AI Portraits | The experience of being portrayed by an AI algorithm

I'm very proud to announce the launch of my art project with Luca Stornaiuolo. https://aiportraits.com experience the #selfai - create your portrait with an AI algorithm.

One year after the first exhibition, AI Portraits is available for everyone!!! 

The images generated by AI Portraits are completely new and inspired by the face identified in the photos. There are no filters and visual effects, the portrait is generated by our Artificial Intelligence algorithms. 

AI Portraits is based on Generative Adversarial Networks (GANs):

The GAN is composed of two neural networks, one learns to recognize portraits of the actors (Discriminator), and the other learns to generate them (Generator).

AI Portraits was developed with intent to generate realistic portraits. The level of resemblance of the portrait is high but deliberately not too similar to the starting image, the data (faces of actors and actresses) on which the model was trained re-emerge in portraits. The intention is to share the experience of being portrayed by an AI algorithm, to discover how AI sees you. There is no willingness to improve or deform the starting picture. 

What is real and what is fiction? The system is trained on millions of photos of actors and actresses. We are using the faces of people in front of the camera to activate portraits with our GAN. The result is an image that examines the concept of identity, pushing the boundaries between the individual that recognizes herself/himself and the collection of faces from the society of spectacle that are sedimented in the neural network. 

What I see is myself? It is a fictitious re-creation of myself, the training data of the actors vaporize my image and create a dialogue between me and the celebrities. We see a cinematographic self, independent and separate from my actual self.