In a viral video that shocked the internet, Microsoft's new AI app made the iconic Mona Lisa painting sing.
As detailed, Microsoft has introduced VASA-1, a breakthrough artificial intelligence (AI) model that can generate stunningly realistic videos of talking human faces.
This innovative AI image-to-video model can transform a still photo of a person's face into a lifelike animation with synchronized lip movements, facial expressions, and head movements that mimic natural human behavior. Masu.
A recent demonstration video showcasing the capabilities of VASA-1 has taken social media by storm, leaving users in awe.
The AI-generated video features Leonardo da Vinci's iconic Mona Lisa painting lip-synced to Anne Hathaway's hit song “Paparazzi.” The video's level of realism and attention to detail sparked widespread surprise and curiosity about the technology's potential uses.
“Microsoft has removed VASA-1. This AI can expressively make a single image sing or speak from an audio reference. Similar to Alibaba's EMO. 10 Wilds Examples: 1. Mona Lisa rapping the paparazzi,” reads the caption of the thread shared by Min Choi.
The video went viral, with some people finding the funny clip amusing. “I fell on the floor laughing when I saw the Mona Lisa clip,” one user wrote. Another person commented: I wish da Vinci could have witnessed this. ”
Some have also raised concerns about unethical use, particularly for the purpose of creating deepfakes.
