CogVideo重大更新
Refactored the Fun version's sampler to accept any resolution, this should make it 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
Launch on cloud
Powered By RTX 4090
Nodes Information
Primitive Nodes (2)
CLIPLoader
LoadImage
Custom Nodes (21)
CogVideoDecode
CogVideoImageEncodeFunInP
CogVideoLoraSelect
CogVideoSampler
CogVideoTextEncode
DownloadAndLoadCogVideoModel
DownloadAndLoadFlorence2Model
Florence2Run
GetNode
INTConstant
ImageBatchMulti
ImageFlip+
ImageResizeKJ
JoinStrings
PrimitiveNode
RIFE VFI
ReverseImageBatch
SetNode
ShowText|pysssss
StringConstantMultiline
VHS_VideoCombine