New freedoms
of imagination

Dream Machine is an AI model that makes high quality, realistic videos fast from text and images.

It is a highly scalable and efficient transformer model trained directly on videos making it capable of generating physically accurate, consistent and eventful shots. Dream Machine is our first step towards building a universal imagination engine and it is available to everyone now!

Try now

High–quality videos from text & images

Speed

Iterate at the speed of thought

Hyper-fast generation time for full-quality generations. 120 frames in 20s! Iterate at the speed of thought, explore more ideas and dream bigger!

Motion

Create action packed shots

Dream Machine generates 5s shots with a realistic smooth motion, cinematography, and drama. Make lifeless into lively. Turn snapshots into stories.

Consistency

Dream worlds with consistent characters

Dream Machine understands how people, animals and objects interact with the physical world. This allows you to create videos with great character consistency and accurate physics.

Camera

Capture attention with breathtaking camera moves

Dream Machine helps you experiment with an endless array of fluid, cinematic and naturalistic camera motions matching the emotion and contents of the scene.

Current
Limitations

Morphing
Movement
Text
Janus

To be
Continued…

Team

Join Us

Model Development

Terrance DeVries
Alex Yu
Samarth Sinha
Thomas Neff
Quei-An Chen
Matt Tancik
Jiaming Song
Ayaan Haque
Angela Dong
Nathan McClean
Paul Yoo
Dominic Rampas
Pablo Pernías
Dan Kondratyuk

Systems Design

Jiacheng Yang
Andrew Prifer
Caroline Ingeborn
Nathan Manousos
Skylar Simpson
Amit Jain
Karan Ganesan
Theo Panagiotopoulos
Alaa Qutaish
David Romero
George Corney
Ahmed Mansy
Barkley Dai
Arthur Islamov
Robera Geleta
Sapna Benali
Vasuman Ravichandran
Tuhin Kumar
Ben Coombs
Keegan McCallum