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

Published 20 hours ago • verified publisher icon lucidrains

Question about the normalization of the input data for ddpm.

Open MingCongSu opened this issue 1 year ago • 0 comments

Just want to ask two naive questions as I am new to the diffusion model. 😅

I noticed that in README.md, it says that the data is normalized from 0 to 1. https://github.com/lucidrains/denoising-diffusion-pytorch/blob/d0c68fc6828291f2c66f6caccb8f4635d9613732/README.md?plain=1#L45

  1. Why do we have to conduct this normalization on data? If we didn't do that, would DDPM still work properly?
  2. If the input is latent like LDM does, do I have to make sure the latent space is also from 0 to 1?

MingCongSu avatar Apr 13 '24 10:04 MingCongSu