Merged
Conversation
JPPhoto
requested review from
Pfannkuchensack,
blessedcoolant,
dunkeroni and
lstein
as code owners
github-actions
bot
added
python
Collaborator
blessedcoolant
left a comment
blessedcoolant
left a comment
There was a problem hiding this comment.
Rest of it seems fine. Pretty straightforward.
blessedcoolant
approved these changes
Feb 5, 2026
lstein
pushed a commit
that referenced
this pull request
Feb 6, 2026
* Add DyPE area option * Added tests and fixed frontend build * Made more pythonic
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This PR introduces a new DyPE preset mode (area) for FLUX that determines activation/scaling from image area rather than max dimension, while preserving neutral baseline behavior at the model's native training size.
Related Issues / Discussions
QA Instructions
Added tests in
tests/backend/flux/dype/test_dype.pycovering area mode behavior.The best way to test actual functionality is to generate images with DyPE off and using the new area setting for both the base model size and larger than model size. Base model images should be identical while larger ones diverge and DyPE ones should be more coherent.
Merge Plan
Checklist
What's Newcopy (if doing a release after this PR)