Welcome to LandmarkDiff

[dreamlessx]

Hey everyone, thanks for checking out LandmarkDiff.

This project predicts facial surgery outcomes from standard clinical photography using anatomically-conditioned latent diffusion. We are actively developing and looking for contributors.

Quick links:

• Getting started
• Contributing guide
• Open issues
• HF Spaces demo

Ways to contribute:

• Add new surgical procedure presets (otoplasty, septoplasty, etc.)
• Improve evaluation metrics
• Help with clinical validation
• Documentation and tutorials
• Performance optimization

Feel free to ask questions, share ideas, or show off what you have built.