diffusers icon indicating copy to clipboard operation
diffusers copied to clipboard

[WIP] DragNUWA SVD

Open a-r-r-o-w opened this issue 2 years ago • 4 comments

What does this PR do?

Code: https://github.com/ProjectNUWA/DragNUWA Paper: https://arxiv.org/abs/2308.08089 Project Page: https://www.microsoft.com/en-us/research/project/dragnuwa/ Demo: https://huggingface.co/spaces/yinsming/DragNUWA

Fixes #6497. This is a WIP and I've freely made changes to the unet code, which I know is less than ideal at the moment. I'd like to get a basic example running first before looking into improving the code. Suggestions on how to refactor and add a pipeline for running DragNUWA in community/core will be very much appreciated, thanks!

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?
  • [ ] Did you read our philosophy doc (important for complex PRs)?
  • [ ] 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.

@DN6 @sayakpaul @moymix

a-r-r-o-w avatar Feb 11 '24 14:02 a-r-r-o-w

I’d say we start with a community pipeline first. This way you will have more freedom.

If the pipeline needs custom modeling components, consider contributing them to research_projects folder. Does this make sense?

sayakpaul avatar Feb 11 '24 15:02 sayakpaul

There is definitely need for some modeling components here because the resnet and spatiotemporal unet layers have new additions. I will move to the research_projects directory after I can get an example working, thanks!

a-r-r-o-w avatar Feb 11 '24 15:02 a-r-r-o-w

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

github-actions[bot] avatar Mar 20 '24 15:03 github-actions[bot]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

github-actions[bot] avatar Apr 27 '24 15:04 github-actions[bot]