EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence

EmbodiedGen is a toolkit to generate diverse and interactive 3D worlds composed of generative 3D assets with plausible physics, leveraging generative AI to address the challenges of generalization in embodied intelligence related research. EmbodiedGen composed of six key modules: Image-to-3D, Text-to-3D, Texture Generation, Articulated Object Generation, Scene Generation and Layout Generation.

---

✨ Table of Contents of EmbodiedGen

• 🖼️ Image-to-3D
• 📝 Text-to-3D
• 🎨 Texture Generation
• 🌍 3D Scene Generation
• ⚙️ Articulated Object Generation
• 🏞️ Layout Generation

🚀 Quick Start

✅ Setup Environment

git clone https://github.com/HorizonRobotics/EmbodiedGen.git
cd EmbodiedGen
git checkout v0.1.0
git submodule update --init --recursive --progress
conda create -n embodiedgen python=3.10.13 -y
conda activate embodiedgen
bash install.sh

🟢 Setup GPT Agent

Update the API key in file: embodied_gen/utils/gpt_config.yaml.

You can choose between two backends for the GPT agent:

• gpt-4o (Recommended) – Use this if you have access to Azure OpenAI.
• qwen2.5-vl – An alternative with free usage via OpenRouter, apply a free key here and update api_key in embodied_gen/utils/gpt_config.yaml (50 free requests per day)

---

🖼️ Image-to-3D

Generate physically plausible 3D asset from input image.

Service

Run the image-to-3D generation service locally. The first run will download required models.

# Run in foreground
python apps/image_to_3d.py
# Or run in the background
CUDA_VISIBLE_DEVICES=0 nohup python apps/image_to_3d.py > /dev/null 2>&1 &

API

Generate a 3D model from an image using the command-line API. Models will be downloaded automatically, please wait for the first run.

python3 embodied_gen/scripts/imageto3d.py \
    --image_path apps/assets/example_image/sample_04.jpg apps/assets/example_image/sample_19.jpg \
    --output_root outputs/imageto3d/

# See result(.urdf/mesh.obj/mesh.glb/gs.ply) in ${output_root}/sample_xx/result

---

📝 Text-to-3D

Create 3D assets from text descriptions for a wide range of geometry and styles.

Service

Run the text-to-3D generation service locally.

python apps/text_to_3d.py

API

Models will be downloaded automatically, see download_kolors_weights.

bash embodied_gen/scripts/textto3d.sh \
    --prompts "small bronze figurine of a lion" "A globe with wooden base and latitude and longitude lines" "橙色电动手钻，有磨损细节" \
    --output_root outputs/textto3d/

---

🎨 Texture Generation

Generate visually rich textures for 3D mesh.

Service

Run the texture generation service locally.

python apps/texture_edit.py

API

Models will be downloaded automatically, see download_kolors_weights, geo_cond_mv.

bash embodied_gen/scripts/texture_gen.sh \
    --mesh_path "apps/assets/example_texture/meshes/robot_text.obj" \
    --prompt "举着牌子的写实风格机器人，大眼睛，牌子上写着“Hello”的文字" \
    --output_root "outputs/texture_gen/" \
    --uuid "robot_text"

---

🌍 3D Scene Generation

🚧 Coming Soon

---

⚙️ Articulated Object Generation

🚧 Coming Soon

---

🏞️ Layout Generation

🚧 Coming Soon

---

📚 Citation

If you use EmbodiedGen in your research or projects, please cite:

@misc{wang2025embodiedgengenerative3dworld,
      title={EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence},
      author={Xinjie Wang and Liu Liu and Yu Cao and Ruiqi Wu and Wenkang Qin and Dehui Wang and Wei Sui and Zhizhong Su},
      year={2025},
      eprint={2506.10600},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2506.10600},
}

---

🙌 Acknowledgement

EmbodiedGen builds upon the following amazing projects and models: 🌟 Trellis | 🌟 Hunyuan-Delight | 🌟 Segment Anything | 🌟 Rembg | 🌟 RMBG-1.4 | 🌟 Stable Diffusion x4 | 🌟 Real-ESRGAN | 🌟 Kolors | 🌟 ChatGLM3 | 🌟 Aesthetic Score | 🌟 Pano2Room | 🌟 Diffusion360 | 🌟 Kaolin | 🌟 diffusers | 🌟 gsplat | 🌟 QWEN2.5VL | 🌟 GPT4o

---

⚖️ License

This project is licensed under the Apache License 2.0. See the LICENSE file for details.