Update metadata and improve model card

#1
by nielsr HF Staff - opened

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

This PR improves the model card by:

  • Adding the pipeline_tag: image-to-video to ensure the model is correctly categorized on the Hub.
  • Setting the library_name to diffusers as evidenced by the model's configuration files and usage instructions.
  • Linking the model to the corresponding paper page on Hugging Face.

These changes help make the model more discoverable and provide users with the correct automated code snippets for usage.

Video-Reason org

Really appreciate your modifications!

Could you also kindly assist us with the download statistics issue? The repository is public, and the model files have been uploaded correctly, including the necessary configuration and weight files. I have tested downloading the model using standard methods such as from_pretrained(), but the download statistics still do not appear to be updating or visible.

We would greatly appreciate any guidance you can provide on this matter.

Hi, yes that's because you have library_name: transformers as metadata in the model card, however in that case you'd need to have a config.json at the root of the repo.

In this case, I'd recommend setting it to library_name: diffusers.

See here for details: https://huggingface.co/docs/hub/models-download-stats

Video-Reason org

I see, thank you for your suggestions

wruisi changed pull request status to closed
wruisi changed pull request status to open
wruisi changed pull request status to merged

Sign up or log in to comment