This PR improves the model card by adding relevant metadata and links to the paper, code, and project page.
Specifically:
- Added `pipeline_tag: text-to-video`.
- Linked the paper: [Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models](https://huggingface.co/papers/2601.04068).
- Linked the GitHub repository and project page.
- Added the official citation.
