“Startling Social Media: Hyper-Realistic Videos Generated from Text Prompts by Microsoft-Backed Startup”
OpenAI, renowned for ChatGPT, has introduced a groundbreaking form of artificial intelligence capable of generating lifelike videos from text prompts, eliciting astonished responses across the internet.
Named Sora, the text-to-video model boasts “a profound grasp of language” and can produce “engaging characters that convey vivid emotions,” OpenAI stated in a Thursday blog post.
“Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background,” the Microsoft-backed startup said.
“The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world.”
OpenAI CEO Sam Altman on X invited users to suggest prompts for Sora before posting results that included realistic videos of two golden retrievers podcasting on top of a mountain, a grandmother making gnocchi, and marine animals taking part in a bicycle race on top of the ocean.
The hyper-realistic quality of videos prompted stunned reactions across social media, with users calling the results “out of this world” and a “game changer”.
“It’s been two hours and my brain still can’t process these generated OpenAI Sora videos,” X user Allen T said.
The demonstration also sparked concerns about potential risks, particularly in a year marked by closely monitored elections worldwide, including the US presidential election in November.
In its blog post, OpenAI outlined several critical safety measures it intends to implement before releasing Sora to the general public.
“We are collaborating with red teamers—experts in fields such as misinformation, hateful content, and bias—who will rigorously test the model,” the company stated.
“We’re also developing tools to identify misleading content, such as a detection classifier capable of recognizing videos generated by Sora.”
OpenAI also acknowledged Sora’s limitations, including challenges with continuity and distinguishing left from right.
“For instance, while a person may be shown taking a bite out of a cookie, the subsequent image of the cookie may lack the bite mark,” the San Francisco-based startup noted.
https://www.pcmag.com/news/openai-unleashes-realistic-text-to-video-sora-ai
