Image-to-Video
ONNX

Improve model card for HuMo: Human-Centric Video Generation

#1
by nielsr HF Staff - opened

This PR improves the model card for HuMo by:

  • Adding pipeline_tag: any-to-any for better discoverability.
  • Adding library_name: diffusers, as indicated by _diffusers_version in config.json.
  • Correcting inconsistent arXiv paper ID references (e.g., in the badge and citation link) to 2509.08519.
  • Adding an explicit link to the project's GitHub repository at https://github.com/Phantom-video/HuMo.
  • Updating the BibTeX citation to reflect the version found in the GitHub README, which is consistent with the 2509.08519 arXiv ID.
Cannot merge
This branch has merge conflicts in the following files:
  • README.md

Sign up or log in to comment