Closed talafek96 closed 1 year ago
Regarding the algorithm shown, why are we sampling a random t instead of training over every t in a sequence? (since the process of adding noise happens one step after another)
@amitir22
in the bullet "Position Embedding":
math.log(10000)
?forward(self, time)
?Re sampling of a random t, I'm not 100% sure but I believe it's related to stability. You don't want to sequentially perform too many iterations on a single image (it will overfit the particular image).
Re position embedding:
what is going on in those lines? EDIT: nvm it's just a cool function.
https://huggingface.co/blog/annotated-diffusion
Related to epic #1