Skip to content
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

Fix model unpatching process when running on CPU #6631

Merged
merged 1 commit into from
Jul 18, 2024

Conversation

lstein
Copy link
Collaborator

@lstein lstein commented Jul 17, 2024

Summary

The model patching/unpatching optimization introduced in #6439 does not work when image generation is executing on the CPU, leading to scrambled images on subsequent generations. This PR disables the optimization when running on CPU.

Related Issues / Discussions

See #6559 and a PR that solves the problem with a config option #6628

QA Instructions

Using CPU rendering, apply a LoRA and run the generation twice. On the second run, the image should not be scrambled looking.

Merge Plan

Merge when approved.

Checklist

  • The PR has a short but descriptive title, suitable for a changelog
  • Tests added / updated (if applicable)
  • Documentation added / updated (if applicable)

@github-actions github-actions bot added python PRs that change python files backend PRs that change backend files labels Jul 17, 2024
@psychedelicious
Copy link
Collaborator

Thanks, prefer this to a config option.

@lstein lstein merged commit 97a7f51 into main Jul 18, 2024
14 checks passed
@lstein lstein deleted the lstein/bugfix/lora-patching branch July 18, 2024 19:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
backend PRs that change backend files python PRs that change python files
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants