The bot that can paint you and Taylor Swift in the style of Picasso

Alex Hern in the style of Rembrandt, and Taylor Swift in the Style of Picasso Composite: Alex Hern, Evan Agostini/Invision/AP, Deep Forger

Deep Forger is a Twitter account which will generate a version of any picture fed to it in the style of any other picture.

The results can be entrancing. Here’s me at a party in the style of Rembrandt:

@alexhern Here’s the breakdown of your forgery, avec style from Rembrandt. #NeuralArt #DeepStyle pic.twitter.com/pStvAJSOOO

— The Deep Forger (@DeepForger) November 25, 2015

And here’s Taylor Swift in the style of Pablo Picasso, which was less successful:

@alexhern Here’s the breakdown of your painting, with style from Pablo Picasso. #DeepStyle #StyleNet pic.twitter.com/xJexRhI3cQ

— The Deep Forger (@DeepForger) November 26, 2015

If you feed the bot just one input, it automatically merges it with a great artist. But you can also submit two pictures, and it will generate a version of the first in the style of the second. So you can get your headshot in the style of Japanese iPhone game Neko Atsume:

This enthralling #DeepForgery was synthesized using a convolutional network on commission; que c’est impressionnant. pic.twitter.com/Bt7fJEePfO

— The Deep Forger (@DeepForger) November 25, 2015

Or the Firefox logo in the style of the Mozilla logo (bit niche, this one):

@dolske concepted this #GenerativeArt #StyleNet. pic.twitter.com/anY1MzT7BK

— The Deep Forger (@DeepForger) November 25, 2015

Others are … weirder.

This captivating #DeepForgery was synthesized using deep convolution networks on commission; que c’est éblouissant. pic.twitter.com/NwPv7VqXyt

— The Deep Forger (@DeepForger) November 26, 2015

And some are just perfect:

This stimulating #DeepForgery is synthesized with a deep neural algorithm on commission; que c’est passionnant! pic.twitter.com/K9PQw2ARdE

— The Deep Forger (@DeepForger) November 24, 2015

Deep Forger is only the latest in a long line of robots doing trippy things with Neural Networks.

First, there was Deep Dream, the Google-built algorithm which purports to let us see what a computer could dream about. The robot used a neural network to identify images by their key features, but it turns out that if you create a feedback loop and feed the same network white noise, the results are pretty trippy:

A dreamscape made from random noise. Photograph: Google

Then, Google freed its neural networks to run across the internet. The company made the software behind the images open-source, allowing other users to make their own horrifying images:

@kcimc this little monster is a half eaten doughnut :D https://t.co/zZ5euPgvsF #deepdream

— Dunks (@dunknicoll) July 2, 2015

In September, a team of German researchers managed to build a similar neural network, but with a much more focused goal: mimic great artists.

The Eiffel tower gets the Van Gogh treatment. Image: kaishengtai/GitHub

At the time, Hannah Jane Parkinson wrote that the algorithm could “accurately copy the painting style of artists as disparate as Pablo Picasso and Vincent Van Gogh – and in just 60 minutes.” Deep Forger beats that by fair margin.

The newest bot is created by Vienna-based game developer Alex Champandard, and is open for submissions. Why not try it yourself, and highlight the best in the comments below?