ChatGPT creator OpenAI display what is text-to-video AI generator Sora can do in new videos published on to YouTube on Monday and Tuesday.
Sora is OpenAI's director of AI. It takes any written request, like “two golden retrievers podcasting on top of a mountain” and create a video that gives life to words. When OpenAI ESTIMATED Sora in February, its potential for deep video alarm bells ring for some, especially in one election year.
Although OpenAI has not yet released Sora to the general public, and has only opened access to AI generator for a select group, she released multiple videos showing what Sora is capable of, from dreamscapes to skateboarding bears. Amazing reality videos illustrate Sora's potential for making movies and commercials.
Connected: OpenAI is delaying the release of its new AI voice generator – Here's why
A video released on Tuesday was a one-minute, 32-second short film prompted by the artist Manuel Sainsily and entrepreneur Will Selviz. The two generated all the visuals with Sora, but edited and added the sound by hand. They wanted to ask, “What if our lives are the result of complicated choices made long before our current existence?”
The resulting video is cohesive and compelling, moving effortlessly from the physical world to a more ethereal plane.
Another video of Sora, released on Monday, is in black and white. It places animals in various historical contexts and situations and shows them interacting with humans. For example, a man rides a hippopotamus like a horse and a beaver plays a banjo.
Artist Benjamin Desai created the one-minute, one-second video and stated that he was “excited to share this imaginative look into an alternate past powered by Sora.”
The latest video, released on Monday, is the longest, at two minutes and nine seconds. It was created by the artist Tammy Lovinwho said it felt like “a dream come true”.
“Ever since I was a kid, I had a kind of montage and surreal take on certain things that I was seeing in reality and I would imagine them differently,” Lovin said. “But since I didn't become a producer or a director, they never came to life until now.”
Lovin's video takes viewers from an ocean wave to a walking scene, then cloud surfing, to jellyfish.
Companies that have access to Sora have already started using it in projects with the public. Toys “R” Us was made First to create a branded film with Sora at the end of June, offering a brief appearance to the public on how AI can work in advertising or promotional campaigns.
OpenAI has not revealed the exact videos that went into Sora's training, but there have been reports that millions of hours of video on YouTube may have played a role.