README.md

---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---

# GaussianCube Model Trained on Objaverse

We provide the GaussianCube model trained on Objaverse. 

For model usage, please refer to [our repo](https://github.com/GaussianCube/GaussianCube).

The `v1.0` is trained under the setting of [our paper](http://arxiv.org/abs/2403.19655). 

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.