Sora

Sora is OpenAI's video generation model built on learnings from DALL-E and GPT models, designed to give people expanded tools for storytelling and creative expression. Users can create videos up to 1080p resolution (20 seconds max) in various formats, generate new content from text, or enhance, remix, and blend their own assets. Sora Turbo is significantly faster than the model previewed in February and is released as a standalone product at Sora.com for ChatGPT Plus and Pro users. Sora 2 is the new powerful media generation model generating videos with synced audio and capable of doing things that are exceptionally difficult for prior video generation models, with better adherence to physics compared to prior systems. Sora is a diffusion model that generates video by starting with base video that looks like static noise and gradually transforms it by removing noise over many steps.