Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,8 @@
|
|
| 8 |
|
| 9 |
We provide the GaussianCube model trained on Objaverse.
|
| 10 |
|
|
|
|
|
|
|
| 11 |
The `v1.0` is trained under the setting of [our paper](http://arxiv.org/abs/2403.19655).
|
| 12 |
|
| 13 |
For `v1.1` version, we re-filter the data of Objaverse according to [aesthetic score](https://laion.ai/blog/laion-aesthetics/). We also include `hssd_models` and `3D-FUTURE` for training, building a training set of around 170k high-quality 3D assets. Moreover, we generate the text captions of each 3D asset using GPT-4o, resulting highly detailed text description. Therefore, our `v1.1` model has stronger capability to longer and more detailed input text captions.
|
|
|
|
| 8 |
|
| 9 |
We provide the GaussianCube model trained on Objaverse.
|
| 10 |
|
| 11 |
+
For model usage, please refer to [our repo](https://github.com/GaussianCube/GaussianCube).
|
| 12 |
+
|
| 13 |
The `v1.0` is trained under the setting of [our paper](http://arxiv.org/abs/2403.19655).
|
| 14 |
|
| 15 |
For `v1.1` version, we re-filter the data of Objaverse according to [aesthetic score](https://laion.ai/blog/laion-aesthetics/). We also include `hssd_models` and `3D-FUTURE` for training, building a training set of around 170k high-quality 3D assets. Moreover, we generate the text captions of each 3D asset using GPT-4o, resulting highly detailed text description. Therefore, our `v1.1` model has stronger capability to longer and more detailed input text captions.
|