New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

about the decoder #4

Open

ysm2000 opened this issue Jun 14, 2024 · 1 comment

ysm2000 commented Jun 14, 2024

Thanks for your nice work!
I have a question, If I replace the decoder with the SD series, will it affect the final generation performance?

Member

Maitreyapatel commented Jun 21, 2024

Hi @ysm2000,
Yes, it may affect it. We observed that the following parts play crucial roles:

Another decoder should be conditioned on the given CLIP embeddings used by our model.
Models like stable unclip do this, but due to insufficient training of these models, they do not perform well.

Therefore, Kandinsky v2.2 is the ideal candidate.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment