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
Features
🎞️ High–quality videos from text & images
⚡️ Iterate at the speed of thought
🚀 Create action packed shots
😏 Consistent characters
📸 Breathtaking camera moves
⏣ About
Dream Machine
Dream Machine is the first in Luma Labs family of frontier generative models that will help you dream with images, videos, text, and other expressive inputs.
As opposed to image-animation models that people have had to contend with so far, Dream Machine is a true video generation model. It’s fast for its class and capabilities, and we will continue to make it more efficient so limits won’t stand in the way of dreamers.
To build Dream Machine Luma Labs worked with Amazon Web Services (AWS) and their best-in-class H100 training infrastructure SageMaker HyperPod. Early feedback on the model has been enthusiastic and gives the feeling of a thousand creative minds getting unshackled.
Iterate at the speed of thought
Dream Machine is an incredibly fast video generator. 120 frames in 120s. Iterate faster, explore more ideas and dream bigger.
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.
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.
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.
