1/1 by Hulki Okan Tabak, minted on Artbreeder GAN Works smart contract on Manifold

Dark Child is a 4 part series created from my Artbreeder experiments during October 2021

Artbreeder is a GAN model. It uses a combination of BigGAN and StyleGAN models to generate and modify images of faces, landscapes, and paintings, among other categories.

GANs, or Generative Adversarial Networks, are a type of machine learning model that can generate new data instances that resemble your training data. They work by training two models simultaneously: a generator and a discriminator. The generator creates new data, and the discriminator tries to distinguish between real and generated data. The generator and discriminator are constantly competing with each other, which helps the generator to learn to create more realistic data.

Artbreeder uses GANs to generate new images and to modify existing images. For example, you can use Artbreeder to generate a new portrait of a person, or to modify an existing portrait to make it look more like someone else. You can also use Artbreeder to generate new landscapes or paintings.