addtime

/

MMGT_pretrained

Like 2

Hi! I'm Niels from the community science team at Hugging Face.

This PR improves the documentation for the MMGT model by:

• Adding the image-to-video pipeline tag for better discoverability.
• Adding library_name: diffusers as the repository contains a standard Diffusers-compatible structure.
• Linking the model card to the research paper and GitHub repository.
• Providing a summary of the two-stage framework (SMGA and MM-HAA).
• Including sample CLI usage instructions for audio-to-video and pose-to-video generation found in the official repository.
• Adding the BibTeX citation for researchers.

Feel free to merge this if it looks good to you!