yunjey/stargan

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

5296 stars · 953 forks observed · 2026-08-28

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

Official PyTorch implementation of StarGAN, a unified generative adversarial network for multi-domain image-to-image translation (CVPR 2018). It trains a single model to translate images across multiple domains, demonstrated on facial attribute transfer and expression synthesis.

Use cases

• translate face images across attributes like hair color and gender with one model
• synthesize facial expressions from a single photo
• train a multi-domain image-to-image translation GAN
• reproduce StarGAN results from the CVPR 2018 paper
• experiment with GAN training on CelebA or RaFD datasets

When to choose

• you need multi-domain image-to-image translation with a single model
• you want a well-cited reference implementation of StarGAN for research
• you are working with facial attribute transfer or expression synthesis on CelebA/RaFD

When to avoid

• you need the improved StarGAN v2 - use clovaai/stargan-v2 instead
• you need actively maintained code with recent PyTorch compatibility
• you need production-ready image translation rather than research code

Facets

library · maturity maintenance

machine-learning deep-learning image-processing machine-learning deep-learning computer-vision image-processing python gan image-to-image-translation pytorch research-code cvpr2018 face-attribute-transfer linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yunjey/stargan")