[ICCV 2025] FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads
💡 Tips for Best Results
Works best with near-frontal portrait images.
The provided checkpoints were not trained with accessories (glasses, hats, etc.). Portraits containing accessories may produce suboptimal results.
If face detection fails, try disabling auto-cropping and manually crop to square.
Inference complete when the turntable video is generated, the interactive 3D gaussian might take several seconds to load.
Input Portrait Image
Drop Image Here
- or -
Click to Upload
Auto Cropping
Guidance Scale
↺
1
10
Random Seed
Generation Steps
↺
10
100
Generate 3D Head
Examples
Input Portrait Image
Auto Cropping
Guidance Scale
Random Seed
Generation Steps
3D Reconstruction Views
Turntable Animation (360° View)
Download 3D Model (.ply)