Flux2 Updates to Improve Image Quality#120
Merged
Merged
Conversation
stikves
approved these changes
Jul 21, 2026
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Issue #111 led us to investigate what might be causing Flux2 regressions. This PR makes a few small changes in the pipeline to be more faithful to the original Python definitions. Although these lead to meaningfully better results, we may need to conduct further investigation to resolve any other possible issues. Therefore, follow-up PRs may be made to further improve image quality and determine root causes.
Changes
<|endoftext|>token (151643) instead of<|im_end|>(151645) for paddingResults
Using similar prompts to those described in #111, we see images like below (a prompt each for the lobster, butterfly, ant, and bee)
