What this is
Tencent's Hunyuan family is the most modality-diverse Chinese AI lineage: text, image, video, 3D, and immersive world models. Open-source across most categories since 2024. This page is a 2026-05-15 release-by-release reference.
Hunyuan Release Timeline
| Date | Release | Notable |
|---|---|---|
| May 14, 2024 | Hunyuan text-to-image (DiT) | Open-source, free commercial use |
| 2024 (mid) | Hunyuan MoE architecture | Integrated into Tencent collaboration products |
| Nov 5, 2024 | Hunyuan-Large + Hunyuan3D-1.0 | MoE LLM + 3D generation, open-source |
| Dec 3, 2024 | Hunyuan-Video | 13B params; open-source text-to-video |
| Jul 26, 2025 | HunyuanWorld-1.0 | First open-source immersive 3D world generation |
| Dec 8, 2025 | Tencent HY 2.0 (Hunyuan 2.0) | 406B params (32B active), 256K context |
| Dec 18, 2025 | HunyuanWorld-1.5 (WorldPlay) | Real-time 3D world creation |
| Apr 16, 2026 | HY-World-2.0 | State-of-the-art 3D world model |
| Apr 23, 2026 | Hy3preview (LLM) | 295B params (21B active), 256K context, fast+slow thinking |
| Apr 2026 | Hunyuan 3.0 launch | Significant programming capability improvement; WeChat AI agent |
Hunyuan Family at a Glance (Mid-2026)
| Family | Category | Open / Proprietary | Best at |
|---|---|---|---|
| Hunyuan / Hunyuan 2.0 / Hunyuan 3.0 / Hy3preview | LLM (text) | Open-source MoE base | Long-context (256K), agentic coding |
| HunyuanDiT | Text-to-image | Open-source | Chinese-prompt image generation |
| Hunyuan-Video | Text-to-video | Open-source | Highest-quality open-source video gen |
| Hunyuan3D 1.0-2.0 | 3D asset generation | Open-source | Single image to 3D mesh |
| HunyuanWorld 1.0 / 1.5 / 2.0 | 3D immersive world models | Open-source | Explorable world generation |
Six Things the Lineage Tells You
- Hunyuan is the most modality-diverse Chinese lineage. Text, image, video, 3D mesh, immersive 3D worlds — all open-source.
- The world-model line (HunyuanWorld) is unique. No US lab has shipped an open-source explorable 3D world generator at this scale.
- Hy3preview (Apr 2026) introduces fast+slow thinking. Routing between fast inference and deeper reasoning in one model.
- 256K context across the LLM line. Consistent long-context across Hunyuan 2.0 and Hy3preview.
- WeChat integration is the distribution moat. Hunyuan 3.0 ties to a WeChat AI agent, putting Tencent's AI in front of 1.3B+ MAU.
- Hunyuan-Video remains the open-source video benchmark. Most other Chinese labs have not shipped a competitive open video model.
What This Means for AI Visibility
Hunyuan's open-source video and world models matter for brands that produce visual content. As open-source video generation goes mainstream, brand likeness, product appearance, and visual brand identity will increasingly be generated by these models. Auditing how your brand is rendered in Hunyuan-Video and HunyuanWorld is the visual-brand analogue to monitoring how it is described in text.
Methodology
Release dates from Baidu's Tencent HY reference, HunyuanVideo on HuggingFace, HunyuanWorld GitHub, TechNode on Hunyuan 2.0, AiBase on Hunyuan 3.0, and Caixin Global on the Hunyuan 3.0 launch.
How Presenc AI Helps
Presenc AI tracks brand mentions in Tencent Hunyuan-served surfaces including WeChat AI agent answers and Tencent Cloud Hunyuan API outputs, with separate monitoring for the open-source video and world model rendering of brand visual identity.