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 role of PLMS #176

Open

CS123n opened this issue Aug 19, 2022 · 1 comment

CS123n commented Aug 19, 2022 •

edited

Hi, congratulations on your wonderful job!

discoart/discoart/runner.py

Line 321 in 6bd664f

sample_fn = diffusion.plms_sample_loop_progressive

I find that you also provide the sampling method PLMS from Pseudo Numerical Methods for Diffusion Models on Manifolds. Is it useful in your situation? If it is true, it would be nice to add a note about it in the readme.
Thanks!

au5tr1ng3r commented Aug 19, 2022

Parameter: diffusion_sampling_mode: "...alternate method that promises good diffusion results in fewer steps..."

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