video-diffusion-pytorch
video-diffusion-pytorch copied to clipboard
Gradient method for conditional sampling
Thanks for your effort in implementation. I did not find any code blocks using autograd package to compute gradient as shown in Eq(6) of the paper. Have you implemented this technique? Or can you tell me which line corresponds to this technique. I am interested in its effectiveness. Thanks
have u figured out how to implement it? It seems this repo not implement it.
Yes, it seems Eq(6) in the paper not be implemented here, right?
Any updates?
you may like to check this paper https://arxiv.org/abs/2209.14687