Speechmatics - API for Voice AI Agents
Mini toolsHY World 2.0
By Tencent
HY-World 2.0 is Tencent Hunyuan’s open-source multimodal world-model framework for both 3D world generation and 3D world reconstruction. The repository says it can turn text or a single image into a high-fidelity navigable 3D world through a four-stage pipeline using HY-Pano 2.0, WorldNav, WorldStereo 2.0, and WorldMirror 2.0, while also reconstructing 3D from multi-view images or casual video in a single forward pass via WorldMirror 2.0. It is positioned as a shift from pixel-video world models to persistent 3D assets, supporting meshes, point clouds, and 3D Gaussian splats that can be imported into tools like Blender, Unity, Unreal Engine, and Isaac Sim.
New
Multimodal
Gen 3
Overview
HY-World 2.0 is Tencent Hunyuan’s multimodal 3D world model for reconstructing, generating, and simulating explorable worlds. It accepts text, single-view images, multi-view images, and videos, then outputs persistent 3D assets such as meshes and Gaussian splattings, aiming to create editable, navigable worlds rather than short-lived generated videos.
About Tencent
Tencent is a world-leading internet and technology company that develops innovative products and services to improve the quality of life of people around the world.
Industry:
Technology, Information and Media
Company Size:
110558
Location:
Shenzhen, CN
Website:
tencent.com
Tools using HY World 2.0
No tools found for this model yet.
Last updated: April 16, 2026
