OpenAI Unveils Sora Text-to-Video Model
Posted on February 19, 2024
OpenAI has revealed Sora, its new text-to-video model. The model generates impressive graphic videos of up to 60 seconds in length based on the text it is given.
OpenAI says Sora can "create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions."
The Internet has been in awe of some of the stunning footage produced by Sora as you can see on Techmeme.
OpenAI also says, "Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background. The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world."
The video below shows the 30+ samples OpenAI revealed in an enteraining video shared on YouTube. The Woolly Mammoths are amazing looking and we would love to see more of the drone-like aerial view of the Gold Rush in California. There is a pirate ship battle (sans pirates) going on inside a cup of coffee. There are also some cute effects like the tiny petri dish red pandas and the cute little monster impressed by a candle flame.