fix(flux): warn on unsupported ip_adapter_masks#13956
Closed
akshan-main wants to merge 1 commit into
Closed
Conversation
Contributor
|
Hi @akshan-main, thanks for the PR! It does not appear to link an issue it fixes. If this PR addresses an existing issue, please add a closing keyword (e.g. |
yiyixuxu
reviewed
Jun 15, 2026
| ip_hidden_states: list[torch.Tensor] | None = None, | ||
| ip_adapter_masks: torch.Tensor | None = None, | ||
| ) -> torch.Tensor: | ||
| if ip_adapter_masks is not None: |
Collaborator
There was a problem hiding this comment.
I think we can just remove this
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Addresses the flux review (#13584), Issue 1:
FluxIPAdapterAttnProcessoracceptsip_adapter_masksbut never applies them, so region-specific IP-Adapter conditioning silently has no effect (the repro in the issue prints0.0between masked and unmasked runs).I looked at implementing the masks properly (the SD
IPAdapterAttnProcessor2_0pattern), but:ip_adapter_masksthrough, so there's no caller to exercise it, andSo rather than ship a risky reimplementation against Flux's packed layout with no caller, this stops the silent no-op: passing
ip_adapter_masksnow emits awarning_oncethat it's unsupported and ignored. Full regional-mask support for Flux would be a follow-up (and needs spatial info plumbed in) — happy to take that on if you'd like it.Before submitting
Who can review?
@hlky @sayakpaul @yiyixuxu