Josef Kuchař

Maybe, but I'm sure that there will be some implementation flaws

that would be great

> cc @rmasiso since they were looking into it too [here](https://github.com/huggingface/diffusers/pull/5928#issuecomment-1848846131). > > I will be referring to [this](https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved/blob/d2bf367d41836dd9204497e32dd30cd1e81ae54d/animatediff/sampling.py#L618C60-L618C60) implementation in this comment. Other implementations are also same/similar. The overall...

Would love to see FreeNoise implementation. I've hacked together implementation for basic chunking above, but results are not that great (only openpose controlnet, no vid2vid). Unfortunately I don't have skills...

Ok, so I was able to port FreeNoise Animatediff code to diffusers - results below (128 frames) @DN6 @a-r-r-o-w Shall i open separate PR? Any hints for implementing chunked inference...