# NVlabs/stylegan2-ada-pytorch

StyleGAN2-ADA - Official PyTorch implementation

Repository: https://github.com/NVlabs/stylegan2-ada-pytorch
Canonical: https://ross.abutalabs.com/products/stylegan2-ada-pytorch
Homepage: https://arxiv.org/abs/2006.06676
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-05-10T18:13:37+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": 2059, "days_push": 845, "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 4487, forks 1241 (observed 2026-08-28T04:08:51.261312+00:00)

## What it is
Official PyTorch implementation of StyleGAN2-ADA, a generative adversarial network with adaptive discriminator augmentation for training with limited data. It supports training from scratch or fine-tuning pre-trained GANs on datasets of only a few thousand images.

## Use cases
- train a GAN on a few thousand images
- generate synthetic faces with StyleGAN2
- fine-tune a pre-trained StyleGAN on my own dataset
- reproduce StyleGAN2-ADA paper results in PyTorch
- compute FID metrics for generated images
- convert my image dataset to the ZIP/PNG training format

## When to choose
- you need state-of-the-art GAN training with limited training data
- you want a verified PyTorch port compatible with TensorFlow StyleGAN2 pickles
- you have NVIDIA GPUs and want faster training than the TF version

## When to avoid
- you need a permissively licensed model for commercial use without checking NVIDIA's license
- you want diffusion models or modern generative approaches instead of GANs
- you lack a CUDA-capable GPU

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, cli
- domain: machine-learning, computer-vision, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: gan, stylegan2, pytorch, generative-models, nvidia, image-synthesis, research-code, gpu, linux

## Member repositories
- NVlabs/stylegan2-ada-pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:51.261312+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 2026-08-29T18:20:29.844805+00:00, confidence not recorded.
  - readme: https://github.com/NVlabs/stylegan2-ada-pytorch (fetched 2026-08-28T04:08:51.261312+00:00, sha 80eccda00e7d)
  - homepage: https://arxiv.org/abs/2006.06676 (fetched 2026-08-29T09:06:44.229792+00:00, sha 8fd164aaf20a)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T09:06:44.239078+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T09:06:44.242920+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T09:06:44.245592+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T09:06:44.240898+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.