-
Notifications
You must be signed in to change notification settings - Fork 6k
Fix an error when DPM Solver Single Step contains duplicate timesteps #4231
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
Conversation
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. |
I'm really not sure how to fix the non-passing test. It seems to be due to the order_list, which causes the order to stay at 2 (instead of 1), which results in the |
Thanks @yiyixuxu! Sounds good, looks like a better path. I noticed the index_counter approach in DPM Solver SDE as well. |
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread. Please note that issues that do not follow the contributing guidelines are likely to be ignored. |
This error has not been resolved, and the other PR hasn't been merged either (it's been marked as stale). |
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread. Please note that issues that do not follow the contributing guidelines are likely to be ignored. |
fixed in #4986 |
Uses the de-duplication logic applied to the other samplers in #2969
I think this sampler got missed?
This change fixes an error when duplicate timesteps are created with the karras flag:
ValueError: only one element tensors can be converted to Python scalars
@patrickvonplaten @sayakpaul
Thanks!