Global AI MapHunyuan ↗
Official project, model family or research program. Follow the source for versions, releases and terms.
China / AI lab
Tencent Hunyuan
◎ Shenzhen, China
Tencent Hunyuan develops Hunyuan models.
Key outputs
HunyuanVideo: A Systematic Framework For Large Video Generative Models ↗
Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai
NaviCache: Test-Time Self-Calibration Caching for Video Generation ↗
Zheqi Lv, Zhibo Zhu, Jinke Wang, Qi Tian, Shengyu Zhang
People & contributors
- Weijie Kong ↗Linked paper authorSOURCE ↗
- Qi Tian ↗Linked paper authorSOURCE ↗
- Zijian Zhang ↗Linked paper authorSOURCE ↗
- Rox Min ↗Linked paper authorSOURCE ↗
Roles are tied to the linked sources. Paper authors are credited as contributors, which does not establish current employment.
Presentations & demonstrations
5m26sHunyuanVideo 1.5: Open Video Generation Model
3m27sHunyuan3D-Buffalo: one AI builds and edits 3D from a sentence
5m33sInside Hunyuan-Large: Tencent's Revolutionary 389B-Parameter AI Model!
10m27sTencent: "Our Hunyuan MT7B Just Crushed GPT 4 and Google Translate"
Films are credited to their original channels. Selected presentations may include independent interviews and technical explanations.
Sources & public activity
- hunyuan.tencent.com/ ↗
- github.com/Tencent-Hunyuan/HunyuanVideo ↗
- arxiv.org/abs/2412.03603 ↗
- arxiv.org/abs/2606.26795 ↗
Profile reviewed 2026-10-30. City-level approximate marker; not a lab street address.