Atlas record: https://www.aitimeline.dev/en/events/evt-0293/
Announcement · February 15, 2024
Sora
OpenAI showed a model that generates minute-long video from a text description, with objects that persist and camera motion that stays consistent.
Why it matters
Video generation crossed the line beyond which the result stopped announcing itself as machine-made.
The model works as a diffusion transformer: video is cut into space-time patches and the transformer gradually removes noise from them. A length of up to a minute was an order of magnitude beyond earlier systems. OpenAI did not open the model at once, giving access only to artists and safety specialists, and named the risk of plausible fakes directly. Public release came only at the end of the year.
Event record
- Event date
- February 15, 2024
- Timeline date
- Event date
- Verification
- Sources gathered automatically · September 18, 2026
- Lines
- ID
- evt-0293
Announcement of 15 February 2024.
Related events
Earlier
- Related The transformer for images 2020
The same idea of cutting the input into patches and processing them with a transformer, applied to video.
- Builds on Diffusion models 2015
Video is generated by the same process of gradually removing noise.
Later
- Related Genie 3 2025links to this record
From video that is watched to a world that is moved through.
- Extends Sora 2 2025links to this record
The next generation of the same model, eighteen months later.