OpenAI announces New No. 1 text to video-generative AI model Sora

Introduction

OpenAI announces New No. 1 text to video-generative AI model Sora. OpenAI has introduced its latest diffusion model, Sora, designed to leverage text for video production. This new AI model, developed by the creators of ChatGPT, can produce videos in different resolutions and aspect ratios. It enables the editing of existing videos swiftly, allowing for prompt adjustments in scenery, lighting, and shooting style through text prompts. Moreover, Sora can generate videos based on a single still image and extend existing videos by seamlessly filling in missing frames.

Sample Video of text to video-generative AI model Sora

OpenAI shares that Sora is currently able to generate up to a minute of Full HD video content and the examples we’ve seen look promising. You can check out Sora’s landing page for more generated video samples. Its a generative AI model.

How text to video-generative AI model works

It works by using a transformer architecture similar to ChatGPT where videos and images are presented as smaller units of data called patches. Videos generated by Sora start as static noise with the model gradually removing noise to form the final product. Its a generative AI model.

What Open AI says about text to video-generative AI model Sora?

Sora can generate complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background. The model understands not only what the user has asked for in the prompt, but also how those things exist in the physical world.

OpenAI shared it is leveraging its existing safety protocols used in DALL·E 3. Sora is currently being tested by “red teamers” – experts who will carry out tests and asses the model for potential risks ahead of its official launch.