Sora (technical preview)
OpenAI previewed Sora, a diffusion transformer that generates up to one-minute HD video from text and was shown only to red teamers and select creatives.
Diffusion transformer denoising latent patches; the report "Video generation models as world simulators" (Tim Brooks, Bill Peebles et al.) pitched video models as general world simulators. Public access came ten months later.
- Date
- Thursday, 15 February 2024
- Lab
- OpenAI
- Kind
- model
- Access
- research preview
Figures
| Measure | Value | Measured by |
|---|---|---|
| Maximum video length stated at announcement | up to 1 minute high-definition clips, demos only | company |
Wikipedia cites OpenAI's announcement and technical report; those pages were not opened directly.
Sources
This record was checked against its sources on 6 October 2026. How we check