Performance of this code in image generation task

[tj-zhu]

Dear @lucidrains, thank you very much for providing the code. It's really helpful for my own research on diffusion model.

I am wondering if you have reached the reported performance in Analog Bits paper for the image generation task?

I am trying to reproduce the image captioning task in the paper, but unfortunately I couldn't reach the reported performance. So I am checking the code of the image generation task in this repo, to see if I did anything wrong in my own code.

Also, if you've tried reproducing the image captioning task, I would love to hear your suggestions.

Thank you very much!