“Microsoft, using artificial intelligence, made Mona Lisa by Leonardo da Vinci read rap. However, many were outraged by this idea from the tech giant.

Microsoft introduced its new AI technology called VASA-1, which can combine still images and audio clips to create realistic video clips of talking faces.”

To showcase this, Microsoft released a clip of Mona Lisa rapping to the song “Paparazzi.”

The clip, part of a study published on April 16, quickly went viral: by Monday morning, one post containing the video had garnered 7.1 million views on X.

People had strong reactions to the viral video: “Why does this need to exist? I can’t think of anything positive about it”; “Another day, another terrible AI video”; “It’s wild, quirky, and creepy all at the same time”; “If only da Vinci could witness this.”

Microsoft explained that the “out-of-distribution generalization” method demonstrates the “ability to process input photos and audio that are outside the training distribution.”

The company emphasized the positive impact of the new artificial intelligence technology, such as increasing equality in education, improving accessibility for those with communication issues, and offering friendly communication or therapeutic support to those in need.

However, it also warned that the new technology is not intended for “misleading or deceiving” and there is a risk of it being misused.