You’ve probably seen a Wombo video floating around in your social media. Maybe it was Ryu van street fighter sing the “witch doctor” or the last three heads of the US Federal Reserve mimics Rick Astley’s “Never Going to Give You Up.” Each track contains exaggerated facial expressions and strange, sometimes nightmare animation. They are silly, fun and offer a useful look at the current situation of theft.
It certainly gets faster and easier to make AI-generated fakes, but the more compelling it is, the more work is needed. The realistic depth of Tom Cruise that went viral on TikTok, for example, required an experienced VFX artist, a top impersonator, and weeks of preparation to pull off. One-click flick that can be created with no effort and expertise still compares to those made by the Wombo app in comparison and will continue to do so for the immediate future. In the short term, deep fakes will naturally be fabricated and become an instant bait.
The Wombo app was launched from Canada late last month after a brief development process. “In August 2020, I had the idea for Wombo while smoking a joint with my roommate on the roof,” says app creator and Wombo CEO Ben-Zion Benkhin. The edge. The release of the product was a huge joy, ‘he says. “I followed the AI space, followed the meme space, followed the deep-false space and just saw the opportunity to do something cool.” In a few weeks, Benkhin estimates that the app has downloaded about 2 million downloads.
Wombo is free and easy to use. Just snap a photo of your face or upload a photo from your camera roll, and press a button to lip-sync the image with one of a handful of meme-adjacent songs. The app’s software will work its magic on anything that even vaguely looks like a face and many things that do not. Although similar applications have been compromised for privacy in the past, Benkhin is adamant that users’ data is secure. “We take privacy really seriously,” he says. “All data is deleted and we do not share it or send it to anyone else.”
The name of the app comes specifically from esports slang Super Smash Bros. Melee. ‘If a player ends up like a crazy combination, the cast will shout’ Wombo Combo ‘! Wombo Combo! ” Benkhin said. Consistent with this origin, Wombo was particularly popular with gamers who used it to animate characters from titles such as League of Legends, Dropout: New Vegas, and Dragon Age. ‘I dug in a bit [the origins of the slang], “Says Benkhin,” and there was apparently some pizza place that started it all, where they would put a bunch of additives on all their pizza and call it a Wombo Combo. ‘
Benkhin says the app works by changing faces using predefined choreography. He and his team shot the basic video for each song in his studio (“which is actually just a room in my apartment”) and then used it to animate each image. “We steal the movements from their face and apply them to your photo,” he says. The app is also an example of the fast-paced world of AI research, where new techniques can become consumer products within weeks. Benkhin notes that the software is built ‘on top of existing work’, but with subsequent tweaks and improvements that make it ‘our own model’.
At the moment, Wombo only offers 14 short tracks of songs to lip-sync with, but Benkhin says he plans to expand these options soon. When asked if the app has the right licenses for the music he uses, he does not want to answer, but says the team is working on it.
As with TikTok, however, it appears that the extent of Wombo may alleviate licensees’ concerns about rights. Benkhin says Wombo has already been approached by artists who want to get their music on the app, and it’s likely to provide a revenue stream in addition to the current premium level (which pays for priority processing and no ads in the app). ‘It’s going to give [artists] a completely new way of involving audiences, ”he says. “It gives them this new viral marketing tool.”
Wombo is far from the first app that uses machine learning to create fast and fun deep dives. Others include ReFace and FaceApp. But it’s the latest example of an increasingly prominent trend, as deep-dive apps become the latest meme templates, allowing users to merge favorite characters, trending songs, choreographed dances, public figures and so much more. The future of theft will definitely be remembered.