Refactor image padding logic to pervent zero tensor in transformer_z_image #12743
+17
−10
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Collaborator
|
@bot /style |
Contributor
|
Style bot fixed some files and pushed the changes. |
Collaborator
|
cc @JerryWu-code can you take a look too? |
Merged
1 task
Contributor
Sure, I'm happy to proceed that, this error does exist on TPU with using torch_xla, and I add a minimal test case to report the problem and fix more on #12770. Ready to merge ~ |
Contributor
Author
|
Should I close the pr now? It's my first time contributing to diffusers :) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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?
In src/diffusers/models/transformers/transformer_z_image.py, there exists a image_padding_len for padding image to be multiple of SEQ_MULTI_OF. However, when the image shape is already multiple of SEQ_MULTI_OF, this will create a tensor with zero shape. This triggers
INVALID_ARGUMENT: Concatenate expects at least one argument.for PyTorch/XLA on TPU. It may also fail on other devices than cuda.Fixes #12742
Who can review?
@yiyixuxu @asomoza