The original K-Diffusion paper report FID scores for FFHQ dataset (64x64) is about 2, but when we use your code repo, the FID is over 60 and the visualization results are very bad after 100 epoch with 256 batch size training. What do you think?
I think there is a bug in the use of "accelerate launch" for launching train.py with acceleration. If you do not use "accelerate" FID is close to 2 points.
Hi authors:
Thanks for your work.
The original K-Diffusion paper report FID scores for FFHQ dataset (64x64) is about 2, but when we use your code repo, the FID is over 60 and the visualization results are very bad after 100 epoch with 256 batch size training. What do you think?![image](https://user-images.githubusercontent.com/93637959/214454772-db5b0a52-a1e9-4d75-be5a-1aeebe8a5b3a.png)
Best, Tutu Iroh Zhao