GAN Station. A Node based Generative Adversarial Network tool.

• Drag and drop node based interface.
• Prepared for ease of use.
• Effortless training and testing of image based models.

The goal of GANSta is to provide an entry point for curious artist and designers to explore the possibilities that modern Generative Adversarial Networks present to their creative process.

Install the dependencies.

$ pip install -r requirements.txt

Run GANsta

$ python main.py

• Tutorial and Further Documentation
• Extending available GAN nodes

• StarGAN v2: Diverse Image Synthesis for Multiple Domains Yunjey Choi, Jung-Woo Ha Clova AI Research (NAVER Corp.)
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020

• Unofficial PyTorch implementation of StarGAN-v2

• pyqt-node-editor

Creative Commons BY-NC 4.0