0
$\begingroup$

I can't find any resources on scaling the denoising model input depending on the current timestep for diffusion models. Just briefly mentioned in the appendix of the paper , but not much more. Does anyone have a source on a comparison of doing vs omitting it?

Here's the huggingface diffusers implementation

$\endgroup$

0

You must log in to answer this question.

Browse other questions tagged .