Sora creates videos for you from texts

Artificial intelligence from OpenAI no longer just spits out texts. In the future, you will also be able to have videos created from text input using the Sora AI system.

The AI ​​system ChatGPT from OpenAI has helped artificial intelligence to boom. Now the company is introducing a new AI system.

But this is no longer just about outputting texts. In the future, with Sora you will also be able to have videos created from your text specifications.

This is Sora from OpenAI

In a tweet at X, OpenAI boss Sam Altman introduced the new AI model Sora and called it a “remarkable moment.” The company wants to start the red teaming phase and give “a limited number of creatives” access to Sora.

here is sora, our video generation model:https://t.co/CDr4DdCrh1

today we are starting red-teaming and offering access to a limited number of creators.@_tim_brooks @billpeeb @model_mechanic are really incredible; amazing work by them and the team.

remarkable moment.

— Sam Altman (@sama) February 15, 2024

The AI ​​system's website states that red teamers should “inspect critical areas for damage or risks.” Artists and filmmakers, on the other hand, have access to the technology to collect feedback for further development.

What can the system do so far?

The AI ​​system Sora creates videos up to a minute long, the website says. The text-to-video model is able to “maintain visual quality and compliance with user instructions.”

Sora is capable of creating complex scenes with multiple characters, specific types of movement, and precise details of the subject and background.

On the website, OpenAI already shows numerous examples created by the application. The respective descriptions from which the videos were created are also listed.

To do this, Sora uses a “deep understanding of language,” which makes it possible to “accurately interpret the information entered and create convincing characters.”

However, the AI ​​system still has weaknesses so far. Cause and effect are particularly problematic. OpenAI uses the example of a person biting into a cookie – but it is possible that it will not show any bite marks afterwards.

Also interesting: