3D world model
A generated 3D world turns into an editable environment with geometry, motion, and explorable space.
What people can do
Start from the practical surface before reading sources and boundaries.
Inspect Tencent's open 3D world generation and reconstruction path for persistent scene assets and engine-oriented workflows.
A generated 3D world turns into an editable environment with geometry, motion, and explorable space.
Generated 3D worlds, video-to-3D reconstruction, editable meshes and Gaussian splats, and interactive exploration with persistent assets.
Tencent exposes code, model cards, and weights through public research surfaces; hosted compute costs, deployment costs, and downstream usage constraints depend on the reader's own environment and the current repository/model licenses.
Source: Tencent-Hunyuan/HY-World-2.0 GitHub repository
Scene explainer
The page starts with the experience, then moves toward source-backed details.
01First impression
HY-World 2.0 is Tencent Hunyuan's multimodal 3D world model for reconstructing, generating, and simulating persistent worlds from text, images, multi-view inputs, and video.
02Capability
Gives the site a primary-source Tencent anchor in generated-3D-world coverage instead of leaving the ecosystem to Alibaba, Ant, World Labs, and DeepMind alone.
03Boundary
Even after the May 2026 expansion, HY-World 2.0 remains a repo-led research workflow rather than a simple public creator product like Marble.
HY-World 2.0 belongs in generated and reconstructed 3D worlds; it should not be flattened into generic AI video or a fully open consumer world simulator.
Release signals
The company profile stays stable. These short signals explain what changed and point back to sources.
FAQ
Use these notes to keep model comments grounded in official sources and careful category boundaries.
The site tracks systems that model environments, actions, spatial structure, or persistent simulated state. Pure text chatbots and ordinary video generators are only included when they provide a clear bridge toward interactive or physical world modeling.
Video models are included only when they help explain the path from generated clips to controllable spaces, physics-aware prediction, or agent-ready simulation. The site keeps that distinction explicit so video generation is not overstated as a finished world simulator.
Primary sources carry the most weight: official product pages, research posts, papers, documentation, code repositories, and company announcements. Secondary media can be referenced, but it stays labeled as reported or adjacent unless independently confirmed.
Useful comments add source links, corrections, release-status notes, comparison questions, or concrete reader context. Comments are public immediately, so readers should avoid private information and unsupported promotional claims.
Discussion
Add source-backed corrections, questions, or notes for this page.
No comments yet. Start with a source note or a question for future coverage.