HunyuanVideo is an open-source video generation model from Tencent's Hunyuan team, released to give the public a video model close to the best closed ones.
In plain words
When it came out in December 2024, the strongest video generators were closed. HunyuanVideo's team published their full approach: how they chose training data, the model design, how they scaled it and the training infrastructure. The result had over 13 billion parameters, the largest open video model at the time, and the code was released. A more efficient HunyuanVideo-1.5 followed in November 2025.
A quick example
Imagine a researcher who wants to test a new video editing idea. With HunyuanVideo's code and weights they can build on a strong model directly, instead of relying on a closed service they cannot change.
Where you'll meet it
- Research on text-to-video generation.
- Open video tools and community workflows.
Related
Sources
- PaperHunyuanVideo: A Systematic Framework For Large Video Generative Models, Kong et al. (arXiv) · read 6 Oct 2026
- DocsHunyuanVideo, Tencent Hunyuan (GitHub) · read 6 Oct 2026
Checked by WhatIsAI against the sources above · 6 Oct 2026. Spotted an error? Report it.