# NVlabs/stylegan

StyleGAN - Official TensorFlow Implementation

Repository: https://github.com/NVlabs/stylegan
Canonical: https://ross.abutalabs.com/products/stylegan
Homepage: https://arxiv.org/abs/1812.04948
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-04-10T08:30:29+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": 2767, "days_push": 875, "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 14416, forks 3135 (observed 2026-08-28T04:11:06.960622+00:00)

## What it is
The official TensorFlow implementation of StyleGAN, NVIDIA's style-based generator architecture for generative adversarial networks from the CVPR 2019 paper. It enables training and synthesizing high-quality photorealistic images, notably human faces, with scale-specific control over generated attributes.

## Use cases
- generate photorealistic human faces with a GAN
- train a style-based generator on my own image dataset
- control specific attributes of generated images via latent vectors
- reproduce the StyleGAN CVPR 2019 paper results
- interpolate between faces in latent space
- study disentanglement of latent factors in GANs

## When to choose
- you need the original StyleGAN architecture exactly as published
- you are doing GAN research or reproducing the paper
- your stack already uses TensorFlow 1.x with CUDA/cuDNN
- you want the official pretrained FFHQ face generator

## When to avoid
- you want modern PyTorch tooling - use StyleGAN2-ADA-PyTorch or StyleGAN3 instead
- you need TensorFlow 2.x or recent GPU support
- you need a permissively licensed model - it is CC BY-NC (non-commercial)
- you want actively maintained code - this repo is legacy

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, machine-learning, image-processing, computer-vision
- platform: python
- tags: gan, stylegan, generative-models, tensorflow, face-generation, research-code, nvidia, gpu, linux

## Member repositories
- NVlabs/stylegan (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:06.960622+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 2026-08-29T17:12:35.579323+00:00, confidence not recorded.
  - readme: https://github.com/NVlabs/stylegan (fetched 2026-08-28T04:11:06.960622+00:00, sha 0263bef3667d)
  - homepage: https://arxiv.org/abs/1812.04948 (fetched 2026-08-29T08:06:03.804736+00:00, sha f9e6e5606d99)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:06:03.807547+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:06:03.811042+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:06:03.812738+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:06:03.809456+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.