wzhgba

/

opendwm-models

like 1

This PR enhances the model card for the CVD-STORM model by:

• Adding the pipeline_tag: text-to-3d to improve discoverability on the Hugging Face Hub.
• Including a direct link to the paper: CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving.
• Providing links to the official project page (https://sensetime-fvg.github.io/CVD-STORM/) and the associated GitHub repository (https://github.com/SenseTime-FVG/OpenDWM).
• Integrating the paper's abstract, a usage section referencing the detailed examples on GitHub, and relevant citation information.

Please review and merge if everything looks good.