Creators are using OpenAI’s Sora to make unreal AI videos

26 Mar 2024

Image: OpenAI

Filmmakers and artists showcase surreal videos created using Sora as OpenAI courts Hollywood studios for partnerships.

OpenAI has shared some very surreal videos created by visual artists and directors using Sora, its AI text-to-video model unveiled last month.

“Since we introduced Sora to the world last month, we’ve been working with visual artists, designers, creative directors and filmmakers to learn how Sora might aid in their creative process,” the company wrote in a blog.

“While we have many improvements to make to Sora, we’re already getting a glimpse of how the model can help creatives bring ideas to reality.”

One of the videos, a short film titled Air Head, was made by Toronto-based multimedia production company and indie pop band Shy Kids, which consists of Walter Woodman, Patrick Cederberg and Matthew Hornick.

The AI video created with the help of Sora features a man with a balloon for a head – something that would have been impossible to film without extensive use of CGI – as the title character, who goes about his day walking, cycling and driving through a city while he narrates his perspective on life.

Shy Kids said that the OpenAI model now gives filmmakers such as themselves the ability to “expand on stories we once thought impossible”.

“As great as Sora is at generating things that appear real, what excites us is its ability to make things that are totally surreal. A new era of abstract expressionism,” said Woodman, who directed Air Head. “People from all over the world with stories ready to burst out of their chests finally have the opportunity to show the world what’s inside.”

‘Fewer technical constraints’

Writer and director Paul Trillo also had an experimental video featured on the OpenAI list of first impressions. It features a dream-like sequence of different environments that the camera rushes through, briefly stopping at scenes in which human-like figures dance and shape-shift.

“Working with Sora is the first time I’ve felt unchained as a filmmaker,” said Trillo, who has been awarded with 19 Vimeo Staff Picks, an honour given to the best short films hosted on Vimeo.

“Not restricted by time, money, other people’s permission, I can ideate and experiment in bold and exciting ways. Sora is at its most powerful when you’re not replicating the old but bringing to life new and impossible ideas we would have otherwise never had the opportunity to see.”

London-based Josephine Miller, co-founder and creative director of Oraar Studio, said that Sora makes it possible to bring ideas she’s had for years to life. Her experimental video features two mermaids and a merman floating underwater, with scales that look like glass paintings.

“The ability to rapidly conceptualise at such a high level of quality is not only challenging my creative process but also helping me evolve in storytelling,” said Miller, who is an expert in 3D visuals, digital fashion and AR. “It’s enabling me to translate my imagination with fewer technical constraints.”

Eyes on Hollywood

When OpenAI first shared examples of videos created by Sora last month, it claimed the AI model is able to generate complex scenes with multiple characters, specific types of motion and accurate details of the subject and background, giving the public “a sense of what AI capabilities are on the horizon”.

But the company also noted some of Sora’s weaknesses: inaccurate physics, mixing up left and right in prompts and suddenly creating new characters, usually in scenes that involve multiple entities.

OpenAI is now wooing studios and filmmakers in Hollywood to partner with the AI start-up in the hopes that Sora can be used in future productions, according to Bloomberg, with CEO Sam Altman having visited parties in Los Angeles during the weekend of the Oscars.

Last month, OpenAI was one of several big names in AI to sign a letter written by venture capitalist Ron Conway calling on everyone to build the technology in a way that improves people’s lives.

“The purpose of AI is for humans to thrive much more than we could before,” the letter reads.

“While AI is unique in directly augmenting human thought, we expect its impact to be more akin to the printing press, the combustion engine, electricity and the internet. The balance of its good and bad impacts on humans will be shaped through the actions and thoughtfulness we as humans exercise.”

Find out how emerging tech trends are transforming tomorrow with our new podcast, Future Human: The Series. Listen now on Spotify, on Apple or wherever you get your podcasts.

Vish Gain is a journalist with Silicon Republic

editorial@siliconrepublic.com