Text-to-video

Zhipu CogVideoX

Tracked

by Zhipu AI (Z.ai)

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

On file

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.

Source record

Source
https://github.com/zai-org/CogVideo
Verification
checked directly on the vendor's own site
Last checked
July 1, 2026
← Back to the directory