All papers and articles cover how to fine-tune unconditional StyleGAN on more unconditional data (meaning belonging to one class). I can't find sources of knowledge covering conditional StyleGANs and I remember that I've heard of it.

I'd like to take some pre-trained unconditional StyleGAN, for example with human faces from original papers, and fine-tune it on conditional data, let's say two classes, so making that model conditional.

Can I fine-tune pre-trained unconditional StyleGAN2/3 to be conditional?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.