v-diffusion-pytorch icon indicating copy to clipboard operation
v-diffusion-pytorch copied to clipboard

split up sample() to allow backwards pass

Open dribnet opened this issue 2 years ago • 1 comments

This refactor takes the existing sample() call and splits it into subroutines disabling @torch.no_grad() to enable optimisation of x. Could be further cleaned up, but this version is working well currently with downstream code.

dribnet avatar Jan 04 '22 04:01 dribnet

(this branch has been caught up, but the CLIP submodule dependency was also removed in f96d121. I can further clean this up by reverting this commit and flatten this history if you are interested in incorporating these changes)

dribnet avatar Jan 15 '22 09:01 dribnet