What is Sora, the new OpenAI model that will allow you to create videos from text indications

(CNN) — AI leader OpenAI has unveiled a new AI model called Sora, which it claims can create “realistic” and “imaginative” 60-second videos from quick text prompts.

In a Wednesday post on its blog, the company said Sora is capable of creating videos up to 60 seconds long from text instructions, with the ability to display scenes with multiple characters, specific types of activities, and background details.

“The model not only understands what the user requested in the message, but also how those things exist in the physical world,” the post said.

OpenAI said it intended to train artificial intelligence (AI) models so they could “help people solve problems that require real-world interactions.”

This is the latest move from the company behind viral chatbot ChatGPT to promote generative artificial intelligence. Although “multimodal models” are not new and text-to-video models already exist, according to Reece Hayden, senior analyst at research firm ABI Research Markets, what sets them apart in this case is the length and accuracy that OpenAI achieves. Claims that Sora has it.

Hayden said these types of AI models could have a big impact on digital entertainment markets with the delivery of new personalized content across all channels.

Hayden said, “An obvious use case is television; creating short scenes that support narratives.” “The model is still limited, but it shows the direction of the market.”

At the same time, OpenAI said that Sora is still a work in progress with obvious “weaknesses”, especially when it comes to the spatial details of a message (combining left and right) and cause and effect. He gave the example of making a video in which someone is cutting a cookie but immediately after that there is no bite mark left.

For now, OpenAI’s message focuses on security. The company said it plans to work with a team of experts to test the latest models and take a closer look at a number of areas, including misinformation, hate content and bias. The company said it is also building tools to help detect misinformation.

Sora will first be made available to cybersecurity professionals, referred to as the “Red Team,” who will evaluate the product for damage or risk. A number of visual artists, designers and filmmakers will also be given access to hear their views on how it can be used by creative professionals.

The latest update comes as OpenAI continues to make progress with ChatGPT.

Earlier this week, the company said it was testing a feature where users can control ChatGPT’s memory, allowing the platform to remember chats to make future conversations more personalized. You may be asked to do so or may be asked to forget the things discussed above.