Text to video: OpenAI announces new Sora model

Image FABRICE COFFRINI/ Getty Images

Microsoft-backed OpenAI is working on software that can generate minute-long videos based on text prompts, the company said on Thursday.

The software, called Sora, is currently available for red teaming, which helps identify flaws in the AI system, as well as for use by visual artists, designers and filmmakers to gain feedback on the model, the company said in a statement.

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

Prompt: “A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. she wears a black leather jacket, a long red dress, and black boots, and carries a black purse. she wears sunglasses and red lipstick. she walks confidently and casually.… pic.twitter.com/cjIdgYFaWq

— OpenAI (@OpenAI) February 15, 2024

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

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 company is also looking to compete with Microsoft, Alphabet’s Google and Amazon in the rapidly transforming generative AI universe.

Prompt: “Several giant wooly mammoths approach treading through a snowy meadow, their long wooly fur lightly blows in the wind as they walk, snow covered trees and dramatic snow capped mountains in the distance, mid afternoon light with wispy clouds and a sun high in the distance… pic.twitter.com/Um5CWI18nS

— OpenAI (@OpenAI) February 15, 2024

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.

Read: OpenAI’s Altman reveals deepest AI fears, hopes to UAE audience