lyneeeeeeeee

/

RealGeneral

like 0

This PR adds a comprehensive model card for RealGeneral, documented in the paper RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models.

It includes the appropriate pipeline_tag (text-to-video), library_name (diffusers), and license (apache-2.0). Additionally, it provides direct links to the project page and GitHub repository, a teaser image, and a basic usage example for the CogVideoXPipeline.