#127 · Primary category: Image Generation

HyperGAN

artificial-intelligence computer-vision gan generative-adversarial-network hypergan machine-learning machine-learning-api online-learning python pytorch sponsors unsupervised-learning

Composable GAN framework with api and user interface

Project last updated:01/21/23

GitHub Stars

1.2K

Forks

160

Contributors

19

License

MIT

Why we included this project

HyperGAN is a PyTorch library that covers the generative workflow from dataset preparation to training and sampling. You configure a model through a command-line tool or the Python API, so you don't have to wire generator, discriminator, and loss functions by hand. That's handy for artists experimenting with style transfer and colorization, researchers who want to test a new setup quickly, and developers who need a reproducible base to customize. The repo includes runnable examples for colorization and logo generation, along with an interface for inspecting what the model produces. The project is in open beta, so the API and documentation still have rough edges.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category