All models

3D world model

HY-World 2.0

Reconstructs, generates, simulates persistent 3D worlds from text, images, video.

Open-source report, weights, and May 2026 world-generation code expansionLocal open source
HY-World 2.0 world model demo View demo
OrganizationTencent Hunyuan
Category3D world model
AvailabilityGitHub, Hugging Face, April 2026 report, May HY-Pano/WorldStereo 2.0 releases.
Last reviewed2026-05-18

01 / Overview

World generation, video-to-3D reconstruction, editable meshes, Gaussian splats, persistent assets.

Reconstructs, generates, simulates persistent 3D worlds from text, images, video.

HY-World 2.0 matters here because it clarifies a specific lane: World generation, video-to-3D reconstruction, editable meshes, Gaussian splats, persistent assets.

This is a source-backed orientation profile, not a benchmark verdict.

02 / Strengths

Where it stands out

  • Primary-source Tencent anchor beside Alibaba, Ant, World Labs, DeepMind.
  • Unusually clear framing: persistent editable 3D assets versus video rollouts.
  • May 2026 added HY-Pano 2.0 code and WorldStereo 2.0 weights.

03 / Boundaries

What not to overclaim

  • Repo-led research workflow, not a public creator product like Marble.
  • Evidence centers on 3D world generation, reconstruction, not generic video.

Generated/reconstructed 3D worlds, not AI video or consumer world simulator.

04 / Access & output

How the model reaches people

Code, cards, weights public; compute, usage constraints follow repository licenses.

Access surface
Open-source research workflow
Tencent-Hunyuan/HY-World-2.0 GitHub repository
Platforms
GitHub · Hugging Face · arXiv · Tencent Hunyuan 3D surface
Outputs
Generated 3D worlds · Reconstructed 3D worlds · Meshes · Gaussian splats · Point clouds
Inputs & compatibility
Unity · Unreal Engine · NVIDIA Isaac-style simulation workflows · Developer-run 3D reconstruction pipelines

05 / Practical path

How to evaluate it

  1. 01

    Check GitHub repo and model card before assuming hosted behavior.

  2. 02

    Choose whether the task is reconstruction, generation, or simulation support.

  3. 03

    Validate output quality in target pipeline before calling it engine-ready.

Continue exploring

Compare the lane, then follow the evidence

Primary evidence

Sources