NVlabs/stylegan2-ada-pytorch

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

4487 stars · 1241 forks observed · 2026-08-28

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

Official PyTorch implementation of StyleGAN2-ADA, a generative adversarial network with adaptive discriminator augmentation for training with limited data. It supports training from scratch or fine-tuning pre-trained GANs on datasets of only a few thousand images.

Use cases

• train a GAN on a few thousand images
• generate synthetic faces with StyleGAN2
• fine-tune a pre-trained StyleGAN on my own dataset
• reproduce StyleGAN2-ADA paper results in PyTorch
• compute FID metrics for generated images
• convert my image dataset to the ZIP/PNG training format

When to choose

• you need state-of-the-art GAN training with limited training data
• you want a verified PyTorch port compatible with TensorFlow StyleGAN2 pickles
• you have NVIDIA GPUs and want faster training than the TF version

When to avoid

• you need a permissively licensed model for commercial use without checking NVIDIA's license
• you want diffusion models or modern generative approaches instead of GANs
• you lack a CUDA-capable GPU

Facets

library · maturity maintenance

machine-learning deep-learning image-processing cli machine-learning computer-vision image-processing artificial-intelligence python cross-platform gan stylegan2 pytorch generative-models nvidia image-synthesis research-code gpu linux

Member repositories

For agents

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