Sora, OpenAI's New Text-To-Video AI Model (Photo by Levart_Photographer on Unsplash)
OpenAI, the creator of ChatGPT, introduced its own text-to-video AI model on Thursday. Sora, the all-new AI model, has the ability to create realistic and imaginative scenes from text instructions. Notably, Sora is not publicly available yet.
According to OpenAI, the new text-to-video generator can create videos up to a minute long based on whatever prompt a user types. The ChatGPT maker claims that Sora will be able to generate videos while maintaining visual quality and adherence to the user’s prompt. “Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions,” wrote OpenAI on its X handle on February 15. The AI startup has also shared sample videos generated using Sora. OpenAI CEO Sam Altman has also posted videos generated using the latest AI model on his X handle.
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 will initially be available to red teamers to assess critical areas for harm or risks. Microsoft-backed OpenAI also mentioned in its blog post that they are granting access to a number of visual artists, designers, and filmmakers to gain feedback on how to advance the model.
here is a better one: https://t.co/WJQCMEH9QG pic.twitter.com/oymtmHVmZN
— Sam Altman (@sama) February 15, 2024
According to OpenAI, its latest AI 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,” added OpenAI in its post. The AI model also has the capacity to create multiple shots within a single generated video that accurately persist characters and visual style.
The AI startup says that they will be taking “several important safety steps” ahead of making Sora available in their products. OpenAI is also working to develop tools that can detect when a video is generated by Sora. The AI giant is also planning to include C2PA metadata in the future if they deploy the model in an OpenAI product. OpenAI further added that they will be engaging policymakers, educators, and artists around the world to understand their concerns and identify positive use cases for the new AI model.
