Miro: Conversational and editable 3D asset generation from text and images

Model Description

Miro is an 3D model focused on transforming creative ideas into physical three-dimensional objects. Developed by the IntimeAI team, this model is fine-tuned from Tencent Hunyuan3D-2.1 on a private dataset, optimized for generating high-quality and esay-to-edit 3D models suitable for production use.

• Model Type: 3D Generation Model
• Base Model: Tencent Hunyuan3D-2.1
• License: Apache License 2.0
• Languages: Chinese, English
• Task Type: 3D generation
• Code Repository: IntimeAI/Miro
• Base Model: tencent/Hunyuan3D-2.1

Citation

If you use the Miro model in your research or projects, please cite:

@misc{miro2026,
  title={Miro: Conversational and editable 3D asset generation from text and images},
  author={IntimeAI},
  year={2026},
  publisher={Hugging Face},
  url={https://huggingface.co/IntimeAI/Miro}
}

Please also cite the base model Tencent Hunyuan3D:

@misc{hunyuan3d2025hunyuan3d,
    title={Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material},
    author={Team Hunyuan3D and Shuhui Yang and Mingxin Yang and Yifei Feng and Xin Huang and Sheng Zhang and Zebin He and Di Luo and Haolin Liu and Yunfei Zhao and Qingxiang Lin and Zeqiang Lai and Xianghui Yang and Huiwen Shi and Zibo Zhao and Bowen Zhang and Hongyu Yan and Lifu Wang and Sicong Liu and Jihong Zhang and Meng Chen and Liang Dong and Yiwen Jia and Yulin Cai and Jiaao Yu and Yixuan Tang and Dongyuan Guo and Junlin Yu and Hao Zhang and Zheng Ye and Peng He and Runzhou Wu and Shida Wei and Chao Zhang and Yonghao Tan and Yifu Sun and Lin Niu and Shirui Huang and Bojian Zheng and Shu Liu and Shilin Chen and Xiang Yuan and Xiaofeng Yang and Kai Liu and Jianchen Zhu and Peng Chen and Tian Liu and Di Wang and Yuhong Liu and Linus and Jie Jiang and Jingwei Huang and Chunchao Guo},
    year={2025},
    eprint={2506.15442},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

@misc{hunyuan3d22025tencent,
    title={Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation},
    author={Tencent Hunyuan3D Team},
    year={2025},
    eprint={2501.12202},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

@misc{yang2024tencent,
    title={Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation},
    author={Tencent Hunyuan3D Team},
    year={2024},
    eprint={2411.02293},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

License

This dataset is released under the Apache License 2.0.

Acknowledgments

Thanks to the Tencent Hunyuan3D team for providing the excellent base model, and to the open-source community for their support.