WATCH: New Microsoft AI Tool VASA-1 Makes Da Vinci's Monalisa Rap
Since being shared, the AI-generated video has gone viral and so far, it has accumulated over seven million views.
The majority of us must have at least once in our lives heard about the painting of Monalisa made by the legendary Leonardo Da Vinci. It is a masterpiece which is adorned by many. Recently the painting has made headlines again but not for its beauty or finesse. Some genius recently had come up with an idea to make Monalisa rap. The person used Microsoft's new AI app, VASA-1. This app has the capability to transform still photographs of people’s faces into lively animation.
Here’s an X post that captures Mona Lisa’s rapping.
Microsoft just dropped VASA-1.
— Min Choi (@minchoi) April 18, 2024
This AI can make single image sing and talk from audio reference expressively. Similar to EMO from Alibaba
10 wild examples:
1. Mona Lisa rapping Paparazzi pic.twitter.com/LSGF3mMVnD
Since being shared, the AI-generated video has gone viral. Till now, it has accumulated over seven million views - and the numbers are still increasing. The share has further collected tons of comments from people. It has amassed over 14,000 likes and has been reposted more than 4,300 times.
Microsoft VASA-1
The new AI model called VASA-1 is able to master lip sync with photos and the motion in these photos will hardly make you believe that they aren't videos. Some of the AI-generated clips depict how scary this technology could be and what it could possibly do if it fell into the wrong hands.
Microsoft feels that the quality of the clips is still not authentic enough and it is making sure that the “videos generated by this method still contain identifiable artefacts, and the numerical analysis shows that there’s still a gap to achieve the authenticity of real videos.”
The company is equally aware of its possible misuse but it appears that it is intent on overlooking them as the positives weigh far higher in its cause.