You've probably heard what crazy stuff AI, machine learning, and deep learning technologies are capable of. Like creating portraits of people who don’t exist, or making a 15th-century Renaissance painting out of your picture, or turning your static single selfie into a living image. Sounds crazy, because it is, but it turns out, this is not all.
Two programmers and AI enthusiasts, Justin Pinkney and Doron Adler, have just created a new mind-bending "toonification" system that basically turns your portrait into a cute cartoon character. Thanks to deep learning, the algorithm fine-tunes the original face and blends it with a cartoon model, keeping the identities the same, but the features cartoonish.
Apparently, their “Toonify” website got so much attention on social media, with people flocking to the website to toonify their selfies, that the costs got out of hand and the team had to temporarily turn off the server.
While they’re working on bringing it back to us, let’s take a look at some of the most amusing cartoon transformations down below so that you'll have time to decide whether to go for Elsa from Frozen, or stick to the Nemo makeover.
More info: Toonify.JustinPinkney.com
Justin Pinkney, who works as a software consultant at MathWorks in the UK, has been spending most of his time writing code, developing algorithms, training models, and encouraging people to embrace good software development practices.
Just recently, Justin and a fellow deep learning explorer Doron Adler developed a new “Toonify Yourself” system that got the internet buzzing big time. To find out more about their project, Bored Panda spoke to Justin, who said he has been messing around with GANs for quite a while and has trained lots of different models.
Justin said he came up with the idea of modifying networks “using 'layer swapping' to make realistic Ukiyo-e portraits.” He shared some code for this online and Doron Adler tried it out on some of his models, “showing really cool results of these almost real cartoon faces.”
Since then, they have been working together to train some new neural networks and produced the Toonify website.
Justin said that although people seem to have a lot of fun seeing what the neural network will turn their face into, they often mention that the results aren’t as good as a human artist could produce. “That's not really surprising, I don't think a human artist could produce 25,000 of these an hour (which we were doing at the peak of traffic),” he explained.
He is now working on making the website come back for free, which he promised will happen super soon. “Server running costs were the biggest challenge. These are big neural networks that are running, and although Google Cloud makes it easy to scale up to lots of traffic, it's still not cheap,” Justin explained.
He also put up a donation page, which you can check out right here, for access to the live site in order to help keep the site running.
Justin believes that there are lots of possibilities for what AI and deep learning technologies could do, and he thinks people are only just scratching the surface.
“Especially with so much code being open source and GPU resources being so accessible (via Google Collab), it means creators and artists can really easily try this stuff out.”
According to the deep learning explorer, the next steps for GANs are “in giving people more control over the images generated and making them more efficient in terms of training data and computing resources.”