chetwinlow1

/

Ovi

like 281

This PR improves the model card for the Ovi model by:

• Updating the pipeline_tag to any-to-any to accurately reflect the model's multimodal input and output capabilities (generating video and audio from text or text+image).
• Adding library_name: diffusers to enable the "how to use" widget and automated code snippets, as the model is compatible with the Diffusers library.
• Correcting the arXiv paper ID in the badge to 2510.01284 and ensuring the link points to the correct arXiv page.
• Adding a direct GitHub repository link badge in the header for easier access.
• Incorporating additional, more detailed sections from the GitHub README, including "Memory & Performance Requirements", "Collaboration", and "Contributors", as well as updated details in "Download Weights" and "Configure Ovi" for improved completeness and user guidance.

These changes will enhance the model's discoverability and provide a more comprehensive overview for users on the Hugging Face Hub.