Updated Feb 16, 2024 - Technology

OpenAI joins race to make videos from text prompts

headshot
A gif of pirate ships in a coffee cup

Image: Created with OpenAI's Sora, a generative AI tool.

OpenAI on Thursday announced Sora, its first tool that can turn a text prompt into a video of up to one minute in length. However, OpenAI said Sora is still in the research stage and is not yet being added to any of the company's products.

The big picture: Others, including Meta, Google and Runway, have announced or released their own text-to-video engines.

Details: Sora is a diffusion model that is able to "generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background."

  • Sora will be able to understand the nuances of the prompt as well as how various objects behave in the physical world.
  • Sora also generates an entire video at once, rather than creating it frame by frame. That helps avoid what has been a challenge with other approaches — ensuring a subject stays the same even when it goes out of view temporarily.

Between the lines: An OpenAI spokesperson stressed that it doesn't plan to make Sora broadly available any time soon as it continues to work on a range of safety issues, including efforts to reduce misinformation, hateful content, and bias as well as clearly labeling the output as generated by AI.

What they're saying: "Today, Sora is becoming available to red teamers to assess critical areas for harms or risks," OpenAI said on its Sora website.

  • "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."
  • "We're sharing our research progress early to start working with and getting feedback from people outside of OpenAI and to give the public a sense of what AI capabilities are on the horizon."

Reactions to Sora represented a Rorschach test for how people already view the impact of generative AI, with a mix of excitement, awe, fear and revulsion.

  • AI creator and ex-Googler Bilawal Sidhu said: "OpenAI just shattered the 'Visual' Turing Test, 'Is it real or is it fake?' isn't just for photos now. Videos too have fallen, and I couldn't be more excited."
  • Filmmaker Justine Bateman, who has been highly critical of the technology, posted: "Every nanosecond of this #AI garbage is trained on stolen work by real artists. Repulsive."
  • YouTube creator and tech reviewer Marques Brownlee was more measured, but noted: "If this doesn't concern you at least a little bit, nothing will."
  • Meanwhile, Cristóbal Valenzuela, CEO of rival text-to-video service Runway, declared simply: "Game on."

Editor's note: This story has been updated with additional comment.

Go deeper