hlwang06

/

HoloCine

like 59

This PR comprehensively updates the model card for the HoloCine model, replacing the previous minimal content with rich details from the paper (HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives) and its GitHub repository.

Specifically, it adds:

• The pipeline_tag (text-to-video), allowing the model to be discovered via its task.
• The library_name (diffusers), enabling automated code snippets for easy use.
• Direct links to the Hugging Face paper page, the project page, and the GitHub repository.
• The paper's abstract.
• Installation instructions.
• Checkpoint downloading instructions.
• A "Sample Usage" section with a Python code snippet from the official repository, demonstrating how to use the model for text-to-video generation.
• Citation information.

Please review and merge this PR if everything looks good.