Question about your model
justinday123 opened this issue · 1 comments
justinday123 commented
Is your model brings pretraied DDPM(trained with FFHQ) and finetune with loss? In your code, it seems like you finetune the model per each image using Model.pt, but there is no word about finetune in your paper. Am i right?
Or, is it updating noise like using classifier guidance?
Thank you for your nice work, and it helped me a lot.
justinday123 commented
Also, is Model.pt is ID Conditional DDPM before using losses?