# stylegan-human/StyleGAN-Human

StyleGAN-Human: A Data-Centric Odyssey of Human Generation

Repository: https://github.com/stylegan-human/StyleGAN-Human
Canonical: https://ross.abutalabs.com/products/stylegan-human
Language: Python
License Family: other
Last push: 2025-01-26T03:44:04+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 3, release rhythm 35, longevity 100
- inputs: {"age_days": 1679, "days_push": 584, "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 1189, forks 150 (observed 2026-08-28T04:03:55.750891+00:00)

## What it is
StyleGAN-Human is a research project providing a large-scale annotated human image dataset (230K+ samples) and StyleGAN-based models for unconditional full-body human image generation. It includes a model zoo, training code, and human editing applications, accompanying a data-centric study of human generation.

## Use cases
- generate photorealistic full-body human images
- train a StyleGAN model on human photos
- get a large annotated human image dataset for GAN research
- edit attributes of generated human images
- study how dataset size and alignment affect GAN quality

## When to choose
- you need pretrained models or data for full-body human image generation
- you are researching data-centric factors in GAN training
- you want a human image dataset with parsing and keypoints

## When to avoid
- you need 3D-aware or video human generation
- you want a production-ready image generation service
- you need a permissively licensed project - the repo has no license

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, data-generation
- domain: deep-learning, computer-vision, image-processing, artificial-intelligence
- platform: python
- tags: stylegan, gan, human-image-generation, model-zoo, research, dataset, image-synthesis, gpu, linux

## Member repositories
- stylegan-human/StyleGAN-Human (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:55.750891+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 2026-08-30T06:23:21.126246+00:00, confidence not recorded.
  - readme: https://github.com/stylegan-human/StyleGAN-Human (fetched 2026-08-28T04:03:55.750891+00:00, sha 37f38b7ed227)
- Data as of 2026-08-30T08:39:29.467469+00:00.