Unlike most dipfast, it realisticly animals body movements, not only the face, but also body movements.
Omnihuman-1 is trained for 19,000 hours of video and can change the body’s proportions, frame formats, and even edit the already pulled cylinders. Published examples – “Performance” Taylor Swift and Ted Talk.
However, technology also has disadvantages: bad source photographs worsen the result and complex poses still cause errors.
Experts warn that such diplies can be used in politics and fraud.
In 2023, AI Aterists earned more than $ 12 billion and this amount continues to grow. Some US states have already adopted laws against Dipllcines, but it is more difficult to define them every year.
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.
