FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning

CVPR 2026 | Paper | Code | Project Page

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.

Contents

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

Citation

@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}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for wlyu/FaceCam

Finetuned
(57)
this model

Paper for wlyu/FaceCam