Update pipeline tag to image-to-video and improve model card

#3
by nielsr HF Staff - opened

Hi! I'm Niels from the Hugging Face community science team.

This PR improves the model card for VOID:

  • Updates the pipeline_tag to image-to-video for better categorization on the Hub.
  • Adds the paper authors and links to the paper page.
  • Maintains the usage examples and architecture details found in the repository.

Hi! Quick question -- I think video-to-video is a better tag given that the model takes in a source video and a sequence of masks then outputs a video?

Thanks, I will close this PR since there's already a pipeline tag + link to the paper page.

nielsr changed pull request status to closed

Sign up or log in to comment