Sora: OpenAI unveils video AI model Sora that will let you create videos from text prompts
Nickie Louise
Posted On February 15, 2024
OpenAI on Thursday unveiled its latest creation, Sora, boasting its capability to craft convincing and imaginative 60-second videos based on brief text prompts.
In a blog post, the creator of the popular ChatGPT said the Sora is capable of translating textual directives into dynamic visual narratives, complete with diverse characters, specific movements, and intricate background settings.
“The model not only grasps the essence of the user’s prompt but also comprehends how these elements manifest in real-world scenarios,” the blog post added. OpenAI further expressed its commitment to refining these AI models, aiming to empower individuals in tackling challenges that demand tangible, real-world solutions.
“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. 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,” OpenAI said.
The company also took to social media to announce the launch of the new AI text-to-video generation model. In a post on X (formerly Twitter), OpenAI said:
“Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.”
Introducing Sora, our text-to-video model.
Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. https://t.co/7j2JN27M3W
Prompt: “Beautiful, snowy… pic.twitter.com/ruTEWn87vf
— OpenAI (@OpenAI) February 15, 2024
Sora marks the latest stride in OpenAI’s ongoing efforts to advance the field of generative AI. While “multi-modal models” aren’t entirely novel, and text-to-video capabilities already exist, what distinguishes Sora, according to Reece Hayden, a senior analyst at ABI Research, is the claimed length and accuracy OpenAI asserts it possesses.
Despite not being ready for widespread use yet, as Altman mentioned in his post, due to the need for thorough security testing and defense against potential flaws and misuse, the founder did mention that it’s currently accessible to a select group of creators, with plans for broader availability in the future.
Below, OpenAI co-founder and CEO Sam Altman has shared a video showcasing Sora’s capabilities.
https://t.co/SOUoXiSMBY pic.twitter.com/JB4zOjmbTp
— Sam Altman (@sama) February 15, 2024
