Add support for nested images to LLava and VipLLava #35558
+371
−475
Conversation
This file contains 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. |
|
Flagging this PR too - I made some changes to the Llava/Pixtral processing for nested images here, so there might be some conflicts! #34801 |
zucchini-nlp
approved these changes
Jan 9, 2025
src/transformers/image_utils.py
Outdated
Comment on lines
263
to
264
| if is_valid_image(images): | ||
| output_images = [[images]] |
There was a problem hiding this comment.
could it be that we get a 4D tensor as a batch of images?
There was a problem hiding this comment.
Yes you are right! Made some changes that should account for that
yonigozlan
requested review from
qubvel,
molbap,
Rocketknight1 and
ArthurZucker
as code owners
yonigozlan
force-pushed
the
uniformize-image-text-to-text-inputs-processing
branch
from
0319100 to
6f595da
Compare
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Outdated suggestions cannot be applied.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?
This PR adds the functions
make_flat_list_of_images,make_nested_list_of_imagesandmake_batched_videostoimage_utils, removing some unnecessarily duplicated code.make_flat_list_of_imagesalso replaces make_list_of_images in clip, blip, and siglip image processors, as it allows image-text-to-text models which use these image processors to support nested images inputs, while preserving BC.Partially addresses #34545
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
@zucchini-nlp