Unconditional Generation's inference code, config, and ckpt

[ziqihuangg]

Hi, thanks for open-sourcing this great work.
I didn't find the inference code or config for unconditional generation (like Figure 8 in your paper).
Could you provide it if you have time? Thanks a lot!

Also, which text-to-image pretrained diffusion transformer did you use to produce Figure 8 (FFHQ) result? Is it a separate one you trained on FFHQ, and the ckpt hasn't been released in this repo?

Thank you very much!

[Benjamin-So]

Hi, I know it has been a few years since this question was originally asked. Did you ever figure out how to reproduce the results of unconditional synthesis?