CogVideoX

by Zhipu AI (Z.ai)

About the model:

text-to-video generation model by QingYing

Model type:

Video

Model performance class:

Full

Link to the model:

https://huggingface.co/zai-org/CogVideoX1.5-5B

Base models:

CogVideoX-5b

End model:

CogVideoX1.5-5B

End model license:

Apache-2.0

About the organisation:

Zhipu AI, branded as Z.ai, is a Chinese technology company specializing in artificial intelligence.

Link to the organisation:

https://www.zhipuai.cn/en/

Model release date:

August 2024

Availability

Base Model Data

They use CogView which has closed dataset along other datasets.

https://arxiv.org/abs/2205.15868

End User Model Data

https://arxiv.org/abs/2205.15868

Base Model Weights

Weights are available on HuggingFace.

https://huggingface.co/zai-org/CogVideoX-2b

End User Model Weights

Weights are available on HuggingFace.

https://huggingface.co/zai-org/CogVideoX1.5-5B

Training Code

https://github.com/zai-org/CogVideo?tab=readme-ov-file

Documentation

Code Documentation

https://huggingface.co/zai-org/CogVideoX1.5-5B

Hardware Architecture

Explained in the paper.

https://arxiv.org/abs/2205.15868

Preprint

Newest paper on their newest model.

https://openreview.net/forum?id=LQzN6TRFg9

Paper

Presented in ICLR in 2023.

https://iclr.cc/virtual/2023/poster/11213

Modelcard

https://huggingface.co/zai-org/CogVideoX1.5-5B

Datasheet

Access

Licenses

Model licensed under Apache-2.0, an OSI-approved license.

https://huggingface.co/zai-org/CogVideoX1.5-5B#model-license

Is this information not up to date?

Contribute here ->

Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by BSTN. This version of the index generated 09 April 2026, website content last updated 11 March 2026.