minimal-diffusion
minimal-diffusion copied to clipboard
A minimal yet resourceful implementation of diffusion models (along with pretrained models + synthetic images for nine datasets)
Thank you for providing code, I'm trying to train the model on Celeba, I have downloaded the dataset and found it has no labels, however in the function get_metadata() in...
Thanks a lot for this clean and modular implementation! I would like to incorporate code from your repo in another project. Could you please add a license file?
hi there, what parameter we have to change to run it our on data also is this model is applicable to run grey scale image data?
File "E:\minimal-diffusion-main\main_single.py", line 38, in / unsqueeze3x(scalars.alpha_bar[t].sqrt()) IndexError: tensors used as indices must be long, byte or bool tensors self.get_x0_from_xt_eps = lambda xt, eps, t, scalars: ( self.clamp_x0( 1 /...
Hi, Thank you for providing the code. It is helping us a lot. We train the model for Imagenet Mini generally contains 40 classes (custom dataset). But the output we...