1. Tutorial Introduction

HunyuanWorld-1.0, launched by Tencent's Hunyuan team at the 2025 World Artificial Intelligence Conference on July 27, 2025, is the first immersive, interactive, and simulated world generation model. The model integrates panoramic visual generation and layered 3D reconstruction technologies, supporting the generation of a 360-degree immersive 3D scene within minutes via text or image input. Users can freely roam the generated world, experiencing a game-like or virtual reality-like interactive feel. The model supports physical simulation and secondary editing, and the generated scenes can be imported into mainstream engines such as Unity and Unreal Engine for further development. The related paper is titled "HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels".

This tutorial uses a dual-GPU RTX A6000 setup. It provides three examples for testing: Text to World, Image to World, and Generate a 3D world. Prompts are only available in English.

2. Project Examples

Text to World

Image to World

Generate a 3D world

3. Operation steps

1. After starting the container, click the API address to enter the Web interface

2. Usage steps

If "Bad Gateway" is displayed, it means the model is initializing. Since the model is large, please wait about 2-3 minutes and refresh the page.

2.1 Text to World

Note: Generation time is approximately 3-5 minutes.

2.2 Image to World

Note: Generation time is approximately 3-5 minutes. 

2.3 Generate a 3D world

Note: Generation time is approximately 5-10 minutes. 

View 3D file effects

1. Download the PLY file above.
2. Download the modelviewer.html file from the project's root directory to your local machine.
3. Double-click to open the modelviewer.html file.
4. Upload the PLY file to preview interactively. 

Citation Information

The citation information for this project is as follows:

@misc{hunyuanworld2025tencent,
    title={HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels},
    author={Tencent Hunyuan3D Team},
    year={2025},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}