Alibaba-Research-Intelligence-Computing

/

Tora_T2V_diffusers

like 1

Follow

Alibaba Cloud Intelligent Culture and Education, 阿里云-智能文教 12

This PR updates the model card to reflect the new model, Tora2, as presented in the paper Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation.

Specifically, it:

• Updates the model title and abstract to reflect Tora2.
• Updates the paper link to the official Hugging Face paper page for Tora2.
• Updates the project page link to the dedicated Tora2 project page.
• Enriches the metadata with structured links for the paper, project page, and GitHub repository.
• Adds new tags (tora2, multi-entity-video-generation) for better discoverability.
• Integrates comprehensive usage sections (Installation, Inference, Training, etc.) directly from the GitHub repository README to provide a more self-contained and useful resource on the Hub.
• Updates the citation to reflect the Tora2 paper.