OpenAI Announces Sora, a Futuristic Text-to-Video AI Model

Today, OpenAI announced Sora, a new generative AI model that can create realistic one-minute videos using nothing but text-based instructions.

“We’re teaching AI to understand and simulate the physical world in motion, with the goal of training models that help people solve problems that require real-world interaction,” OpenAI’s Sora website explains. “Introducing Sora, our text-to-video model. Sora can generate videos up to a minute long while maintaining visual quality and adherence to the user’s prompt.”

Well, you had to think this was coming. But you surely also didn’t think it would happen this quickly.

OpenAI made Sora available today to its “red teamers,” a group of industry experts who help the company with risk assessment and mitigation strategies related to biases, safety filters, and other potential issues common with leading-edge AI models. It’s also invited a select group of filmmakers, visual artists, and designers to provide feedback about Sora and how it might be used in the creative arts. And it says it will engage with policymakers, educators, and artists around the world to understand their concerns and identify positive use cases for this new technology.

And I can see why this is necessary. The many sample videos on the Sora website are, in a word, breathtaking. It’s not difficult to imagine that this capability will change video creation forever.

“Sora is able to generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background,” OpenAI notes. “The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world. The model has a deep understanding of language, enabling it to accurately interpret prompts and generate compelling characters that express vibrant emotions. Sora can also create multiple shots within a single generated video that accurately persist characters and visual style.”

It’s not perfect, of course, and OpenAI admits to some “weaknesses” in the Sora model. It can struggle with accurately simulating the physics of a complex scene, for example, and doesn’t always understand cause and effect. But seriously, check this out. Sora looks incredible.