AI-Powered Text & Image to Video Generator

luma

ray

Warm

Fast, high quality text-to-video and image-to-video (Also known as Dream Machine)

Official

49.8K runs

$0.45 per output video

Commercial use

Run with an API

Pricing

License

Paper

Playground API Examples README

Input

prompt

*string

Shift + Return to add a new line

This video shows the majestic beauty of a waterfall cascading down a cliff into a serene lake. The waterfall, with its powerful flow, is the central focus of the video. The surrounding landscape is lush and green, with trees and foliage adding to the natural beauty of the sceneThis video shows the majestic beauty of a waterfall cascading down a cliff into a serene lake. The waterfall, with its powerful flow, is the central focus of the video. The surrounding landscape is lush and green, with trees and foliage adding to the natural beauty of the scene

Text prompt for video generation

aspect_ratio

string

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

Default: "16:9"

loop

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

start_image

file

An optional first frame of the video to use as the starting frame.

end_image

file

An optional last frame of the video to use as the ending frame.

start_video_id

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.

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.

start_image_url

string

Shift + Return to add a new line

URL of an image to use as the starting frame

end_image_url

string

Shift + Return to add a new line

URL of an image to use as the ending frame

Run this model in Node.js with one line of code:

npx create-replicate --model=luma/ray

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run luma/ray using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  loop: false,
  prompt: "This video shows the majestic beauty of a waterfall cascading down a cliff into a serene lake. The waterfall, with its powerful flow, is the central focus of the video. The surrounding landscape is lush and green, with trees and foliage adding to the natural beauty of the scene",
  aspect_ratio: "16:9"
};

const output = await replicate.run("luma/ray", { input });

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run luma/ray using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "luma/ray",
    input={
        "loop": False,
        "prompt": "This video shows the majestic beauty of a waterfall cascading down a cliff into a serene lake. The waterfall, with its powerful flow, is the central focus of the video. The surrounding landscape is lush and green, with trees and foliage adding to the natural beauty of the scene",
        "aspect_ratio": "16:9"
    }
)

# To access the file URL:
print(output.url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.read())

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run luma/ray using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "loop": false,
      "prompt": "This video shows the majestic beauty of a waterfall cascading down a cliff into a serene lake. The waterfall, with its powerful flow, is the central focus of the video. The surrounding landscape is lush and green, with trees and foliage adding to the natural beauty of the scene",
      "aspect_ratio": "16:9"
    }
  }' \
  https://api.replicate.com/v1/models/luma/ray/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Generated in

38.3 seconds

Tweak it Upscale Iterate in playgroundReport View full prediction

Examples

View more examples

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