online tool AI portraits is developed with the intent to generate realistic images — the level of resemblance of the resulting portrait is close to the user’s face but deliberately not too similar to the starting image. using generative adversarial networks (GANs), the website scans your picture and creates a resembling face by overlapping millions of actors’ photos. the goal — as the developers explain — is to share the experience of being portrayed by an AI algorithm, discover how AI sees you, while there is no aim to improve or deform the starting picture.

artificial intelligence generates your portrait based on millions of actors' photos
AI portraits always generates a frontal close-up — the quality of the portrait improves with a frontal view.

 

 

‘we use frontal images of actors to activate portraits with our GAN,’ explains mauro martino, the co-developer of AI portraits. ‘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 that are sedimented in the neural network.’

artificial intelligence generates your portrait based on millions of actors' photos
the tool finds a way to portray the parts of your face missing at the photo 

 

 

what you see at the generated portrait is a fictitious recreation of yourself — the training data of the actors vaporizes your image and creates a dialogue between you and the celebrities. the pictures generated by AI portraits are completely new and inspired by the face identified in the photos. there are no filters or visual effects — the portrait is generated by the company’s artificial intelligence algorithms. 

artificial intelligence generates your portrait based on millions of actors' photos
AI Portraits continues to generate a frontal close-up by reconstructing the missing parts of the face

 

 

 

 

artificial intelligence generates your portrait based on millions of actors' photos
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)

 

 

designboom has received this project from our ‘DIY submissions‘ feature, where we welcome our readers to submit their own work for publication. see more project submissions from our readers here.

 

edited by: maria erman | designboom