# NVlabs/stylegan2-ada

StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation

Repository: https://github.com/NVlabs/stylegan2-ada
Canonical: https://ross.abutalabs.com/products/stylegan2-ada
Homepage: https://arxiv.org/abs/2006.06676
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-07-02T14:00:16+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": 2156, "days_push": 792, "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 1829, forks 484 (observed 2026-08-28T04:05:41.677271+00:00)

## What it is
NVIDIA's official TensorFlow implementation of StyleGAN2 with adaptive discriminator augmentation (ADA), enabling high-quality GAN training on small datasets. It includes command-line tools for training, image generation, and projection, though it has been superseded by the official PyTorch version.

## Use cases
- train a GAN on a few thousand images
- generate synthetic faces with stylegan2
- fine-tune a pretrained GAN on my own dataset
- reproduce the ADA paper training runs
- project real images into latent space of a GAN
- improve FID on CIFAR-10 with limited data

## When to choose
- you need the original TensorFlow implementation for research reproducibility
- you have limited training images and want stable GAN training via ADA
- you need to load network pickles from StyleGAN or StyleGAN2

## When to avoid
- you prefer PyTorch - use the official stylegan2-ada-pytorch instead
- you need actively maintained code or a permissive license
- you lack a CUDA GPU

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, cli
- domain: machine-learning, deep-learning, computer-vision, image-processing, artificial-intelligence
- platform: python
- tags: gan, stylegan2, generative-models, tensorflow, discriminator-augmentation, nvidia-research, image-synthesis, limited-data-training, linux, gpu

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:41.677271+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 2026-08-30T03:19:21.444303+00:00, confidence not recorded.
  - readme: https://github.com/NVlabs/stylegan2-ada (fetched 2026-08-28T04:05:41.677271+00:00, sha 3bd8119e4d65)
  - homepage: https://arxiv.org/abs/2006.06676 (fetched 2026-08-29T10:58:28.541308+00:00, sha 8fd164aaf20a)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T10:58:28.544001+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T10:58:28.549878+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T10:58:28.551982+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T10:58:28.546875+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.