README.md

---
license: apache-2.0
base_model:
- Wan-AI/Wan2.2-I2V-A14B
---

# FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning

**CVPR 2026** | [Paper](https://arxiv.org/abs/2412.17812) | [Code](https://github.com/weijielyu/FaceCam) | [Project Page](https://www.wlyu.me/FaceCam/)

FaceCam generates portrait videos with precise camera control from a single input video and a target camera trajectory.

For usage instructions, see the [official code repository](https://github.com/weijielyu/FaceCam).

## Contents

- **gaussians.ply**: Proxy 3D head representation
- **wan2.2_14b**: Fine-tuned Wan2.2-I2V-A14B model weights for camera control

## Citation

```bibtex
@misc{lyu2025facelift,
    title={FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads}, 
    author={Weijie Lyu and Yi Zhou and Ming-Hsuan Yang and Zhixin Shu},
    year={2025},
    eprint={2412.17812},
    archivePrefix={arXiv},
    primaryClass={cs.CV},
    url={https://arxiv.org/abs/2412.17812}
}
```