mlscade/image_tune | Run with an API on Replicate

mlscade / image_tune

image_tune

Cold

Public
189 runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

image_path

*file

Input image

auto_color_correction

boolean

Apply automatic color correction

Default: false

auto_white_balance

boolean

Apply automatic white balance

Default: false

auto_contrast

boolean

Apply automatic contrast

Default: false

auto_sharpness

boolean

Apply automatic sharpness

Default: false

saturation

number

(minimum: 0, maximum: 2)

Saturation level

Default: 1

temperature

number

(minimum: 0, maximum: 2)

Temperature

Default: 1

brightness

number

(minimum: 0, maximum: 2)

Brightness level

Default: 1

contrast

number

(minimum: 0, maximum: 2)

Contrast level

Default: 1

sharpness

number

(minimum: 0, maximum: 1)

Sharpness level

Default: 0

blur

number

(minimum: 0, maximum: 1)

Blur level

Default: 0

noise

number

(minimum: 0, maximum: 1)

Noise level

Default: 0

vignette

number

(minimum: 0, maximum: 1)

Vignette effect

Default: 0

exposure_offset

number

(minimum: 0, maximum: 1)

Exposure offset

Default: 0

chromatic_aberration

number

(minimum: 0, maximum: 1)

Chromatic aberration

Default: 0

rotate_degrees

number

(minimum: -180, maximum: 180)

Rotate image (degrees)

Default: 0

ascii_effect

integer

(minimum: 0, maximum: 20)

Apply ASCII effect. Recommended value 10

Default: 0

tilt_shift

string

Tilt shift effect position

Default: "None"

black_and_white

boolean

Apply black and white

Default: false

sepia

boolean

Apply sepia effect

Default: false

flip_image

boolean

Flip image horizontally

Default: false

glitch

boolean

Apply glitch effect

Default: false

vhs

boolean

Apply VHS effect

Default: false

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

npx create-replicate --model=mlscade/image_tune

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

const output = await replicate.run(
  "mlscade/image_tune:25ec44751071a0448d93dd9fd9aafa551d99349fc24ee5f26bced9403775f3ac",
  {
    input: {
      vhs: false,
      blur: 0,
      noise: 0,
      sepia: false,
      glitch: false,
      contrast: 1,
      vignette: 0,
      sharpness: 0,
      brightness: 1,
      flip_image: false,
      saturation: 1,
      tilt_shift: "None",
      temperature: 1,
      ascii_effect: 0,
      auto_contrast: false,
      auto_sharpness: false,
      rotate_degrees: 0,
      black_and_white: false,
      exposure_offset: 0,
      auto_white_balance: false,
      chromatic_aberration: 0,
      auto_color_correction: false
    }
  }
);

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

output = replicate.run(
    "mlscade/image_tune:25ec44751071a0448d93dd9fd9aafa551d99349fc24ee5f26bced9403775f3ac",
    input={
        "vhs": False,
        "blur": 0,
        "noise": 0,
        "sepia": False,
        "glitch": False,
        "contrast": 1,
        "vignette": 0,
        "sharpness": 0,
        "brightness": 1,
        "flip_image": False,
        "saturation": 1,
        "tilt_shift": "None",
        "temperature": 1,
        "ascii_effect": 0,
        "auto_contrast": False,
        "auto_sharpness": False,
        "rotate_degrees": 0,
        "black_and_white": False,
        "exposure_offset": 0,
        "auto_white_balance": False,
        "chromatic_aberration": 0,
        "auto_color_correction": False
    }
)

# 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 mlscade/image_tune 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 $'{
    "version": "mlscade/image_tune:25ec44751071a0448d93dd9fd9aafa551d99349fc24ee5f26bced9403775f3ac",
    "input": {
      "vhs": false,
      "blur": 0,
      "noise": 0,
      "sepia": false,
      "glitch": false,
      "contrast": 1,
      "vignette": 0,
      "sharpness": 0,
      "brightness": 1,
      "flip_image": false,
      "saturation": 1,
      "tilt_shift": "None",
      "temperature": 1,
      "ascii_effect": 0,
      "auto_contrast": false,
      "auto_sharpness": false,
      "rotate_degrees": 0,
      "black_and_white": false,
      "exposure_offset": 0,
      "auto_white_balance": false,
      "chromatic_aberration": 0,
      "auto_color_correction": false
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

No output yet! Press "Submit" to start a prediction.

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.