OpenAI launches video generation model Sora

OpenAI on Thursday announced Sora, an artificial intelligence (AI) model that can create realistic videos from text instructions of up to one minute in length. However, the ChatGPT maker said the tool is still in research stage and is not available with the company's products yet.

"Today we are starting red-teaming and offering access to a limited number of creators," chief executive Sam Altman took to X to unveil OpenAI's latest offering.



Altman then opened it out to X to suggest ideas for videos Sora can create to demonstrate the tool's capabilities. "we'd like to show you what sora can do, please reply with captions for videos you'd like to see and we'll start making some!" his post read.


To a prompt about a wizard with blue robes, Altman posted a video showcasing a white-bearded man in blue robes covered in stars, created on Sora.

"Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background," the company said, adding that it can create multiple shots within a single video.

Apart from generating videos from text prompts, Sora can animate a still image, the company said in a blogpost.

The video generation software follows OpenAI's ChatGPT chatbot, which was released in late 2022 and created a buzz around GenAI with its ability to compose emails and write codes and poems.

Social media giant Meta Platforms beefed up its image generation model Emu last year to add two AI-based features that can edit and generate videos from text prompts. The Facebook-parent is also looking to compete with Microsoft, Alphabet's Google and Amazon in the rapidly transforming generative AI universe.

Sora is a work-in-progress, with the company adding that the model may confuse the spatial details of a prompt, and have difficulty in following a specific camera trajectory.

OpenAI said it was also developing tools which can discern if a video was generated by Sora.

(With inputs from agencies)