OpenAI said its new platform Sora can generate videos up to a minute long
OpenAI said its new platform Sora can generate videos up to a minute long AFP

OpenAI, the creator of ChatGPT and image generator DALL-E, said it was testing a text-to-video model called Sora that would allow users to create realistic videos with a simple prompt.

The Microsoft-backed company said the new platform was currently being tested but released a few videos of what it said was already possible, with the accompanying input made to generate the video.

"Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user's prompt," OpenAI said in a blog post.

The model could also take an existing still image and generate a video from it, the company said.

OpenAI CEO Sam Altman on X said the company was "offering access to a limited number of creators" in a testing phase.

He also invited users to suggest prompts on X, the convincing results of which he posted on the platform a few moments later.

These included a short video of two golden retrievers podcasting on a mountain.

Another showed a "half duck half dragon (that) flies through a beautiful sunset with a hamster dressed in adventure gear on its back."

The San Francisco-based startup warned that the "current model has weaknesses" such as confusing left and right or failing to maintain visual continuity throughout the length of a video.

In its announcement, the company said that safety would be key and that Sora would face adversarial testing -- known as red-teaming -- in which dedicated users try to make the platform malfunction, produce inappropriate content or go off the rails.

"We'll be engaging policymakers, educators and artists around the world to understand their concerns and to identify positive use cases for this new technology," OpenAI said.

Meta, Google and Runway AI are also working on text-to-video AI technology and have released similar samples of their work.