Phr00t
Phr00t
> > > https://huggingface.co/MinusZoneAI/ComfyUI-CogVideoX-MZ > > > > > > Hi @wailovet can you upload Q8 GGUF version ? > > Thank in advance > > I don't have the...
> > > > > https://huggingface.co/MinusZoneAI/ComfyUI-CogVideoX-MZ > > > > > > > > > > > > Hi @wailovet can you upload Q8 GGUF version ? > > >...
> > > > > > > https://huggingface.co/MinusZoneAI/ComfyUI-CogVideoX-MZ > > > > > > > > > > > > > > > > > > Hi @wailovet can you...
> > Looks like it is just referred to as "K" and not "K_M" in the source files. You want to use the "K" methods over the "_0" methods, which...
> > > > Looks like it is just referred to as "K" and not "K_M" in the source files. You want to use the "K" methods over the "_0"...
> > The tiled_vae doesn't seem to support every available resolution, it should work with the CogVideoX default, but probably not with all of the resolutinos CogVideoX-Fun allows. I don't...
Apparently there is tons of logic to pick faces in the backend, but that isn't exposed via this node. I "fixed" this myself by forcing the "best" face to be...
Same problem reported here: https://github.com/Lightricks/LTX-Video-Q8-Kernels/issues/2 No solution found yet.
https://github.com/kijai/ComfyUI-CogVideoXWrapper/commit/3efe90ba35467fb0ad92d97676d3ee140d872c2f Woah! Are there actually LORAs available to try somewhere, or is this aspirational support?