WorldPlay (HY-World 1.5)
Tencent Hunyuan's WorldPlay: a streaming video diffusion model, released as HY-World 1.5, that enables real-time interactive world exploration with long-term geometric consistency — processing live keyboard and mouse input to generate an explorable AI world frame by frame at up to 24fps. Open-sourced (code and weights on GitHub/Hugging Face). The official hosted demo requires signing in to a Tencent Hunyuan 3D account; open-source self-hosting is available without one. Distinct from the later, separately-released HY-World 2.0.
About this world
Tencent Hunyuan's WorldPlay: a streaming video diffusion model, released as HY-World 1.5, that enables real-time interactive world exploration with long-term geometric consistency — processing live keyboard and mouse input to generate an explorable AI world frame by frame at up to 24fps. Open-sourced (code and weights on GitHub/Hugging Face). The official hosted demo requires signing in to a Tencent Hunyuan 3D account; open-source self-hosting is available without one. Distinct from the later, separately-released HY-World 2.0.
- Generator
- Tencent Hunyuan — HY-World 1.5 (WorldPlay)
- Category
- Simulation
- Source
- Visit source ↗
- Added to QuantWorlds
- 22 August 2026
Built with
HY-World 1.5 (WorldPlay)
Tencent Hunyuan's streaming video diffusion model for real-time, interactive world modeling with long-term geometric consistency, released as WorldPlay. Given a single image or text prompt, it generates a next-chunk (16-frame) video prediction conditioned on live user keyboard/mouse actions, dynamically reconstituting context memory from past frames to keep the world geometrically consistent over long sessions. Runs at up to 24fps in first- or third-person, across real-world and stylized scenes. Open-sourced (code, weights, and full training pipeline). Predecessor to, and released separately from, the later HY-World 2.0.
View Tencent Hunyuan →Created by
Tencent Hunyuan — Team HunyuanWorld
Unclaimed profile
Explore similar worlds
Discover something new.
Explore more AI-generated worlds across the emerging world-model ecosystem.