World-simulator video diffusion transformer generating complex spatiotemporal scenes.
Sora is a diffusion transformer model developed by OpenAI that generates videos from text instructions up to a minute long while maintaining high visual quality and adherence to physical world dynamics.
Official model variants, context limits, and target filmmaking workflows
Commercial video generation model with rapid turnaround times for creative directors.
Relationships mapped to canonical tools, techniques, prompts, workflows, films, and research
Every factual capability, benchmark, and parameter is backed by a verifiable primary source
OpenAI