---
license: mit
datasets:
- Caoza/PhysX-Mobility
- Caoza/PhysX-3D
base_model:
- Qwen/Qwen2.5-VL-7B-Instruct
tags:
- Simulation-Ready
- Physical 3D Generation
- 3D Vision
- 3D
pipeline_tag: image-to-3d
---
## PhysX-Anything

<p align="left"><a href="https://arxiv.org/abs/2511.13648"><img src='https://img.shields.io/badge/arXiv-Paper-red?logo=arxiv&logoColor=white' alt='arXiv'></a>
<a href='https://huggingface.co/papers/2511.13648'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Paper-blue'></a>
<a href='https://physx-anything.github.io/'><img src='https://img.shields.io/badge/Project_Page-Website-green?logo=homepage&logoColor=white' alt='Project Page'></a>
<a href='https://youtu.be/okMms-NdxMk'><img src='https://img.shields.io/youtube/views/okMms-NdxMk'></a>

The model of PhysX-Anything,  the first simulation-ready physical 3D generative framework that, given a single in-the-wild image, produces high-quality sim-ready 3D assets with explicit geometry, articulation, and physical attributes.

Project page: https://physx-anything.github.io/

Code: https://github.com/ziangcao0312/PhysX-Anything