fix(mm): flux variant probing #7862
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
psychedelicious
requested review from
lstein,
blessedcoolant,
brandonrising,
hipsterusername and
jazzhaiku
as code owners
github-actions
bot
added
python
psychedelicious
force-pushed
the
psyche/fix/mm/flux-variant-probing
branch
from
514a7f9 to
f477899
Compare
jazzhaiku
approved these changes
Mar 31, 2025
Before FLUX Fill was merged, we didn't do any checks for the model variant. We always returned "normal". To determine if a model is a FLUX Fill model, we need to check the state dict for a specific key. Initially, this logic was too strict and rejected quantized FLUX models. This issue was resolved, but it turns out there is another failure mode - some fine-tunes use a different key. This change further reduces the strictness, handling the alternate key and also falling back to "normal" if we don't see either key. This effectively restores the previous probing behaviour for all FLUX models. Closes #7856 Closes #7859
psychedelicious
force-pushed
the
psyche/fix/mm/flux-variant-probing
branch
from
600fb2f to
be16666
Compare
hipsterusername
approved these changes
Mar 31, 2025
|
There is something wonky w/ the macos test runner. Can't reproduce this issue locally on my M1 Pro. I'm going to split off the testing changes into a separate PR so we can get the user-facing issue resolved sooner rather than later. |
psychedelicious
force-pushed
the
psyche/fix/mm/flux-variant-probing
branch
from
be16666 to
20469a8
Compare
4 tasks
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Outdated suggestions cannot be applied.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
Before FLUX Fill was merged, we didn't do any checks for the model variant. We always returned "normal".
To determine if a model is a FLUX Fill model, we need to check the state dict for a specific key. Initially, this logic was too strict and rejected quantized FLUX models. This issue was resolved, but it turns out there is another failure mode - some fine-tunes use a different key.
This change further reduces the strictness, handling the alternate key and also falling back to "normal" if we don't see either key. This effectively restores the previous probing behaviour for all FLUX models.
Related Issues / Discussions
Closes #7856
Closes #7859
QA Instructions
I have a variety of FLUX models already installed. My testing strategy:
use_memory_db: trueininvokeai.yamlI tested these models, all of which install correctly and have the correct variant (normal vs inpaint for FLUX Fill):
Merge Plan
n/a
Checklist
What's Newcopy (if doing a release after this PR)