lucidrains/gigagan-pytorch
A PyTorch implementation of GigaGAN, Adobe's state-of-the-art generative adversarial network for high-resolution image synthesis.
Not currently ranked — collecting fresh signals.
star history
This repository provides a complete implementation of GigaGAN, a cutting-edge GAN architecture for image generation. It includes the main generator-discriminator training code along with 1k to 4k upsampler modules. The implementation incorporates techniques from the author’s lightweight GAN work for faster convergence and improved stability, including skip layer excitation and reconstruction auxiliary loss in the discriminator.
Frequently asked
- What is lucidrains/gigagan-pytorch?
- A PyTorch implementation of GigaGAN, Adobe's state-of-the-art generative adversarial network for high-resolution image synthesis.
- Is gigagan-pytorch open source?
- Yes — lucidrains/gigagan-pytorch is open source, released under the MIT license.
- What language is gigagan-pytorch written in?
- lucidrains/gigagan-pytorch is primarily written in Python.
- How popular is gigagan-pytorch?
- lucidrains/gigagan-pytorch has 1.9k stars on GitHub.
- Where can I find gigagan-pytorch?
- lucidrains/gigagan-pytorch is on GitHub at https://github.com/lucidrains/gigagan-pytorch.