NVlabs/stylegan2-ada
Official TensorFlow implementation of StyleGAN2 with adaptive discriminator augmentation for training generative adversarial networks with limited data.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official TensorFlow implementation of StyleGAN2 with adaptive discriminator augmentation (ADA), a technique that stabilizes GAN training when data is limited. The approach uses adaptive data augmentation to prevent discriminator overfitting, enabling high-quality image generation with as few as a few thousand training images. It supports mixed-precision training for faster computation and lower GPU memory usage.
Frequently asked
- What is NVlabs/stylegan2-ada?
- Official TensorFlow implementation of StyleGAN2 with adaptive discriminator augmentation for training generative adversarial networks with limited data.
- Is stylegan2-ada open source?
- Yes — NVlabs/stylegan2-ada is an open-source project tracked on heatdrop.
- What language is stylegan2-ada written in?
- NVlabs/stylegan2-ada is primarily written in Python.
- How popular is stylegan2-ada?
- NVlabs/stylegan2-ada has 1.8k stars on GitHub.
- Where can I find stylegan2-ada?
- NVlabs/stylegan2-ada is on GitHub at https://github.com/NVlabs/stylegan2-ada.