVideoTextEncode
CogVideoXFunControlSampler
DWPreprocessor
DownloadAndLoadCogVideoGGUFModel
GetImageSizeAndCount
INTConstant
ImageConcatMulti
ImageResizeKJ
RH_Prompter
ShowText|pysssss
VHS_LoadVideo
VHS_VideoCombine
WidgetToString