VASA-1 is a model that creates realistic video from a single image and audio recording. The system blurs the line between reality and fake.
The technology not only synchronizes sound with images, but also recreates facial expressions, emotions and head movements, creating an effect of astonishing authenticity.
At the same time, the new artificial intelligence works with high resolution (512 x 512 pixels) and an impressive speed of 45 frames per second. What’s even cooler is that the model renders a realistic talking face in real time at 40 frames per second.
All this opens up attractive possibilities: historical figures for educational resources or virtual friends for psychological support.
But the potential for abuse is also huge. VASA-1 can create convincing deepfakes to spread misinformation and destroy trust.
Fortunately, Microsoft has no plans to release this powerful technology without strong protection mechanisms.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
