Command-a-vision fix

[dongluw]

What does this PR do?

• fix a bug in the image resize code, which affects performance
  before fix:

after fix:

• add test cases

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue or the forum? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[Rocketknight1]

cc @molbap @yonigozlan @zucchini-nlp

[molbap]

Hi @dongluw , thanks for the contribution, indeed there seems to be a flip issue. however how do you obtain the test image above? I'm surprised our tests haven't caught this, it should be all wrong, so a reproducer would help

[dongluw]

hey @molbap I saved the stacked_images to images patch by patch https://github.com/dongluw/transformers/blob/9ef13ef775fe5a05c634fb2705a500ef59f28763/src/transformers/models/cohere2_vision/image_processing_cohere2_vision_fast.py#L228

this issue only affects generation quality if images are of very high/low aspect ratio

full image is

[github-actions]

[For maintainers] Suggested jobs to run (before merge)

run-slow: cohere2_vision