lucidrains/stylegan2-pytorch

Health v2 · maintenance only

Adoption not part of the score

3783 stars · 582 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A simple PyTorch implementation of StyleGAN2, a state-of-the-art generative adversarial network, trainable entirely from the command line without coding. It lets users train GANs on their own image datasets and generate novel images or latent-space interpolation videos.

Use cases

• train a GAN on my own image dataset
• generate realistic fake images of faces or objects
• create latent space interpolation videos
• learn how StyleGAN2 works in PyTorch
• generate images of things that don't exist
• experiment with generative adversarial networks without coding

When to choose

• you want a minimal, easy-to-use StyleGAN2 implementation trainable via CLI
• you have a GPU with CUDA and a folder of training images
• you want a pip-installable package with checkpointing and resumption built in

When to avoid

• you need the latest GAN architectures or state-of-the-art image quality
• you require distributed or multi-GPU training at scale
• you have no GPU available, since training requires CUDA

Facets

library · maturity maintenance

machine-learning deep-learning image-processing cli deep-learning machine-learning artificial-intelligence image-processing python cli cross-platform stylegan2 generative-adversarial-network pytorch image-generation gan gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lucidrains/stylegan2-pytorch")