# run-youngjoo/SC-FEGAN

SC-FEGAN : Face Editing Generative Adversarial Network with User's Sketch and Color (ICCV2019)

Repository: https://github.com/run-youngjoo/SC-FEGAN
Canonical: https://ross.abutalabs.com/products/sc-fegan
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-05-20T07:20:41+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2759, "days_push": 835, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3329, forks 519 (observed 2026-08-28T04:07:56.536504+00:00)

## What it is
SC-FEGAN is a GUI application that uses a generative adversarial network (SN-patchGAN discriminator with a U-Net generator) to edit face images from user sketches, color strokes, and masks. It was published at ICCV 2019 and ships as a Python/TensorFlow demo with a PyQt5 interface.

## Use cases
- edit face photos by drawing sketches and colors
- inpaint or restore missing regions of a face image
- add or remove accessories like earrings on a portrait
- generate synthetic face images from rough sketches
- try a research GAN for face editing locally

## When to choose
- you want interactive sketch-and-color face editing with a ready GUI
- you need a reference implementation of the ICCV 2019 SC-FEGAN paper for research
- you have a Linux machine with a GPU and can run TensorFlow 1.x-era code

## When to avoid
- you need commercial use - the model is CC BY-NC licensed
- you need multi-GPU support or modern maintained TensorFlow versions
- you want a production-grade face editing pipeline rather than a research demo

## Facets
- artifact type: application
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning, gui
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python
- tags: gan, face-editing, face-inpainting, sketch-to-image, image-generation, pyqt5, tensorflow, research-code, non-commercial-license, linux, gpu

## Member repositories
- run-youngjoo/SC-FEGAN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:56.536504+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:41:44.711348+00:00, confidence not recorded.
  - readme: https://github.com/run-youngjoo/SC-FEGAN (fetched 2026-08-28T04:07:56.536504+00:00, sha 94e48f6cc546)
- Data as of 2026-08-30T08:39:29.467469+00:00.