guiders/tangential_classifier_free_guidance: fix AttributeError in is_conditional property#13764
Open
Dev-X25874 wants to merge 1 commit into
Open
Conversation
…_conditional property
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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?
Fixes a bug in
TangentialClassifierFreeGuidance.is_conditionalwhere the propertyreferenced a non-existent attribute
self._num_outputs_prepared, causing anAttributeErrorat runtime wheneveris_conditionalis accessed.The base class
BaseGuidance(guider_utils.py) defines and incrementsself._count_preparedto track how many forward passes have been prepared per step.Every other guider in the module (
ClassifierFreeGuidance,MagnitudeAwareGuidance,AdaptiveProjectedGuidance,FrequencyDecoupledGuidance,AutoGuidance, etc.) correctlyreads
self._count_prepared == 1in theiris_conditionalproperty.TangentialClassifierFreeGuidancealone usedself._num_outputs_prepared, which isdefined nowhere in the class hierarchy.
The fix is a single-token substitution:
_num_outputs_prepared→_count_prepared.Fixes # (issue)
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@sayakpaul @yiyixuxu