Pad SDXL Tokens to Prevent Tensor Mismatch #2991
Open
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
pad SDXL conditioning tensors before concatenation when shape differs.
Panchovix
added a commit
to Panchovix/stable-diffusion-webui-reForge
that referenced
this pull request
Aug 8, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
There is a rare instance when prompt length is too long in SDXL causing a tensor mismatch, as mentioned in #2540. Added padding logic in “get_learned_conditioning” to ensure equal token lengths before concatenating the local and global conditionings in SDXL, preventing shape mismatches during inference. When the local and global conditioning tensors have different lengths, the shorter tensor is padded with zeros before concatenation.