# Tencent Open-Sources HunyuanVideo

- Date: 2024-12-03
- Type: model
- Credit: Tencent
- URL: https://aifilmhistory.org/entry/hunyuanvideo-open-source

Tencent releases HunyuanVideo's inference code and weights — a 13-billion-parameter video model that's the largest open-source release of its kind to date. Anyone can download it, run it locally, fine-tune it, and ship workflows that don't depend on a subscription or a closed API. For researchers, ComfyUI builders, and creators wary of platform risk after seeing what happens when models get sunset, this immediately becomes the open-source anchor of the AI video stack.

Links:
- HunyuanVideo GitHub: https://github.com/Tencent/HunyuanVideo
- HunyuanVideo Technical Report: https://arxiv.org/abs/2412.03603

---
Source: https://aifilmhistory.org/entry/hunyuanvideo-open-source
Era: 2024 · The Great Convergence
Last updated: 2026-10-02