Feature: Support for resizing multiple format loras. #2057
Conversation
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
|
In f-strings, we need to replace |
|
@woct0rdho Right, oops. Fixed. Eyeballing refactors in PR versions, bad habit of mine. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Various trainers use different naming conventions for loras, which break the resize script. A ubiquitous one is lora_A / lora_B instead of lora_down / lora_up. This change reads whichever convention was used in the given model and adjusts all hardcoded references to that name.
A bit of a patchwork fix using global variables since I don't know the full flow of the code, but I've tested it extensively over several types of base models' loras (from 1.5 to wan) and it works for every lora I've tested.