zhengrchan

Results 2 comments of zhengrchan

The deepspeed needs to save model in all processes, not only the main process. So just remove the `accelerator.is_main_process` in the saving part should work. Otherwise, other processes will wait...

I'm confused too. In my case, infer imgs from custom stage1 model could be full of noise if the cfg_guidance_scale > 1. I'm trying to train with cfg.