Support inference with LyCORIS BOFT networks #14871
Merged
Conversation
This file contains 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
|
@v0xie For the compatibility of "load weight" I may change the content of state dict in the near future. (Will be something in LyCORIS 2.1.0) Will review and refine this in next week |
LyCORIS will support save oft_blocks instead of oft_diag in the near future (for both OFT and BOFT) But this means we need to store the rescale if user enable it.
|
This should be fine now. |
|
There is an execution path where before if/else checks. |
AUTOMATIC1111
approved these changes
Feb 19, 2024
AUTOMATIC1111
added a commit
that referenced
this pull request
Feb 19, 2024
Support inference with LyCORIS BOFT networks
Closed
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Outdated suggestions cannot be applied.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.
Description
This draft PR adds support for inference of BOFT networks trained with the dev branch of LyCORIS. The implementation is based on @KohakuBlueleaf's implementation here: https://github.com/KohakuBlueleaf/LyCORIS/blob/dev/lycoris/modules/boft.py
Since the name "oft_diag" is the same between OFT and BOFT, I think the simplest way to differentiate the two is the dimension of the weights (OFT: 3, BOFT: 4).
The calc_updown code is slightly modified from the get_weight function in the original. I'm not sure what to do about the scale parameter so I leave it at 1.0.
Screenshots/videos:
Checklist: