There are many eternal mysteries in the human condition. Why are we here? Who created the universe? And most importantly, can Mona Lisa rap?
Microsoft announced a new artificial intelligence technology called VASA-1. VASA-1 can turn a photo of someone's face and a short clip of their voice into a lifelike video using a computer. And thanks to this breakthrough, the company is now able to recreate Leonardo da Vinci's famous painting “Mona Lisa” and the real thing that played actress Anne Hathaway's viral 2011 rap “Paparazzi.” I was able to create a video like this.
Microsoft's video is the latest example of tech companies making rapid advances with AI tools, but the rapping Mona Lisa definitely straddles the line between bizarre and creepy.
The software giant's new technology isn't the only use of AI to interpret and experience the world of art and the broader media. For example, Microsoft partner startup OpenAI has created similarly eye-catching videos through its text-to-video model, Sora. text prompt. Google has a similar tool called Lumiere.
Availability of these tools is limited. For everyday AI tools, be sure to check out CNET's hands-on reviews of image generators from Adobe Firefly, OpenAI's Dall-E 3, and Google's ImageFX, as well as reviews of chatbots like ChatGPT, Gemini, Claude, and more.
From deepfakes to reality
Microsoft's technology may seem like nothing new. Researchers have been demonstrating shockingly lifelike video manipulations for years, often calling them deepfakes. Some of the most impressive deepfakes include the Massachusetts Institute of Technology deepfake that in 2019 used AI technology to make it appear as though President Richard Nixon was giving a speech that he never actually gave. contained.
Experts are increasingly concerned that deepfakes could be used to spread disinformation.
These concerns haven't stopped app developers from effectively offering basic versions of what Microsoft has created. Such apps have become so popular that cybersecurity researchers warn that photos uploaded by people could be used to advance technology without the consent of the owner or subject. are doing.
Microsoft hopes these technologies will do more good than harm.
In a blog post announcing VASA-1, the company said: “While recognizing the potential for abuse, it is imperative that we recognize the significant positive potential of our technology.” “Benefits such as improving educational equity, increasing accessibility for individuals with communication difficulties, and providing companionship and therapeutic support for those in need make our research and other related pursuits important.” is emphasized.”
Microsoft added that it is “dedicated to developing AI responsibly, with the goal of advancing human well-being.”
Editor's note: CNET used an AI engine to create dozens of stories and label them accordingly. The notes you are reading are attached to articles that substantively cover the topic of AI, all written by professional editors and writers. Learn more about. AI policy.