vijishmadhavan/SkinDeep

Get Deinked!!

46
/ 100
Emerging

Uses a U-Net generator with self-attention and spectral normalization trained on synthetically generated tattoo-skin pairs (overlaid from APDrawing datasets and procedurally generated designs via OpenCV). Leverages perceptual loss based on VGG16 and progressive resizing to improve detail preservation and generalization across portrait and full-body images. Built on fastai and PyTorch, designed to run on GPU with Jupyter notebooks or Docker.

956 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

956

Forks

108

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jun 01, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/vijishmadhavan/SkinDeep"

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