Official Gradio demo for Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation.
🔥 We make the first attempt to integrate camera geometry into a unified multimodal model, introducing a camera-centric framework (Puffin) to advance multimodal spatial intelligence.
🖼️ Try to switch the task table and choose different prompts or images to get the generation or understanding results.

If Puffin is helpful, please help to star the Github Repo. Thank you.

📑 Citation
If our work is useful for your research, please consider citing:

@article{liao2025puffin,
title={Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation},
author={Liao, Kang and Wu, Size and Wu, Zhonghua and Jin, Linyi and Wang, Chao and Wang, Yikai and Wang, Fei and Li, Wei and Loy, Chen Change},
journal={arXiv preprint arXiv:2510.08673},
year={2025}
}

📧 Contact
If you have any questions, please feel free to reach me out at kang.liao@ntu.edu.sg.