nerdyrodent/VQGAN-CLIP

Do we need to train VQGAN and CLIP together?

charlotte12l opened this issue · 2 comments

In training, do we need to train VQGAN and CLIP together? Or they are just trained separately but when inference we will use them two.

They're pre-trained.

@nerdyrodent Actually I mean when I finetune(train) the model, do I just train VQGAN and CLIP separately, or train them together? I guess just separately is enough?