Official

luma / ray

Fast, high quality text-to-video and image-to-video (Also known as Dream Machine) (Updated 4 weeks, 2 days ago)

  • Public
  • 41.3K runs
  • Commercial use
  • Paper
  • License
Iterate in playground

Input

*string
Shift + Return to add a new line

Text prompt for video generation

string

Aspect ratio of the video. Ignored if a start frame, end frame or video ID is given.

Default: "16:9"

boolean

Whether the video should loop, with the last frame matching the first frame for smooth, continuous playback. This input is ignored if end_image_url or end_video_id are set.

Default: false

string
Shift + Return to add a new line

URL of an image to use as the starting frame

string
Shift + Return to add a new line

URL of an image to use as the ending frame

string
Shift + Return to add a new line

Continue or extend a video generation with a new generation. You can combine this with end_image_url, or end_video_id.

string
Shift + Return to add a new line

Prepend a new video generation to the beginning of an existing one (Also called 'reverse extend'). You can combine this with start_image_url, or start_video_id.

Output

Generated in

Pricing

Model pricing for luma/ray. Looking for volume pricing? Get in touch.

$0.45
per output video

or around 22 videos for $10

Official models are always on, maintained, and have predictable pricing. Learn more.

Check out our docs for more information about how pricing works on Replicate.

Readme

Luma’s Ray video

A video AI model for generating realistic and fantastical videos from text prompts and images.

Dream Machine is a video generation model built on a scalable, multimodal transformer architecture. It generates physically accurate and consistent videos directly from text instructions and images.

Key Features

  • Direct video generation
  • Handles both realistic and fantastical scenes
  • Maintains physical accuracy and consistency
  • Supports text and image inputs
  • Built for efficiency and scalability

Architecture Goals

Dream Machine is designed to be:

  • Fast and responsive
  • Highly expressive
  • Capable of handling complex scenes

Terms of use

https://lumalabs.ai/dream-machine/api/terms

Privacy

Data from this model is sent from Replicate to Luma.

https://lumalabs.ai/legal/privacy