Modular backend - LoRA/LyCORIS #6667
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
StAlKeR7779
requested review from
lstein,
blessedcoolant,
brandonrising,
RyanJDick,
hipsterusername and
psychedelicious
as code owners
github-actions
bot
added
python
RyanJDick
requested changes
Jul 26, 2024
Co-Authored-By: Ryan Dick <[email protected]>
RyanJDick
reviewed
Jul 29, 2024
Co-Authored-By: Ryan Dick <[email protected]>
Co-Authored-By: Ryan Dick <[email protected]>
RyanJDick
approved these changes
Jul 31, 2024
There was a problem hiding this comment.
Looks good!
I tested the following test cases on both _old_invoke and _new_invoke against main:
- LoRA patching and unpatching speeds are the same
- Images generated with LoRA are unchanged
- Images generated after removing a LoRA are unchanged (i.e. the LoRA is being unpatched properly).
- Can stack multiple LoRAs
I left one minor comment. I'll go ahead and fix that and fix the conflicts with main prior to merging.
hipsterusername
approved these changes
Jul 31, 2024
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Outdated suggestions cannot be applied.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.
Summary
Code for lora patching from #6577.
Additionally made it the way, that lora can patch not only
weight, but alsobias, because saw some loras which doing it.Related Issues / Discussions
#6606
https://invokeai.notion.site/Modular-Stable-Diffusion-Backend-Design-Document-e8952daab5d5472faecdc4a72d377b0d
QA Instructions
Run with and without set
USE_MODULAR_DENOISEenvironment.Merge Plan
Replace old lora patcher with new after review done.
If you think that there should be some kind of tests - feel free to add.
Checklist