Improve model card for CVD-STORM: Add pipeline tag, links, and abstract
#5
by nielsr HF Staff - opened
This PR significantly enhances the model card for CVD-STORM by:
- Adding the
pipeline_tag: text-to-3dto better categorize the model's capabilities for generating 4D (3D + time) scenes. - Associating it with the paper CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving.
- Including a direct link to the project page: https://sensetime-fvg.github.io/CVD-STORM/.
- Providing a link to the GitHub repository: https://github.com/SenseTime-FVG/OpenDWM.
- Incorporating the paper's abstract to provide a clear overview of the model's purpose and methodology.
- Adding the citation information from the GitHub repository.
Please review and merge this PR if everything looks good.