tkarras/progressive_growing_of_gans

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

6179 stars · 1083 forks observed · 2026-08-28

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

Official TensorFlow implementation of the ICLR 2018 NVIDIA paper 'Progressive Growing of GANs', which trains generators and discriminators from low to high resolution for stable, high-quality image synthesis. It includes training code, pretrained networks, and a higher-quality CelebA dataset.

Use cases

• train a GAN to generate high-resolution images
• reproduce the progressive growing of GANs paper results
• generate synthetic celebrity faces with a GAN
• study progressive GAN training methodology
• benchmark GAN image quality with inception score

When to choose

• you want the reference implementation of the Progressive GAN paper
• you need to generate 1024x1024 images with GANs on NVIDIA GPUs
• you are doing research on GAN training stability and metrics

When to avoid

• you need a maintained, modern GAN framework - use StyleGAN2-ADA or StyleGAN3 instead
• you want diffusion models or transformer-based generators
• you need a non-TensorFlow or CPU-only training setup

Facets

library · maturity maintenance

machine-learning deep-learning image-processing gpu-computing deep-learning machine-learning computer-vision image-processing artificial-intelligence python gan generative-adversarial-networks tensorflow research-code image-generation nvidia-research iclr-2018 gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tkarras/progressive_growing_of_gans")