On Thursday, OpenAI announced Sora, a brand new model that generates high-quality videos of up to one minute via text messages.
The new tool, called Sora, will initially only be available to a small group of artists and filmmakers, as well as “red teams,” or researchers trying to find ways the AI tool can be used for malicious purposes, OpenAI said in the document. Thursday’s announcement.
Sora builds on the technology behind the OpenAI image generation tool DALL-E. It interprets the user’s prompt, expands it into a more detailed set of instructions, and then uses an AI model trained on the video and images to create a new video.
The quality of AI-generated images, audio, and video has increased rapidly over the past year, with companies like OpenAI, Google, Meta, and Stable Diffusion racing to build more capable tools and find ways to sell them.
This is not the first time such videos or audio have been created, and other companies have created their own AI generators for converting text to video. Google is testing one called Lumiere, Meta has a model called Emu, and artificial intelligence startup Runway is already building products to help filmmakers create videos. But artificial intelligence experts and analysts said that the length and quality of Sora’s videos were greater than what they had seen before.
One of the videos created by Sora, which OpenAI shared on its website, shows a couple walking through a snowy Tokyo while cherry blossoms and snowflakes fly around them.
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
OpenAI said it is working with experts in areas such as disinformation, hate content and bias to test the tool before making it available to the public. The company is also building tools that can identify videos produced by Sora and insert metadata into the produced videos to facilitate discovery.
