-
Notifications
You must be signed in to change notification settings - Fork 180
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.
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
Implement samplers correctly #2
Comments
@152334H thoughts about https://github.com/wl-zhao/UniPC ? |
Examples on images AUTOMATIC1111/stable-diffusion-webui#7710 |
Their project says they support Their code in https://github.com/wl-zhao/UniPC/blob/main/example/stable-diffusion/ldm/models/diffusion/uni_pc/uni_pc.py also seems very similar to the DPM-Solver repo, which i'll be integrating soon, so that's good |
on a related note, I realised a few days ago (thanks to mrq) that my implementation of k-diffusion was actually completely wrong. I'll be adding code that actually runs dpm++2m correctly in about an hour (the K diffusion integration is most likely screwed), then I can go for uniPC |
I'll write a larger blog about this later, but to clarify, this is what happened:
tldr: past samplers were fake; dpm++2m is now experimental but real, DDIM+cond_free is preferable for steps < 20 until better samplers exist. Consequently, I'm making DDIM the default sampler for All claims stated here only apply to fp32 inference; I have no idea what the results are like on |
It seems you should:
|
well. yes. a bit late for that now though |
Have you tried any other solver or Rectified Flow for diffusion inference speed up? |
I don't actually work on this project anymore |
ok, Thanks for your work, it helps me a lot. |
The text was updated successfully, but these errors were encountered: