8 repos
Video generation models and implementations built on the Wan 2.2 architecture, spanning text-to-video, image-to-video, and text-image-to-video synthesis tasks. The cluster includes multiple model variants (5B and A14B parameters) with both standalone and Diffusers-integrated implementations, enabling developers to generate and manipulate video content from various input modalities using state-of-the-art generative AI techniques.