# facebookresearch/pytorch_GAN_zoo

A mix of GAN implementations including progressive growing

Repository: https://github.com/facebookresearch/pytorch_GAN_zoo
Canonical: https://ross.abutalabs.com/products/pytorch_gan_zoo
Language: Python
License: BSD-3-Clause
License Family: permissive
Archived: true
Last push: 2021-10-12T21:33:09+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2785, "days_push": 1786, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1627, forks 268 (observed 2026-08-28T04:05:13.191778+00:00)

## What it is
A PyTorch toolbox of GAN implementations including Progressive Growing GAN, DCGAN, and StyleGAN (beta), plus tools like GDPP, AC-GAN conditioning, and evaluation metrics (SWD, Inception Score). Built for researchers and developers training generative image models.

## Use cases
- train a progressive growing GAN on celebaHQ to generate faces
- generate 1024x1024 fake images with StyleGAN or PGAN
- train a GAN on my own image dataset
- evaluate GAN quality with inception score and SWD
- conditionally generate images with AC-GAN
- generate images inspired by a reference image
- compare DCGAN and PGAN implementations in PyTorch

## When to choose
- you want ready-to-run PyTorch implementations of PGAN, DCGAN, or StyleGAN for image generation research
- you need GAN training utilities and evaluation metrics in one toolbox
- you want to reproduce Facebook Research GAN experiments on standard datasets

## When to avoid
- you need actively maintained code with recent PyTorch compatibility (last release 2021)
- you want diffusion models or modern generative approaches instead of GANs
- you need production image generation rather than research training

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, data-science
- domain: machine-learning, deep-learning, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: gan, pytorch, generative-models, stylegan, dcgan, progressive-growing, image-generation, facebook-research, gpu, linux

## Member repositories
- facebookresearch/pytorch_GAN_zoo (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:13.191778+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 2026-08-30T03:48:24.308686+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/pytorch_GAN_zoo (fetched 2026-08-28T04:05:13.191778+00:00, sha 696bd488ec65)
- Data as of 2026-08-30T08:39:29.467469+00:00.