-
Notifications
You must be signed in to change notification settings - Fork 5k
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
Switching to DPM++ SDE Karras sampling method #2064
Comments
This might be the only scheduler method we don't have yet - I assume you referring to: https://github.com/crowsonkb/k-diffusion/blob/41b4cb6df0506694a7776af31349acf082bf6091/k_diffusion/sampling.py#L543 Think this is already the second issue about it, would be extremely nice to add it then. Maybe someone from the community has time to do it ? :-) Will try to find some time otherwise. Here a nice doc on how to change schedulers in general: https://huggingface.co/docs/diffusers/main/en/using-diffusers/schedulers |
You can use this to find alternative of DPM++ SDE Karras in You can also try: The default sampling method used by I hope this helps :) |
I am interested to add it. |
This would be great :-) Do you want to open a PR for it? It's quite useful to compare your implementation with https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_k_diffusion.py to make sure results are the same |
Yeah ! I will open a PR for it. Thanks for letting me know. I will compare the implementation to verify the results. |
Has output for the different schedulers in When testing Epic Diffusion, I was unable to reproduce the output of a basic I initially suspected this may be related to how the AUTOMATIC1111 GUI overcomes the 77 token limit of CLIP, but after reading the description of how they achieve this I'm less convinced... See also this issue. |
Hey @jslegers, For the future, it would be great if you could open a new issue. I've answered here in more detail: https://huggingface.co/spaces/anzorq/finetuned_diffusion/discussions/64 |
Personally, I'm not a fan of raising issues for just asking a question. In my experience, as a senior software developer, this easily leads to issue-spam and makes it difficult to keep an overview of actual bugs & feature requests. Also, I felt this issue was related enough to not warrant raising a new issue. But I'll try to keep your different preference in mind for the future whenever I have similar questions.
Thanks for the link. |
It's a bit easier to find issues according to the issue title later on, so we usually prefer to open new issues when the topic is slightly different. |
Hello @patrickvonplaten, I'd like to pick this ticket and try to raise a PR. |
Hey @nipunjindal, This sounds great! Let me know if you need help |
Hello @patrickvonplaten, Happy to get some help here. I am unable to find text related to this scheduler, do you mind sharing the way to go about it? |
Hey @nipunjindal, Would this feature request maybe help: #2905 Essentially, it's not really a new scheduler, it just uses different sigmas. We could quite easily support this with a |
1 similar comment
Hey @nipunjindal, Would this feature request maybe help: #2905 Essentially, it's not really a new scheduler, it just uses different sigmas. We could quite easily support this with a |
Hello @patrickvonplaten, Thanks definitely this is helpful (simplifies it all :)), to me the |
I've added the "correct" version of the SDE-type DPM-Solver++: #3344 |
Closing this with #3344 |
How can I change the scheduler in
StableDiffusionPipeline
to use what AUTOMATIC111's gui calls the "DPM++ SDE Karras" sampling method?Also, whats the default sampling method being used by
StableDiffusionPipeline
?The text was updated successfully, but these errors were encountered: