Sponsored by
YouArt
tencent / Hunyuan3D-2
Model's Last Updated: October 17 2025
image-to-3d
Introduction of Hunyuan3D-2
Model Details of Hunyuan3D-2
“ Living out everyone’s imagination on creating and manipulating 3D assets.”
🔥 News
- Jan 21, 2025: 💬 Release Hunyuan3D 2.0 . Please give it a try!
Abstract
We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets. This system includes two foundation components: a large-scale shape generation model - Hunyuan3D-DiT, and a large-scale texture synthesis model - Hunyuan3D-Paint. The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly aligns with a given condition image, laying a solid foundation for downstream applications. The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant texture maps for either generated or hand-crafted meshes. Furthermore, we build Hunyuan3D-Studio - a versatile, user-friendly production platform that simplifies the re-creation process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes efficiently. We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models, including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and e.t.c.
☯️ Hunyuan3D 2.0
Architecture
Hunyuan3D 2.0 features a two-stage generation pipeline, starting with the creation of a bare mesh, followed by the synthesis of a texture map for that mesh. This strategy is effective for decoupling the difficulties of shape and texture generation and also provides flexibility for texturing either generated or handcrafted meshes.
Performance
We have evaluated Hunyuan3D 2.0 with other open-source as well as close-source 3d-generation methods. The numerical results indicate that Hunyuan3D 2.0 surpasses all baselines in the quality of generated textured 3D assets and the condition following ability.
| Model | CMMD(⬇) | FID_CLIP(⬇) | FID(⬇) | CLIP-score(⬆) |
|---|---|---|---|---|
| Top Open-source Model1 | 3.591 | 54.639 | 289.287 | 0.787 |
| Top Close-source Model1 | 3.600 | 55.866 | 305.922 | 0.779 |
| Top Close-source Model2 | 3.368 | 49.744 | 294.628 | 0.806 |
| Top Close-source Model3 | 3.218 | 51.574 | 295.691 | 0.799 |
| Hunyuan3D 2.0 | 3.193 | 49.165 | 282.429 | 0.809 |
Generation results of Hunyuan3D 2.0:
Pretrained Models
| Model | Date | Huggingface |
|---|---|---|
| Hunyuan3D-DiT-v2-0 | 2025-01-21 | Download |
| Hunyuan3D-Paint-v2-0 | 2025-01-21 | Download |
🤗 Get Started with Hunyuan3D 2.0
You may follow the next steps to use Hunyuan3D 2.0 via code or the Gradio App.
Install Requirements
Please install Pytorch via the official site. Then install the other requirements via
pip install -r requirements.txt
# for texture
cd hy3dgen/texgen/custom_rasterizer
python3 setup.py install
cd hy3dgen/texgen/differentiable_renderer
bash compile_mesh_painter.sh
API Usage
We designed a diffusers-like API to use our shape generation model - Hunyuan3D-DiT and texture synthesis model - Hunyuan3D-Paint.
You could assess Hunyuan3D-DiT via:
from hy3dgen.shapegen import Hunyuan3DDiTFlowMatchingPipeline
pipeline = Hunyuan3DDiTFlowMatchingPipeline.from_pretrained('tencent/Hunyuan3D-2')
mesh = pipeline(image='assets/demo.png')[0]
The output mesh is a trimesh object , which you could save to glb/obj (or other format) file.
For Hunyuan3D-Paint , do the following:
from hy3dgen.texgen import Hunyuan3DPaintPipeline
from hy3dgen.shapegen import Hunyuan3DDiTFlowMatchingPipeline
# let's generate a mesh first
pipeline = Hunyuan3DDiTFlowMatchingPipeline.from_pretrained('tencent/Hunyuan3D-2')
mesh = pipeline(image='assets/demo.png')[0]
pipeline = Hunyuan3DPaintPipeline.from_pretrained('tencent/Hunyuan3D-2')
mesh = pipeline(mesh, image='assets/demo.png')
Please visit minimal_demo.py for more advanced usage, such as text to 3D and texture generation for handcrafted mesh .
Gradio App
You could also host a Gradio App in your own computer via:
pip3 install gradio==3.39.0
python3 gradio_app.py
Don't forget to visit Hunyuan3D for quick use, if you don't want to host yourself.
📑 Open-Source Plan
- Inference Code
- Model Checkpoints
- ComfyUI
- TensorRT Version
🔗 BibTeX
If you found this repository helpful, please cite our report:
@misc{hunyuan3d22025tencent,
title={Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation},
author={Tencent Hunyuan3D Team},
year={2025},
}
Acknowledgements
We would like to thank the contributors to the DINOv2 , Stable Diffusion , FLUX , diffusers and HuggingFace repositories, for their open research and exploration.
Star History
Runs of tencent Hunyuan3D-2 on huggingface.co
100.6K
Total runs
0
24-hour runs
774
3-day runs
1.0K
7-day runs
-31.0K
30-day runs
More Information About Hunyuan3D-2 huggingface.co Model
Url of Hunyuan3D-2
Hunyuan3D-2 huggingface.co Url
Provider of Hunyuan3D-2 huggingface.co
Other API from tencent
Total runs:
368.2K
Run Growth:
308.0K
Growth Rate:
85.45%
Total runs:
90.7K
Run Growth:
-582.4K
Growth Rate:
-642.43%
Total runs:
55.6K
Run Growth:
-3.6K
Growth Rate:
-6.51%
Total runs:
50.9K
Run Growth:
26.4K
Growth Rate:
52.98%
Total runs:
49.8K
Run Growth:
2.4K
Growth Rate:
5.02%
Total runs:
42.5K
Run Growth:
39.1K
Growth Rate:
98.29%
Total runs:
30.3K
Run Growth:
3.7K
Growth Rate:
12.36%
Total runs:
19.6K
Run Growth:
19.6K
Growth Rate:
100.00%
Total runs:
17.9K
Run Growth:
-8.7K
Growth Rate:
-48.26%
Total runs:
17.4K
Run Growth:
9.2K
Growth Rate:
53.10%
Total runs:
13.9K
Run Growth:
11.5K
Growth Rate:
83.81%
Total runs:
13.3K
Run Growth:
-16.8K
Growth Rate:
-130.53%
Total runs:
10.2K
Run Growth:
1.9K
Growth Rate:
18.93%
Total runs:
7.4K
Run Growth:
-1.1K
Growth Rate:
-14.82%
Total runs:
5.8K
Run Growth:
5.8K
Growth Rate:
100.00%
Total runs:
5.6K
Run Growth:
5.6K
Growth Rate:
100.00%
Total runs:
5.3K
Run Growth:
-1.6K
Growth Rate:
-30.29%
Total runs:
4.5K
Run Growth:
-889
Growth Rate:
-20.16%
Total runs:
4.3K
Run Growth:
-538
Growth Rate:
-13.31%
Total runs:
3.5K
Run Growth:
3.2K
Growth Rate:
93.74%
Total runs:
3.3K
Run Growth:
-931
Growth Rate:
-29.15%
Total runs:
3.0K
Run Growth:
-174
Growth Rate:
-5.86%
Total runs:
2.8K
Run Growth:
2.3K
Growth Rate:
80.50%
Total runs:
2.7K
Run Growth:
2.7K
Growth Rate:
100.00%
Total runs:
2.7K
Run Growth:
-15.4K
Growth Rate:
-576.52%
Total runs:
2.2K
Run Growth:
2.0K
Growth Rate:
92.03%
Total runs:
1.8K
Run Growth:
327
Growth Rate:
17.71%
Total runs:
1.7K
Run Growth:
-873
Growth Rate:
-51.17%
Total runs:
1.6K
Run Growth:
-950
Growth Rate:
-58.90%
Total runs:
1.6K
Run Growth:
275
Growth Rate:
17.12%
Total runs:
1.4K
Run Growth:
1.2K
Growth Rate:
82.02%
Total runs:
1.1K
Run Growth:
644
Growth Rate:
61.27%
Total runs:
1.0K
Run Growth:
611
Growth Rate:
60.20%
Total runs:
1.0K
Run Growth:
738
Growth Rate:
74.40%
Total runs:
693
Run Growth:
-114
Growth Rate:
-16.45%
Total runs:
607
Run Growth:
-552
Growth Rate:
-93.72%
Total runs:
572
Run Growth:
54
Growth Rate:
10.00%
Total runs:
552
Run Growth:
-1.7K
Growth Rate:
-301.45%
Total runs:
548
Run Growth:
170
Growth Rate:
30.97%
Total runs:
510
Run Growth:
109
Growth Rate:
23.75%
Total runs:
480
Run Growth:
79
Growth Rate:
16.46%
Total runs:
466
Run Growth:
243
Growth Rate:
54.61%
Total runs:
461
Run Growth:
-997
Growth Rate:
-363.87%
Total runs:
444
Run Growth:
117
Growth Rate:
27.40%
Total runs:
428
Run Growth:
113
Growth Rate:
29.05%
Total runs:
422
Run Growth:
68
Growth Rate:
16.92%
Total runs:
418
Run Growth:
418
Growth Rate:
100.00%
Total runs:
407
Run Growth:
256
Growth Rate:
67.02%
Total runs:
350
Run Growth:
-122
Growth Rate:
-36.20%
Total runs:
317
Run Growth:
-81
Growth Rate:
-25.55%
Total runs:
307
Run Growth:
-389
Growth Rate:
-166.24%
Total runs:
300
Run Growth:
-16
Growth Rate:
-7.17%
Total runs:
297
Run Growth:
-416
Growth Rate:
-140.07%
Total runs:
290
Run Growth:
-86
Growth Rate:
-29.66%
Total runs:
280
Run Growth:
161
Growth Rate:
55.90%
Total runs:
280
Run Growth:
-137
Growth Rate:
-48.93%
Total runs:
277
Run Growth:
60
Growth Rate:
22.64%
Total runs:
277
Run Growth:
-69
Growth Rate:
-24.91%
Total runs:
220
Run Growth:
-57
Growth Rate:
-25.91%
Total runs:
214
Run Growth:
34
Growth Rate:
17.09%
Total runs:
210
Run Growth:
-63
Growth Rate:
-31.66%
Total runs:
203
Run Growth:
62
Growth Rate:
32.12%
Total runs:
199
Run Growth:
38
Growth Rate:
17.51%
Total runs:
187
Run Growth:
106
Growth Rate:
57.92%
Total runs:
180
Run Growth:
1
Growth Rate:
0.56%
Total runs:
176
Run Growth:
31
Growth Rate:
19.14%
Total runs:
171
Run Growth:
106
Growth Rate:
62.35%