Minimum: The minimum GPU memory required is 30GB for generating a single NVS video (batch_size=1) of 32 frames each time.
Recommended: We recommend using a GPU with 40GB of memory.
Operating system: Linux
🧱 Download Pretrained Models
bash
1Diffportrait360
2|----...
3|----pretrained_weights
4|----back_head-230000.th # back head generator5|----model_state-3400000.th # diffportrait360 main module6|----easy-khair-180-gpc0.8-trans10-025000.th
7|----...
🔗 BibTeX
If you find Diffportrait360 is useful for your research and applications, please cite Diffportrait360 using this BibTeX:
BibTeX
1@article{gu2025diffportrait360,
2 title={DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis},
3 author={Gu, Yuming and Tran, Phong and Zheng, Yujian and Xu, Hongyi and Li, Heyuan and Karmanov, Adilbek and Li, Hao},
4 journal={arXiv preprint arXiv:2503.15667},
5 year={2025}
6}
License
Our code is distributed under the Apache-2.0 license.
Acknowledgements
This work is supported by the Metaverse Center Grant from the MBZUAI Research Office. We appreciate the contributions from Diffportrait3D, PanoHead, SphereHead, ControlNet for their open-sourced research. We thank Egor Zakharov, Zhenhui Lin, Maksat Kengeskanov, and Yiming Chen for the early discussions, helpful suggestions, and feedback.
