Add comprehensive model card for ReDiff with metadata and usage

by nielsr HF Staff - opened Oct 28

←

nielsr

Oct 28

This PR significantly enhances the model card for the ReDiff model.

It includes:

Essential metadata: pipeline_tag: image-text-to-text and library_name: transformers, which improve discoverability and enable the automated "how to use" widget on the model page.
Clear links to the paper (https://huggingface.co/papers/2510.19871), the project page (https://rediff-hku.github.io/), and the GitHub repository (https://github.com/jiyt17/ReDiff).
An introductory description and a visual teaser from the GitHub repository.
A "Quick Inference Demo" section, copied directly from the GitHub README, to provide users with an immediate way to test the model.
The BibTeX citation for proper attribution.

Please review and merge this PR to improve the accessibility and information of this model.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment