NVlabs/stylegan2

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

11184 stars · 2489 forks observed · 2026-08-28

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

The official TensorFlow implementation of StyleGAN2, NVIDIA's improved style-based generative adversarial network for high-quality unconditional image synthesis. It includes training code, pre-trained networks, and tooling from the paper 'Analyzing and Improving the Image Quality of StyleGAN'.

Use cases

• generate photorealistic faces with a GAN
• train a StyleGAN2 model on my own image dataset
• generate high-resolution images from latent vectors
• project real images into GAN latent space
• reproduce the StyleGAN2 paper results
• use pre-trained GAN networks for image synthesis research

When to choose

• you need the original, paper-faithful StyleGAN2 implementation in TensorFlow
• you want to reproduce or build on the published research results
• you need the official pre-trained networks from NVIDIA

When to avoid

• you prefer PyTorch - use StyleGAN2-ADA-PyTorch instead
• you need actively maintained code with modern dependency support
• you want a simple high-level API rather than research code
• you need permissive licensing for commercial use

Facets

library · maturity maintenance

machine-learning deep-learning image-processing gpu-computing deep-learning computer-vision image-processing artificial-intelligence python gan generative-models tensorflow stylegan image-synthesis research-code nvidia linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="NVlabs/stylegan2")