Add Transformers library name and update model card
Browse filesAdds the Transformers library name to ensure the "how to use" button appears. Also updates the model card content with the latest news and models from the Github README.
README.md
CHANGED
@@ -1,17 +1,18 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
3 |
license: other
|
4 |
license_name: tencent-hunyuan-community
|
5 |
license_link: https://huggingface.co/tencent/Hunyuan3D-2/blob/main/LICENSE.txt
|
6 |
-
language:
|
7 |
-
- en
|
8 |
-
- zh
|
9 |
-
tags:
|
10 |
-
- image-to-3d
|
11 |
-
- text-to-3d
|
12 |
pipeline_tag: image-to-3d
|
|
|
|
|
|
|
13 |
---
|
14 |
|
|
|
15 |
<p align="center">
|
16 |
<img src="./assets/images/teaser.jpg">
|
17 |
</p>
|
@@ -42,7 +43,21 @@ For code and more details on how to use it, refer to the [Github repository](htt
|
|
42 |
|
43 |
## 🔥 News
|
44 |
|
45 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
## **Abstract**
|
48 |
|
@@ -100,8 +115,8 @@ Generation results of Hunyuan3D 2.0:
|
|
100 |
|
101 |
| Model | Date | Huggingface |
|
102 |
|----------------------|------------|--------------------------------------------------------|
|
103 |
-
| Hunyuan3D-DiT-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2) |
|
104 |
-
| Hunyuan3D-Paint-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2) |
|
105 |
| Hunyuan3D-Delight-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-delight-v2-0) |
|
106 |
|
107 |
## 🤗 Get Started with Hunyuan3D 2.0
|
@@ -119,7 +134,7 @@ cd hy3dgen/texgen/custom_rasterizer
|
|
119 |
python3 setup.py install
|
120 |
cd ../../..
|
121 |
cd hy3dgen/texgen/differentiable_renderer
|
122 |
-
|
123 |
```
|
124 |
|
125 |
### API Usage
|
@@ -161,10 +176,39 @@ for handcrafted mesh**.
|
|
161 |
You could also host a [Gradio](https://www.gradio.app/) App in your own computer via:
|
162 |
|
163 |
```bash
|
164 |
-
pip3 install gradio==3.39.0
|
165 |
python3 gradio_app.py
|
166 |
```
|
167 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
168 |
Don't forget to visit [Hunyuan3D](https://3d.hunyuan.tencent.com) for quick use, if you don't want to host yourself.
|
169 |
|
170 |
## 📑 Open-Source Plan
|
@@ -177,7 +221,7 @@ Don't forget to visit [Hunyuan3D](https://3d.hunyuan.tencent.com) for quick use,
|
|
177 |
|
178 |
## 🔗 BibTeX
|
179 |
|
180 |
-
If you found this repository helpful, please cite our
|
181 |
|
182 |
```bibtex
|
183 |
@misc{hunyuan3d22025tencent,
|
@@ -189,8 +233,8 @@ If you found this repository helpful, please cite our report:
|
|
189 |
primaryClass={cs.CV}
|
190 |
}
|
191 |
|
192 |
-
@misc{
|
193 |
-
title={
|
194 |
author={Tencent Hunyuan3D Team},
|
195 |
year={2024},
|
196 |
eprint={2411.02293},
|
@@ -203,15 +247,19 @@ If you found this repository helpful, please cite our report:
|
|
203 |
|
204 |
Thanks for the contributions of community members, here we have these great extensions of Hunyuan3D 2.0:
|
205 |
|
|
|
206 |
- [ComfyUI-Hunyuan3DWrapper](https://github.com/kijai/ComfyUI-Hunyuan3DWrapper)
|
207 |
- [Hunyuan3D-2-for-windows](https://github.com/sdbds/Hunyuan3D-2-for-windows)
|
208 |
-
- [📦 A bundle for running on Windows | 整合包](https://github.com/YanWenKun/
|
|
|
|
|
209 |
|
210 |
## Acknowledgements
|
211 |
|
212 |
We would like to thank the contributors to
|
213 |
-
the [DINOv2](https://github.com/facebookresearch/dinov2), [Stable Diffusion](https://github.com/Stability-AI/stablediffusion), [FLUX](https://github.com/black-forest-labs/flux), [diffusers](https://github.com/huggingface/diffusers)
|
214 |
-
and [
|
|
|
215 |
|
216 |
## Star History
|
217 |
|
@@ -221,4 +269,5 @@ and [HuggingFace](https://huggingface.co) repositories, for their open research
|
|
221 |
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=Tencent/Hunyuan3D-2&type=Date" />
|
222 |
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=Tencent/Hunyuan3D-2&type=Date" />
|
223 |
</picture>
|
224 |
-
</a>
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- zh
|
5 |
+
library_name: transformers
|
6 |
license: other
|
7 |
license_name: tencent-hunyuan-community
|
8 |
license_link: https://huggingface.co/tencent/Hunyuan3D-2/blob/main/LICENSE.txt
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
pipeline_tag: image-to-3d
|
10 |
+
tags:
|
11 |
+
- image-to-3d
|
12 |
+
- text-to-3d
|
13 |
---
|
14 |
|
15 |
+
```markdown
|
16 |
<p align="center">
|
17 |
<img src="./assets/images/teaser.jpg">
|
18 |
</p>
|
|
|
43 |
|
44 |
## 🔥 News
|
45 |
|
46 |
+
- Feb 14, 2025: 🛠️ Release texture enhancement module, please obtain high-definition textures via [here](minimal_demo.py)!
|
47 |
+
- Feb 3, 2025: 🐎
|
48 |
+
Release [Hunyuan3D-DiT-v2-0-Fast](https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-dit-v2-0-fast), our
|
49 |
+
guidance distillation model that could half the dit inference time, see [here](minimal_demo.py) for usage.
|
50 |
+
- Jan 27, 2025: 🛠️ Release Blender addon for Hunyuan3D 2.0, Check it out [here](#blender-addon).
|
51 |
+
- Jan 23, 2025: 💬 We thank community members for
|
52 |
+
creating [Windows installation tool](https://github.com/YanWenKun/Hunyuan3D-2-WinPortable), ComfyUI support
|
53 |
+
with [ComfyUI-Hunyuan3DWrapper](https://github.com/kijai/ComfyUI-Hunyuan3DWrapper)
|
54 |
+
and [ComfyUI-3D-Pack](https://github.com/MrForExample/ComfyUI-3D-Pack) and other
|
55 |
+
awesome [extensions](#community-resources).
|
56 |
+
- Jan 21, 2025: 💬 Enjoy exciting 3D generation on our website [Hunyuan3D Studio](https://3d.hunyuan.tencent.com)!
|
57 |
+
- Jan 21, 2025: 🤗 Release inference code and pretrained models
|
58 |
+
of [Hunyuan3D 2.0](https://huggingface.co/tencent/Hunyuan3D-2). Please give it a try
|
59 |
+
via [huggingface space](https://huggingface.co/spaces/tencent/Hunyuan3D-2) and
|
60 |
+
our [official site](https://3d.hunyuan.tencent.com)!
|
61 |
|
62 |
## **Abstract**
|
63 |
|
|
|
115 |
|
116 |
| Model | Date | Huggingface |
|
117 |
|----------------------|------------|--------------------------------------------------------|
|
118 |
+
| Hunyuan3D-DiT-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-dit-v2-0) |
|
119 |
+
| Hunyuan3D-Paint-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-paint-v2-0) |
|
120 |
| Hunyuan3D-Delight-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-delight-v2-0) |
|
121 |
|
122 |
## 🤗 Get Started with Hunyuan3D 2.0
|
|
|
134 |
python3 setup.py install
|
135 |
cd ../../..
|
136 |
cd hy3dgen/texgen/differentiable_renderer
|
137 |
+
python3 setup.py install
|
138 |
```
|
139 |
|
140 |
### API Usage
|
|
|
176 |
You could also host a [Gradio](https://www.gradio.app/) App in your own computer via:
|
177 |
|
178 |
```bash
|
|
|
179 |
python3 gradio_app.py
|
180 |
```
|
181 |
|
182 |
+
### API Server
|
183 |
+
|
184 |
+
You could launch an API server locally, which you could post web request for Image/Text to 3D, Texturing existing mesh,
|
185 |
+
and e.t.c.
|
186 |
+
|
187 |
+
```bash
|
188 |
+
python api_server.py --host 0.0.0.0 --port 8080
|
189 |
+
```
|
190 |
+
|
191 |
+
A demo post request for image to 3D without texture.
|
192 |
+
|
193 |
+
```bash
|
194 |
+
img_b64_str=$(base64 -i assets/demo.png)
|
195 |
+
curl -X POST "http://localhost:8080/generate" \
|
196 |
+
-H "Content-Type: application/json" \
|
197 |
+
-d '{
|
198 |
+
"image": "'"$img_b64_str"'",
|
199 |
+
}' \
|
200 |
+
-o test2.glb
|
201 |
+
```
|
202 |
+
|
203 |
+
### Blender Addon
|
204 |
+
|
205 |
+
With an API server launched, you could also directly use Hunyuan3D 2.0 in your blender with
|
206 |
+
our [Blender Addon](blender_addon.py). Please follow our tutorial to install and use.
|
207 |
+
|
208 |
+
https://github.com/user-attachments/assets/8230bfb5-32b1-4e48-91f4-a977c54a4f3e
|
209 |
+
|
210 |
+
### Official Site
|
211 |
+
|
212 |
Don't forget to visit [Hunyuan3D](https://3d.hunyuan.tencent.com) for quick use, if you don't want to host yourself.
|
213 |
|
214 |
## 📑 Open-Source Plan
|
|
|
221 |
|
222 |
## 🔗 BibTeX
|
223 |
|
224 |
+
If you found this repository helpful, please cite our reports:
|
225 |
|
226 |
```bibtex
|
227 |
@misc{hunyuan3d22025tencent,
|
|
|
233 |
primaryClass={cs.CV}
|
234 |
}
|
235 |
|
236 |
+
@misc{yang2024hunyuan3d,
|
237 |
+
title={Hunyuan3D 1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation},
|
238 |
author={Tencent Hunyuan3D Team},
|
239 |
year={2024},
|
240 |
eprint={2411.02293},
|
|
|
247 |
|
248 |
Thanks for the contributions of community members, here we have these great extensions of Hunyuan3D 2.0:
|
249 |
|
250 |
+
- [ComfyUI-3D-Pack](https://github.com/MrForExample/ComfyUI-3D-Pack)
|
251 |
- [ComfyUI-Hunyuan3DWrapper](https://github.com/kijai/ComfyUI-Hunyuan3DWrapper)
|
252 |
- [Hunyuan3D-2-for-windows](https://github.com/sdbds/Hunyuan3D-2-for-windows)
|
253 |
+
- [📦 A bundle for running on Windows | 整合包](https://github.com/YanWenKun/Hunyuan3D-2-WinPortable)
|
254 |
+
- [Hunyuan3D-2GP](https://github.com/deepbeepmeep/Hunyuan3D-2GP)
|
255 |
+
- [Kaggle Notebook](https://github.com/darkon12/Hunyuan3D-2GP_Kaggle)
|
256 |
|
257 |
## Acknowledgements
|
258 |
|
259 |
We would like to thank the contributors to
|
260 |
+
the [DINOv2](https://github.com/facebookresearch/dinov2), [Stable Diffusion](https://github.com/Stability-AI/stablediffusion), [FLUX](https://github.com/black-forest-labs/flux), [diffusers](https://github.com/huggingface/diffusers), [HuggingFace](https://huggingface.co), [CraftsMan3D](https://github.com/wyysf-98/CraftsMan3D),
|
261 |
+
and [Michelangelo](https://github.com/NeuralCarver/Michelangelo/tree/main) repositories, for their open research and
|
262 |
+
exploration.
|
263 |
|
264 |
## Star History
|
265 |
|
|
|
269 |
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=Tencent/Hunyuan3D-2&type=Date" />
|
270 |
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=Tencent/Hunyuan3D-2&type=Date" />
|
271 |
</picture>
|
272 |
+
</a>
|
273 |
+
```
|