Yixuan Ren
Yixuan Ren
This solution https://github.com/huggingface/diffusers/issues/2306 seems to work
I found the right file in an ealier issue: https://github.com/snap-research/articulated-animation/issues/12#issuecomment-836635256
Hi may I ask if any update here?
I have an observation: take the last group of experiments on 3dshapes as an example, there are 1800 in total (10800~12599). As mentioned in the paper, they evaluated 6 methods,...
I think it's because there is a VQModelInterface wrapper, and the decode func there performs the codebook lookup before final decoding.