A Microsoft-backed startup surprises social networks with hyper-realistic videos created through text messages.
OpenAI, the creator of ChatGPT, has introduced a new form of artificial intelligence that creates realistic videos based on text prompts, sparking shocked reactions online.
The text-to-video model, called Sora, has “a deep understanding of language” and can generate “compelling characters that express vibrant emotions,” OpenAI said in a blog post on Thursday.
“Sora is capable of generating complex scenes with multiple characters, specific types of motion, and precise subject and background details,” the Microsoft-backed startup said.
“The model understands not only what the user has requested in the message, but also how those things exist in the physical world.”
OpenAI CEO Sam Altman on a bicycle race on top of the ocean. .
—Sam Altman (@sama) February 15, 2024
The hyper-realistic quality of the videos sparked shocked reactions on social media, with users calling the results “out of this world” and “game-changing.”
“It's been two hours and my brain still can't process these videos generated by OpenAI Sora,” said X user Allen T.
The demonstration also raised concerns about potential risks, especially in a year of closely watched elections around the world, including the US presidential election in November.
OpenAI said on its blog that it would take several important safety measures before releasing Sora to the general public.
“We are working with red teams (experts in areas such as disinformation, hate content and bias) who will adversely test the model,” the company said.
“We're also building tools to help detect misleading content, such as a detection classifier that can tell when Sora generated a video.”
OpenAI also acknowledged that Sora has weaknesses, including difficulty with continuity and distinguishing left from right.
“For example, a person may take a bite of a cookie, but afterward, the cookie may not have the bite mark,” the San Francisco-based startup said.
OpenAI's rivals Meta and Google have also demonstrated text-to-video AI technology, but their models have not produced results as realistic as Sora's.
SORA is out of this world.
OpenAI's new text-to-video model just launched and it's crazy.
More examples below ⬇️ pic.twitter.com/qbMy5Rz5Mc
— Linus (●ᴗ●) (@LinusEkenstam) February 15, 2024
