tedlasai

/

learn2refocus

like 0

This PR improves the model card for "Learning to Refocus with Video Diffusion Models" by adding crucial metadata and enhancing its documentation.

Key changes include:

• Adding pipeline_tag: image-to-video to correctly categorize the model on the Hub, reflecting its capability to generate video sequences from images.
• Adding library_name: diffusers, as evidenced by _diffusers_version in the config.json files, to enable automated usage snippets.
• Including direct links to the project page and the GitHub repository for easy access to further information and code.
• Providing a concise description of the model's purpose, based on the paper's abstract.
• Adding a citation section with the BibTeX entry from the project's GitHub README.

These updates will make the model more discoverable and user-friendly on the Hugging Face Hub.