Feature: Hyper flux lora support. #8472
Open
skunkworxdark wants to merge 4 commits intoinvoke-ai:mainfrom
Open
Feature: Hyper flux lora support. #8472skunkworxdark wants to merge 4 commits intoinvoke-ai:mainfrom
skunkworxdark wants to merge 4 commits intoinvoke-ai:mainfrom
Conversation
First Check-in - works, but not happy with the code quality and I feel it is not following the established code style
skunkworxdark
requested review from
blessedcoolant,
hipsterusername,
lstein,
maryhipp and
psychedelicious
as code owners
github-actions
bot
added
python
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Related bug report: #8415
My attempt at adding hyper and turbo FLUX LoRA support. This was done with a lot of help from Gemini. I am not fully happy with the code. I don't feel it follows well with the existing code structure.
I found it tricky to follow exactly how all the FLUX LoRA patching worked. I did a fair bit of testing, and it does seem to have a positive effect on the number of steps needed to generate. However, I am not 100% confident it works fully as expected and does the patching correctly for these hyper/turbo LoRAs. It really needs someone who has a better understanding than I to take a look over it.
Related Issues / Discussions
#8415
QA Instructions
Load up one of the hyper/turbo LoRAs and generate and image.
Other Flux LoRAs should also be tested to make sure nothing have been broken.
Merge Plan
No plan. This is really just a WIP at the moment.
Checklist
What's Newcopy (if doing a release after this PR)