CogVideo major update Refactored the Fun version's sampler to accept any resolution, this should make it a lot simpler to use with Tora. BREAKS OLD WORKFLOWS, old FunSampler nodes need to be remade. The old bucket resizing is now on it's own node (CogVideoXFunResizeToClosestBucket) to keep the functionality, I honestly don't know if it matters at all, but just in case. Fun version's vid2vid is now also in the same node, the old vid2vid node is deprecated. Added support for FasterCache, this trades more VRAM use for speed with slight quality hit, similar to PAB: https://github.com/Vchitect/FasterCache Improved torch.compile support, it actually works now
Open
Download
Nodes Information
Primitive Nodes (3)
CLIPLoader
LoadImage
PreviewImage
Custom Nodes (10)
CogVideoDecode
CogVideoImageEncode
CogVideoLoraSelect
CogVideoSampler
CogVideoTextEncode
CogVideoXFasterCache
DownloadAndLoadCogVideoModel
ImageResizeKJ
RIFE VFI
VHS_VideoCombine