-
Couldn't load subscription status.
- Fork 6.5k
fix: SD3 ControlNet validation so that it runs on a A100. #11238
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. The docs are available until 30 days after the last update. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Left a few comments. Thanks @sayakpaul
| prompt_2=None, | ||
| prompt_3=None, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Not a blocker for this PR but looks like prompt_2 and prompt_3 should be made Optional in the pipeline.
| dataset = load_dataset( | ||
| args.train_data_dir, | ||
| cache_dir=args.cache_dir, | ||
| trust_remote_code=True, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice, could be an argument but more convenient like this especially as the example dataset requires it. Can be replicated across training scripts.
For future reference we should look at the num_proc option which should help speed up processing.
What does this PR do?
Fixes #11225