OpenAI has introduced an artificial intelligence model Sora that can create realistic videos from text prompts. This is stated in the company’s official announcement.

Sora is capable of generating videos up to a minute long, while maintaining visual quality and compliance with user prompts.

“Today, Sora is becoming available to red teamers to assess critical areas for harms or risks. We are also granting access to a number of visual artists, designers, and filmmakers to gain feedback on how to advance the model to be most helpful for creative professionals,” OpenAI said in a statement.

According to the company, Sora is capable of generating complex scenes with multiple characters, specific types of movement, and precise object and background details. The model understands not only what the user has asked for in the prompt, but also how these things exist in the physical world.

Besides, OpenAI’s Sora has a deep understanding of language, which allows it to accurately interpret cues and create convincing characters.

“Sora is capable of generating entire videos all at once or extending generated videos to make them longer. By giving the model foresight of many frames at a time, we’ve solved a challenging problem of making sure a subject stays the same even when it goes out of view temporarily,” OpenAI added.

However, the model still has weaknesses. It can have difficulty accurately modeling the physics of complex scenes and fail to understand cause and effect relationships. For example, a person can take a bite of a cookie, but afterwards, there may be no bite marks on the cookie. At the same time, Sora can get “confused” in space, i.e., confuse right and left.

OpenAI also reported that the company takes care of security issues while working on Sora. For this purpose, it works with experts, in particular in the field of disinformation. The giant is also developing tools that will help determine when a video was created using Sora.

The company emphasized that Sora serves as the basis for models that can understand and simulate the real world. OpenAI believes that this capability will be an important milestone on the way to creating AGI.