Sora
OpenAI's text-to-video generative model, capable of creating short video clips from text descriptions.
Think of it like
The next frontier: if DALL-E paints pictures, Sora directs films.
Example
Prompt: "A cozy home library with warm lighting and vintage books" → generates a 60-second video.
How it actually works
Sora generates videos by predicting pixels in spacetime as a diffusion process. Research-grade as of late 2023; not yet widely available. Capabilities shown in research papers are impressive.
For product teams
Could disrupt video production and creative industries; monetization model TBD.
For engineers
Much harder than image generation; inference time and compute still high.
Read anything AI without the jargon
Look up any term in plain English, or save terms as you read with the free Chrome extension.
Open DecoderAdd to Chrome