Sora, text-to-video model, OpenAI Inc., San Francisco, California, USA


Introducing Sora — OpenAI’s text-to-video model

Feb 17, 2024

Introducing Sora, our text-to-video model.

Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions.

We’ll be taking several important safety steps ahead of making Sora available in OpenAI’s products. We are working with red teamers — domain experts in areas like misinformation, hateful content, and bias — who are adversarially testing the model.

All the clips in this video were generated directly by Sora without modification.

Chapters:
00:09 Dancing Kangaroo
00:22 Snow Dogs
00:43 River Birds
00:55 Petri Dish Pandas
01:08 Big Sur
01:21 Movie Trailer Astronaut
01:40 Coffee Pirates
01:57 Tokyo Snow
02:09 Cyberpunk Robot
02:30 Candle Monster
02:43 The Offroader
03:04 Paper Origami
03:27 Nosy Cat
03:38 Woolly Mammoths
03:51 Lagos
04:14 Television Gallery
04:37 Cloud Reader
04:59 Miniature Construction
05:11 Gold Rush Aerial
05:38 Fairytale Furball
05:49 Amalfi Coast Aerial
06:12 Tokyo Tourist
06:31 Blossoming Flower
06:42 Art Museum
07:05 Solemn Gentleman
07:28 Eye Close-up
07:47 Chinese New Year
07:58 Surfing Otter
08:17 Dalmatian in the Window
08:31 Tokyo Train
08:42 Zen Garden Gnome
08:53 Flock of Paper Planes
09:16 Lost Lone Wolf
 
Back
Top