GOD.EXEA god's-eye view of the AI universe
2026Drag to orbit · right-drag to pan · scroll to zoom
GOD.EXE is booting…

Model

HunyuanVideo

HunyuanVideo is an open-weight AI model from Tencent 腾讯, released in 2024, made for developers.

An open-weight video generation model from Tencent Hunyuan.

Main jobs: Text to video. It is open source and free to use. You can use it on your own server and through an API.

Visit aivideo.hunyuan.tencent.com

Markdown version of https://godooo.ai/en/model/hunyuanvideo. Every page on this site has one: add .md to its address.

At a glance

Type
Model
Released
2024
Galaxy
Video
Open source
Yes
GitHub stars
12,566
How you run it
Self-host · API
Made for
Developers
Also known as
混元视频

What it can do

  • Text to videomain jobunconfirmed

    “HunyuanVideo, a novel open-source video foundation model that exhibits performance in video generation that is comparable to, if not superior to, leading closed-source models.”— github.com, 2026-09-24
  • Image to videosupportedunconfirmed

    “HunyuanVideo (Image-to-Video Model) - [X] Inference - [X] Checkpoints”— github.com, 2026-09-24

unconfirmedproposed by a machine, awaiting calibration

Alternatives

Connections

Questions

What is HunyuanVideo?

HunyuanVideo is an open-weight AI model from Tencent 腾讯, released in 2024, made for developers. An open-weight video generation model from Tencent Hunyuan.

Is HunyuanVideo free?

Yes. HunyuanVideo is open source and free to use.

Is HunyuanVideo open source?

Yes. The source code is at https://github.com/Tencent-Hunyuan/HunyuanVideo.

Can HunyuanVideo run locally?

HunyuanVideo can be self-hosted on your own server.

What can HunyuanVideo do?

Main jobs: Text to video. It can also do: Image to video.

Who makes HunyuanVideo?

HunyuanVideo is made by Tencent 腾讯.

What are open-source alternatives to HunyuanVideo?

Open-source ones: CogVideoX and Open-Sora. Others: Sora, Kling 可灵, Runway, Veo · Flow, Hailuo 海螺 and Jimeng 即梦.

Sources