fix(z-image): Fix padding token shape mismatch for GGUF models #8690
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Outdated suggestions cannot be applied.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
Fix shape mismatch when loading GGUF-quantized Z-Image transformer models.
GGUF Z-Image models store
x_pad_tokenandcap_pad_tokenwith shape[3840], but diffusersZImageTransformer2DModelexpects[1, 3840](with batch dimension). This caused aRuntimeErroron Linux systems when loading models likez_image_turbo-Q4_K.gguf.The fix:
unsqueeze)Related Issues / Discussions
Reported by Linux user using:
QA Instructions
z_image_turbo-Q4_K.gguf)RuntimeError: size mismatch for x_pad_tokenerror occursMerge Plan
None, straightforward fix.
Checklist
What's Newcopy (if doing a release after this PR)