AviadDahan

/

ID-LoRA-CelebVHQ

like 3

Hi! I'm Niels from the Hugging Face community science team. I'm opening this PR to improve the model card for ID-LoRA.

This PR:

• Adds the any-to-any pipeline tag to accurately reflect the model's audio-video generation capabilities.
• Links the model to the official research paper: ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA.
• Adds links to the project page and the official GitHub repository.
• Updates the usage instructions with the recommended two-stage inference script from the documentation.
• Adds the citation information for the paper.