Official

luma / photon-flash

Accelerated variant of Photon prioritizing speed while maintaining quality

Warm

Public
62.5K runs
$0.01 per image
Commercial use
License

Run with an API

Playground API Examples README

Input

prompt

*string

Shift + Return to add a new line

A train car is engulfed in a massive explosion, with flames and smoke billowing into the sky as debris flies in all directions, cinematic photograph, explosive action, high contrast, dynamic lighting.A train car is engulfed in a massive explosion, with flames and smoke billowing into the sky as debris flies in all directions, cinematic photograph, explosive action, high contrast, dynamic lighting.

Text prompt for image generation

aspect_ratio

string

Aspect ratio of the generated image

Default: "16:9"

image_reference_url

string

Shift + Return to add a new line

URL of a reference image to guide generation

image_reference_weight

number

(minimum: 0, maximum: 1)

Weight of the reference image. Larger values will make the reference image have a stronger influence on the generated image.

Default: 0.85

style_reference_url

string

Shift + Return to add a new line

URL of a style reference image

style_reference_weight

number

(minimum: 0, maximum: 1)

Weight of the style reference image

Default: 0.85

character_reference_url

string

Shift + Return to add a new line

URL of a character reference image

seed

integer

Random seed. Set for reproducible generation

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

npx create-replicate --model=luma/photon-flash

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";

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

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

const input = {
  prompt: "A train car is engulfed in a massive explosion, with flames and smoke billowing into the sky as debris flies in all directions, cinematic photograph, explosive action, high contrast, dynamic lighting.",
  aspect_ratio: "16:9",
  image_reference_weight: 0.85,
  style_reference_weight: 0.85
};

const output = await replicate.run("luma/photon-flash", { 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/photon-flash using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "luma/photon-flash",
    input={
        "prompt": "A train car is engulfed in a massive explosion, with flames and smoke billowing into the sky as debris flies in all directions, cinematic photograph, explosive action, high contrast, dynamic lighting.",
        "aspect_ratio": "16:9",
        "image_reference_weight": 0.85,
        "style_reference_weight": 0.85
    }
)
print(output)

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/photon-flash 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": {
      "prompt": "A train car is engulfed in a massive explosion, with flames and smoke billowing into the sky as debris flies in all directions, cinematic photograph, explosive action, high contrast, dynamic lighting.",
      "aspect_ratio": "16:9",
      "image_reference_weight": 0.85,
      "style_reference_weight": 0.85
    }
  }' \
  https://api.replicate.com/v1/models/luma/photon-flash/predictions

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