OmniHuman sample videos demonstrate the scope of both human and animal movement. OmniHuman screenshot by Leslie KatzTikTok owner ByteDance has unveiled OmniHuman-1, an AI system that can generate lifelike videos of people talking, gesturing, singing, playing instruments and more all from a single photo.OmniHuman significantly outperforms existing methods, generating extremely realistic human videos based on weak signal inputs, especially audio, reads a research paper on the tool published Sunday on online open-access archive arXiv. It supports image inputs of any aspect ratio, whether they are portraits, half-body or full-body images, delivering more lifelike and high-quality results across various scenarios.On the OmniHuman-1 project page, researchers share sample videos showcasing the tools capabilities. Examples demonstrate hand and body movements seen from multiple angles, animated characters, animals and historical figures brought back to life.In one crisp black and white video, Albert Einstein speaks in front of a blackboard, punctuating his words with hand gestures and subtle facial expressions: What would art be like without emotions? It would be empty, he says. What would our lives be like without emotion? They would be empty of values.Its as if weve gone back in time to watch the famed theoretical physicist deliver a university lecture, only the footage looks like it was filmed today.Theyre very impressive, Freddy Tran Nager, a clinical associate professor of communications at USCs Annenberg School for Communication and Journalism, said in an interview after viewing the sample videos. If you were thinking of reviving Humphrey Bogart and casting him in a film, Im not sure how they would look. But on a small screen, especially on a phone, these are impressive.MORE FOR YOUThe tool places ByteDance, and therefore TikTok, squarely in the crowded and competitive race to create the best, most realistic-looking footage of AI-generated humans. These digital figures are popping everywhere as virtual influencers who promote products, government officials helping citizens navigate social services and faux versions of celebrities who can entertain and interact with fans or concerningly, appear in fake political endorsements.Tran says he could envision systems such as OmniHuman being used in educational settings by both teachers and students: I would like Marilyn Monroe to teach me statistics. Because of OmniHumans connection to TikTok, he could also envision it eventually being used by burned-out content creators who turn to virtual versions of themselves for a respite.Or, he said, TikTok can say, You know what? Now we can just create videos on our own. Who needs the human beings?Samantha G. Wolfe, an adjunct professor at NYUs Steinhardt School of Culture, Education and Human Development, also sees both the promise and potential peril of tools like OmniHuman.Creating something from just a picture and making it look like its really talking and really moving is fascinating from a technological standpoint, but it could have a lot of potential negative consequences too, she said in an interview. Pretend versions of business leaders or political leaders saying something that isnt accurate can have a huge influence on a business, or a huge influence on a country.As AI-generated videos grow more sophisticated, so do the risks, Wolfe said. When it starts to look more and more like reality, more and more like humans actually doing it, the likelihood of people believing it becomes so much greater, she said.The ByteDance team trained OmniHuman on more than 18,700 hours of human video data, combining multiple types of inputs, such as text, audio and physical poses, though ByteDance did not immediately respond to a request for comment for more specifics on the training data.OmniHuman isnt the first AI tool to generate videos from a single photo, but what sets it apart in Nagers eyes is the amount of training data the team behind it has access to. If you created a TikTok video, he said, theres a good chance youre now in a database thats going to be used to create virtual humans.