run-youngjoo/SC-FEGAN

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3329 stars · 519 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

application · maturity maintenance

image-processing machine-learning deep-learning gui computer-vision image-processing deep-learning artificial-intelligence python gan face-editing face-inpainting sketch-to-image image-generation pyqt5 tensorflow research-code non-commercial-license linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="run-youngjoo/SC-FEGAN")