Skip to Content
Artificial intelligence

Turn selfies into classical portraits with the AI that fuels deepfakes

An example of an AI-generated classical portrait
An example of an AI-generated classical portraitAI Portraits

It’s the same AI technique behind deepfakes, but also a $432,500 artwork.

The news: The tool lets users upload their photos, then view a classical-style faux watercolor, oil, or ink portrait based on the photo a few seconds later. Each one is unique. You can give it a go here.

How it was made: The tool’s creators at the MIT-IBM Watson AI Lab used generative adversarial network (GAN) models, a popular AI technique. It involves getting two neural networks to duel each other to produce an acceptable outcome: a generator, which looks at examples and tries to mimic them, and a discriminator, which judges if they are real by comparing them with the same training examples. In this case, they used 45,000 portrait images to train the program, including paintings by Titian, van Gogh, and Rembrandt.

No smiling, please: None of the portraits it creates include smiles, because it was uncommon for such overt facial expressions to be painted in the era the training examples cover. 

Is it safe? You might worry about the privacy implications of uploading your photo, especially after the recent furor over FaceApp. However, the researchers have promised the pictures are immediately deleted after processing by their servers, and they won’t be used for any other purpose. 

Sign up here for our daily newsletter The Download to get your dose of the latest must-read news from the world of emerging tech.

Deep Dive

Artificial intelligence

The inside story of how ChatGPT was built from the people who made it

Exclusive conversations that take us behind the scenes of a cultural phenomenon.

AI is dreaming up drugs that no one has ever seen. Now we’ve got to see if they work.

AI automation throughout the drug development pipeline is opening up the possibility of faster, cheaper pharmaceuticals.

GPT-4 is bigger and better than ChatGPT—but OpenAI won’t say why

We got a first look at the much-anticipated big new language model from OpenAI. But this time how it works is even more deeply under wraps.

The original startup behind Stable Diffusion has launched a generative AI for video

Runway’s new model, called Gen-1, can change the visual style of existing videos and movies.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.