Sora

Sora is an advanced AI model that transforms text descriptions into photorealistic video clips. Developed by OpenAI, the same company behind ChatGPT and DALL-E, Sora uses a transform-based diffusion technique to create detailed scenes with complex camera movement and multiple characters. It can generate videos up to 20 seconds long in 1080p resolution and supports various image formats such as landscape, portrait and square. Users can also remix and extend existing videos, create storyboards and apply stylised filters such as 'cardboard' or 'film noir'.

Sora is primarily aimed at creative professionals in film, advertising, education and social media. It is used to create concept videos, pitches, training materials and visual content for campaigns.