Open masaisai111 opened 1 month ago
May I ask why the author does not want to use pipe to load each module, such as unet, when reasoning during training
you can also use pipe to load each module, here I followed diffusers repo
Here I think, pipe.unet=unet(load alone), is this the correct understanding
here,base_model_path==args.pretrained_model_name_or_path
May I ask why the author does not want to use pipe to load each module, such as unet, when reasoning during training