"(Smith's team hasn't publicly commented on or responded to a request from NPR about how the video was made.) "You're managing so many intricate details," said San Francisco-based visual artist and researcher kyt janae, an expert on AI image creation. "You have each individual human being in the crowd. They're all moving independently and have unique features — their hair, their face, their hat, their phone, their shirt.""
"But the latest AI video generation models such as Google's Veo 3 and OpenAI's Sora 2 are getting pretty good. "We're moving into a world where in a generous time estimate of a year, the lines of reality are going to get really blurry," janae said. "And verifying what is real and what isn't real is going to almost have to become like a practice.""
A Will Smith concert video circulated showing visual glitches in audience members, including odd fingers and faces, raising suspicions of AI manipulation. Crowd scenes present unique technical challenges for image and video generation because each person moves independently and has distinct features. New AI video models such as Google's Veo 3 and OpenAI's Sora 2 are becoming considerably more capable. Experts predict that within roughly a year the boundary between real and synthetic footage will blur, increasing the need for routine verification. Crowd size remains an influential visual metric, and many social media images were AI-generated in 2023.
Read at www.npr.org
Unable to calculate read time
Collection
[
|
...
]