Text-to-video

Zhipu CogVideoX

by Zhipu AI (Z.ai)

Zhipu AI's open video model family, powering their consumer 'Qingying' (清影) product.

CogVideoX is built on a diffusion transformer architecture, co-developed with Tsinghua University, and is available in 2B and 5B parameter sizes with both text-to-video and image-to-video variants.