sanviiz/hairstyle-try-on

Virtual hair makeover from image processing project.

41
/ 100
Emerging

Leverages semantic segmentation maps to isolate hair regions, then applies Stochastic Differential Editing (SDEdit) with fast marching inpainting to transfer hairstyles and colors from target images onto source faces. Built on SDEdit's diffusion-based architecture, it handles occluded faces and enables single-image hairstyle transfer through noise-level conditioning. Includes a Streamlit demo deployable on Google Colab with pre-trained face segmentation and CelebA-HQ checkpoints.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

45

Forks

9

Language

Python

License

MIT

Last pushed

Jul 19, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sanviiz/hairstyle-try-on"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.