Hi, Niels here from the community science team at Hugging Face.
This PR improves the model card for Cosmos3-Super-Image2Video by:
- Adding the `pipeline_tag: image-to-video` to ensure the model is correctly categorized on the Hub.
- Setting the `library_name: diffusers` to enable the automated code snippet widget and the "Use in Diffusers" button.
- Linking the model repository to the research paper [Cosmos 3: Omnimodal World Models for Physical AI](https://huggingface.co/papers/2606.02800).
- Adding a "Sample Usage" section with a `diffusers` code snippet found in the documentation to help users get started quickly.
