Fix model unpatching process when running on CPU #6631
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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