SDXL: pooled prompt embeds need batch dim for batched writer#2846
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request updates the
_slice_batch_output_for_cachefunction insimpletuner/helpers/caching/text_embeds.pyto better handle tensor shapes and ensure compatibility with batch processing. The main changes focus on adjusting tensor dimensions when dealing with single-item batches and specific output keys.Tensor shape handling improvements:
batch_size == 1, ensuring consistent tensor shapes for downstream processing.pooled_prompt_embedsandnegative_pooled_prompt_embeds, added a squeeze operation to remove unnecessary batch dimensions when the tensor is 2D, improving compatibility with expected output formats.