# clovaai/stargan-v2

StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

Repository: https://github.com/clovaai/stargan-v2
Canonical: https://ross.abutalabs.com/products/stargan-v2
Language: Python
License: NOASSERTION
License Family: other
Topics: pytorch, image-to-image-translation, generative-models, stargan-v2, cvpr2020
Last push: 2023-04-27T00:58:48+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2464, "days_push": 1225, "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 3617, forks 674 (observed 2026-08-28T04:08:11.808280+00:00)

## What it is
The official PyTorch implementation of StarGAN v2, a CVPR 2020 paper on diverse image-to-image translation across multiple domains using a single generative framework. It includes training and evaluation code, pre-trained models, and the AFHQ animal faces dataset.

## Use cases
- translate face images across attributes like hair color and gender
- generate diverse stylized versions of an input image
- convert animal face photos between cats, dogs, and wild species
- train a multi-domain image-to-image translation model
- benchmark generative image translation models
- download and use the AFHQ dataset for generative research

## When to choose
- you need multi-domain image-to-image translation with diverse outputs in one model
- you want to reproduce or build on CVPR 2020 StarGAN v2 research
- you need a high-quality animal faces dataset for generative modeling

## When to avoid
- you need a production-ready image editing service with support
- you lack a CUDA GPU, since training and inference are GPU-heavy
- you need the latest generative models such as diffusion-based translation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, image-processing, deep-learning
- domain: machine-learning, computer-vision, image-processing, artificial-intelligence
- platform: python
- tags: image-to-image-translation, generative-models, gan, pytorch, cvpr-2020, style-transfer, research-code, gpu, linux

## Member repositories
- clovaai/stargan-v2 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:11.808280+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 2026-08-29T18:31:59.689885+00:00, confidence not recorded.
  - readme: https://github.com/clovaai/stargan-v2 (fetched 2026-08-28T04:08:11.808280+00:00, sha d47c60606960)
- Data as of 2026-08-30T08:39:29.467469+00:00.