[LoRA] Make sure LoRA can be disabled after it's run#2128
Merged
Conversation
|
The documentation is not available anymore as the PR was closed or merged. |
Contributor
Author
|
Sorry already merging now as I need it for another PR |
patil-suraj
reviewed
Jan 27, 2023
Comment on lines
+158
to
+166
| # if current processor is in `self._modules` and if passed `processor` is not, we need to | ||
| # pop `processor` from `self._modules` | ||
| if ( | ||
| hasattr(self, "processor") | ||
| and isinstance(self.processor, torch.nn.Module) | ||
| and not isinstance(processor, torch.nn.Module) | ||
| ): | ||
| logger.info(f"You are removing possibly trained weights of {self.processor} with {processor}") | ||
| self._modules.pop("processor") |
Contributor
There was a problem hiding this comment.
Looks good ! But what happens when processor is a module ? Do we just overwrite it ? Would be nice to add more comments here, found it a bit hard to understand at first glance.
yoonseokjin
pushed a commit
to yoonseokjin/diffusers
that referenced
this pull request
Dec 25, 2023
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
As very nicely stated by @jorgemcgomes in #2124 (comment) it's currently not possible to "disable" LoRA attention processors.
This PR fixes this by hacking a bit into PyTorch's module dict (think it's fine & safe though :-))