facebookresearch/pytorch_GAN_zoo

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1627 stars · 268 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning image-processing data-science machine-learning deep-learning image-processing artificial-intelligence python cross-platform gan pytorch generative-models stylegan dcgan progressive-growing image-generation facebook-research gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="facebookresearch/pytorch_GAN_zoo")