Date of update: 24.04.2024 12:58
The date of publishing:
24.04.2024 12:56
Microsoft has released the VASA 1 artificial intelligence model, capable of making high-quality video clips using simple elements, CNN reports.
VASA 1 is capable of creating a video clip of a person speaking using only a photo of that person and a pre-recorded audio file. Hope example, using Microsoft’s AI engine generated a video clip in which Mona Lisa appears singing a rap song. Moreover, the video clip has the speech perfectly synchronized with the image and facial expressions, the result being extremely convincing.
Embed
How the wood thieves managed to trick SUMAL
2 years in prison for those who create and distribute deep fake
How AI hackers use to cheat people
What Elvis would have looked like at 88 years old
What NATO leaders look like in the version produced by AI
Computer scientist: AI is the greatest force that ever existed
A new internet challenge: AI-rigged images
How does religion reconcile with Artificial Intelligence?
The EU does not want AI surveillance
At the same time, the technology can also be used with images of faces that are not photographs. Hope example, can make a video clip using an image of a cartoon character.
According to CNN, it’s easy to see how this technology can be used for nefarious purposes and how it can help spread false information online or create confusion among internet users.
Microsoft has announced that it does not intend to make the VASA 1 technology public, due to the high risk of someone using it to imitate other people, but adds that in the future it may prove useful in education or to provide people with a virtual friend.
Publisher: VM
Download the Digi24 app and find out the most important news of the day
Tags: Mona Lisa raps artificial intelligence engine created Microsoft
