whatisgithub

What is hy-world-2.0?

tencent-hunyuan/hy-world-2.0 — explained in plain English

Analysis updated 2026-05-18

1,911PythonAudience · researcherComplexity · 5/5Setup · hard

In one sentence

A research model that builds editable, persistent 3D worlds and digital twins from text, images, or video.

Mindmap

mindmap
  root((repo))
    What it does
      Builds 3D worlds
      Reconstructs digital twins
      Editable outputs
    Tech stack
      PyTorch
      Gaussian splatting
      WorldMirror 2.0
    Use cases
      Game engine assets
      Video to 3D twin
      Interactive exploration
    Audience
      Researchers
      3D engineers
      Game developers

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Reconstruct a 3D digital twin of a space from a casual video using WorldMirror 2.0

USE CASE 2

Generate a navigable 3D scene from a single text prompt or image for use in a game engine

USE CASE 3

Explore AI generated 3D worlds interactively in first person or third person mode

What is it built with?

PythonPyTorch3D Gaussian Splatting

How does it compare?

tencent-hunyuan/hy-world-2.0nvlabs/protomotionsnvidia-nemo/datadesigner
Stars1,9111,9451,859
LanguagePythonPythonPython
Last pushed2026-07-04
MaintenanceActive
Setup difficultyhardhardmoderate
Complexity5/55/53/5
Audienceresearcherresearcherdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · hard Time to first run · 1day+

Requires GPU hardware and multiple large pretrained model components, full generation pipeline not yet fully released.

So what is it?

HY-World 2.0 is a research project from Tencent's Hunyuan team that builds full three dimensional worlds from text, images, or video, rather than generating flat video that disappears after playback. It accepts several kinds of input, including text prompts, single images, multiple view images, and video, and outputs persistent 3D representations such as meshes and Gaussian splats that can be opened and edited in engines like Blender, Unity, Unreal Engine, or Isaac Sim. The system offers two main capabilities. World generation takes a text prompt or a single image and produces a navigable 3D scene through four stages: generating a panorama with a companion model called HY-Pano 2.0, planning a camera trajectory with a component called WorldNav, expanding the scene outward with WorldStereo 2.0, and composing the final result with WorldMirror 2.0 combined with 3D Gaussian splatting. World reconstruction takes multiple images or a casual video and, through WorldMirror 2.0, predicts depth, surface normals, camera parameters, point clouds, and Gaussian splat attributes in a single pass, effectively turning a video into a digital twin of the space it shows. The project frames its advantage over pixel based world models like Genie 3 or Cosmos around editability and permanence: the output is a real, reusable 3D asset rather than a video clip with a fixed length, it plays in real time on consumer GPUs once generated, and it supports precise physics based collision instead of imprecise character control. HY-World 2.0 also supports first person and third person interactive exploration of the worlds it produces. As of the most recent update, the project has open sourced the HY-Pano 2.0 panorama model and the WorldMirror 2.0 reconstruction model with their inference code and weights, while full world generation code and a couple of related components are still marked as coming soon. The project provides a technical report, pretrained models on Hugging Face, and demo videos showing generated scenes and reconstructions.

Copy-paste prompts

Prompt 1
Explain how HY-World 2.0's four stage pipeline turns a text prompt into a navigable 3D scene
Prompt 2
Walk me through downloading the HY-Pano 2.0 and WorldMirror 2.0 weights from Hugging Face
Prompt 3
Show me how WorldMirror 2.0 predicts depth, normals, and Gaussian splats from multi-view images

Frequently asked questions

What is hy-world-2.0?

A research model that builds editable, persistent 3D worlds and digital twins from text, images, or video.

What language is hy-world-2.0 written in?

Mainly Python. The stack also includes Python, PyTorch, 3D Gaussian Splatting.

How hard is hy-world-2.0 to set up?

Setup difficulty is rated hard, with roughly 1day+ to a first successful run.

Who is hy-world-2.0 for?

Mainly researcher.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.