FACELANDMARKS API Endpoint Documentation | PixLab Developers Handbook

API Endpoint Access URL

https://api.pixlab.io/facelandmarks

Get Your API Key & Try FACELANDMARKS Now ↗

Description

Utilize the FACELANDMARKS API endpoint to detect and extract facial landmarks, along with their corresponding rectangle coordinates. This functionality can be integrated with other API endpoints, including CROP, MOGRIFY, and MERGE, to facilitate advanced face processing. The output will include the rectangle coordinates and extracted facial shapes for each detected face. Several complementary API endpoints are available, such as crop for face extraction, drawrectangles for face annotation, and mogrify for content redaction.

HTTP Methods

GET, POST

HTTP Parameters

Required

Fields	Type	Description
`img`	URL	Input media URL. If you want to upload your image directly from your app, then submit a `multipart/form-data` POST request.
`key`	String	Your PixLab API Key ↗. You can also embed your key in the `WWW-Authenticate:` HTTP header and omit this parameter if you want to.

POST Request Body

If you plan to use POST instead of a simple GET request:

Allowed Content-Types:

multipart/form-data
application/json

Use multipart/form-data if you want to upload your media file directly (refer to the REST API code samples or The PixLab Github Repository↗ for a working example). If you are using JSON, then the media file must be already uploaded somewhere. Call store if you want to upload an image before invoking this endpoint.

HTTP Response

application/json.

This command always return a JSON object after each call. The field of interest here is the faces array which hold the rectangle & landmarks coordinates for each detected face. The following are the JSON fields returned in response body:

Fields	Type	Description
status	Integer	Status code 200 indicates success, any other code indicates failure.
faces	Array	JSON array holding the rectangle & landmarks coordinates (See below for fields).
error	String	Error message if `status` != 200.

The following are the object fields returned for each detected face in the faces array defined above:

Fields	Type	Description
rectangle	Array	JSON array holding the rectangle coordinates for this face (See below).
landmarks	Array	JSON array holding the landmarks coordinates for this face (See below).

The following are the object fields returned in each rectangle array, member of the faces array defined above:

Fields	Type	Description
face_id	Integer	Detected face ID.
left	Integer	Rectangle left coordinate: X.
top	Integer	Rectangle top coordinate: Y.
width	Integer	Rectangle width.
height	Integer	Rectangle height.

The following are the object fields returned in each landmarks array, member of the faces array defined above:

Fields	Type	Description
nose	Array	Nose Tip coordinates in the form [x: `Integer`, y: `Integer`].
nose_bottom_left	Array	Nose bottom left coordinates in the form [x: `Integer`, y: `Integer`].
nose_bottom_right	Array	Nose bottom right coordinates in the form [x: `Integer`, y: `Integer`].
mouth_left	Array	left most coordinates of the mouth in the form [x: `Integer`, y: `Integer`].
mouth_right	Array	Right most coordinates of the mouth in the form [x: `Integer`, y: `Integer`].
bottom_lip	Array	Bottom Lip coordinates in the form [x: `Integer`, y: `Integer`].
top_lip	Array	Top Lip coordinates in the form [x: `Integer`, y: `Integer`].
chin	Array	Chin coordinates in the form [x: `Integer`, y: `Integer`].
eye	Array	Array holding the coordinates of the region surrounding the eyes. These includes: pupil_left: Left Pupil coordinates in the form [x: `Integer`, y: `Integer`]. pupil_right: Right Pupil coordinates in the form [x: `Integer`, y: `Integer`]. left_brow_inner: Left Eye Brow Inner coordinates in the form [x: `Integer`, y: `Integer`]. left_brow_outer: Left Eye Brow Outer coordinates in the form [x: `Integer`, y: `Integer`]. right_brow_inner: Right Eye Brow Inner coordinates in the form [x: `Integer`, y: `Integer`]. right_brow_outer: Right Eye Brow Outer coordinates in the form [x: `Integer`, y: `Integer`]. left_inner: Left Eye Inner coordinates in the form [x: `Integer`, y: `Integer`]. left_outer: Left Eye Outer coordinates in the form [x: `Integer`, y: `Integer`]. right_inner: Right Eyer Inner coordinates in the form [x: `Integer`, y: `Integer`]. right_outer: Right Eyer Outer coordinates in the form [x: `Integer`, y: `Integer`].
bone	Array	Array holding the coordinates of some regions of the bone. These includes: center: Bone Center coordinates in the form [x: `Integer`, y: `Integer`]. outer_left: Coordinates of Left most region of the bone in the form [x: `Integer`, y: `Integer`]. outer_right: Coordinates of Right most region of the bone in the form [x: `Integer`, y: `Integer`].

For additional processing, feel free to adjust these coordinates for the next command such as crop for face extraction, drawrectangles for marking faces, mogrify and merge to mimic the Snapchat filters effects (refer to the REST API code samples for a concrete example).

If you need additional landmarks coordinates, please fill an API feature request ticket from the support tab of your dashboard ↗.

Code Samples


import requests
import json
from typing import List, Dict, Any

def smart_resize(img: str, width: int, height: int, key: str) -> str:
    """Resize an image using smartresize."""
    params = {
        'img': img,
        'key': key,
        'width': width,
        'height': height
    }
    response = requests.get('https://api.pixlab.io/smartresize', params=params)
    response.raise_for_status()
    reply = response.json()
    if reply['status'] != 200:
        raise Exception(reply['error'])
    return reply['link']

def apply_snapchat_filters(
    img: str,
    key: str,
    draw_crown: bool = False,
    flower: str = 'http://pixlab.xyz/images/flower_crown.png',
    dog_left_ear: str = 'http://pixlab.xyz/images/dog_left_ear.png',
    dog_right_ear: str = 'http://pixlab.xyz/images/dog_right_ear.png',
    dog_nose: str = 'http://pixlab.xyz/images/dog_nose.png'
) -> str:
    """Apply Snapchat-like filters to an image."""
    # Detect face landmarks
    response = requests.get(
        'https://api.pixlab.io/facelandmarks',
        params={'img': img, 'key': key}
    )
    response.raise_for_status()
    reply = response.json()
    
    if reply['status'] != 200:
        raise Exception(reply['error'])
    
    faces = reply.get('faces', [])
    if not faces:
        raise Exception("No faces were detected")
    
    print(f"{len(faces)} faces were detected")
    coordinates: List[Dict[str, Any]] = []

    for face in faces:
        cord = face['rectangle']
        landmarks = face['landmarks']
        
        if draw_crown:
            fit_crown = smart_resize(
                flower,
                20 + cord['width'],
                0,
                key
            )
            coordinates.append({
                'img': fit_crown,
                'x': landmarks['bone']['outer_left']['x'],
                'y': landmarks['bone']['outer_left']['y']
            })
        else:
            coordinates.extend([
                {
                    'img': smart_resize(dog_left_ear, cord['width']//2, cord['height']//2, key),
                    'x': landmarks['bone']['outer_left']['x'],
                    'y': landmarks['bone']['outer_left']['y']
                },
                {
                    'img': smart_resize(dog_right_ear, cord['width']//2, cord['height']//2, key),
                    'x': landmarks['bone']['outer_right']['x'],
                    'y': landmarks['bone']['outer_right']['y']
                },
                {
                    'img': smart_resize(dog_nose, cord['width']//2, cord['height']//2, key),
                    'x': landmarks['nose']['x'] - 18,
                    'y': landmarks['nose']['y'] - 10
                }
            ])
        draw_crown = not draw_crown

    # Perform composite operation
    response = requests.post(
        'https://api.pixlab.io/merge',
        headers={'Content-Type': 'application/json'},
        data=json.dumps({
            'src': img,
            'key': key,
            'cord': coordinates
        })
    )
    response.raise_for_status()
    reply = response.json()
    
    if reply['status'] != 200:
        raise Exception(reply['error'])
    
    return reply['link']

if __name__ == "__main__":
    # Configuration
    IMG_URL = 'https://trekkerscrapbook.files.wordpress.com/2013/09/face-08.jpg'
    API_KEY = 'My_PIXLAB_API_KEY'
    DRAW_CROWN = False

    try:
        result_url = apply_snapchat_filters(IMG_URL, API_KEY, DRAW_CROWN)
        print(f"Snap Filter Effect: {result_url}")
    except Exception as e:
        print(f"Error: {e}")


// Target image to composite stuff on. Must contain at least one face.
const img = 'https://trekkerscrapbook.files.wordpress.com/2013/09/face-08.jpg';

// The flower crown.
const flower = 'http://pixlab.xyz/images/flower_crown.png';

// The dog parts: Left & right ears, nose & optionally the tongue
const dog_left_ear  = 'http://pixlab.xyz/images/dog_left_ear.png';
const dog_right_ear = 'http://pixlab.xyz/images/dog_right_ear.png';
const dog_nose      = 'http://pixlab.xyz/images/dog_nose.png';
const dog_tongue    = 'http://pixlab.xyz/images/dog_tongue.png';

// Your PixLab API key
const key = 'My_PIXLAB_API_KEY';

// If set to true then composite the flower crown. Otherwise, composite the dog stuff.
let draw_crown = false;

// Resize an image (Dog parts or the flower crown) to fit the face dimension using smartresize.
async function smart_resize(img, width, height) {
    console.log("Resizing images...");
    const response = await fetch(`https://api.pixlab.io/smartresize?img=${encodeURIComponent(img)}&key=${key}&width=${width}&height=${height}`);
    const reply = await response.json();
    if (reply.status !== 200) {
        console.log(reply.error);
        process.exit(1);
    } else {
        return reply.link; // Resized image
    }
}

(async () => {
    // First step, Detect & extract the landmarks for each human face present in the image.
    let response = await fetch(`https://api.pixlab.io/facelandmarks?img=${encodeURIComponent(img)}&key=${key}`);
    let reply = await response.json();
    if (reply.status !== 200) {
        console.log(reply.error);
        process.exit(1);
    }

    const total = reply.faces.length; // Total detected faces
    if (total < 1) {
        console.log("No faces were detected..exiting");
        process.exit(1);
    }

    console.log(`${total} faces were detected`);

    // This list contain all the coordinates of the regions where the flower crown or the dog parts should be
    // Composited on top of the target image later using the `merge` command.
    let coordinates = [];

    // Iterate all over the detected faces and make our stuff
    for (let face of reply.faces) {
        // Show the face coordinates 
        console.log("Coordinates...");
        let cord = face.rectangle;
        console.log(`\twidth: ${cord.width} height: ${cord.height} x: ${cord.left} y: ${cord.top}`);

        // Show landmarks of interest:
        console.log("Landmarks...");
        let landmarks = face.landmarks;
        console.log(`\tNose: X: ${landmarks.nose.x}, Y: ${landmarks.nose.y}`);
        console.log(`\tBottom Lip: X: ${landmarks.bottom_lip.x}, Y: ${landmarks.bottom_lip.y}`);
        console.log(`\tTop Lip: X: ${landmarks.top_lip.x}, Y: ${landmarks.top_lip.y}`);
        console.log(`\tChin: X: ${landmarks.chin.x}, Y: ${landmarks.chin.y}`);
        console.log(`\tMouth Left: X: ${landmarks.mouth_left.x}, Y: ${landmarks.mouth_left.y}`);
        console.log(`\tMouth Right: X: ${landmarks.mouth_right.x}, Y: ${landmarks.mouth_right.y}`);

        console.log(`\tBone Center: X: ${landmarks.bone.center.x}, Y: ${landmarks.bone.center.y}`);
        console.log(`\tBone Outer Left: X: ${landmarks.bone.outer_left.x}, Y: ${landmarks.bone.outer_left.y}`);
        console.log(`\tBone Outer Right: X: ${landmarks.bone.outer_right.x}, Y: ${landmarks.bone.outer_right.y}`);

        console.log(`\tEye Pupil Left: X: ${landmarks.eye.pupil_left.x}, Y: ${landmarks.eye.pupil_left.y}`);
        console.log(`\tEye Pupil Right: X: ${landmarks.eye.pupil_right.x}, Y: ${landmarks.eye.pupil_right.y}`);

        console.log(`\tEye Left Brown Inner: X: ${landmarks.eye.left_brow_inner.x}, Y: ${landmarks.eye.left_brow_inner.y}`);
        console.log(`\tEye Right Brown Inner: X: ${landmarks.eye.right_brow_inner.x}, Y: ${landmarks.eye.right_brow_inner.y}`);

        console.log(`\tEye Left Outer: X: ${landmarks.eye.left_outer.x}, Y: ${landmarks.eye.left_outer.y}`);
        console.log(`\tEye Right Outer: X: ${landmarks.eye.right_outer.x}, Y: ${landmarks.eye.right_outer.y}`);

        draw_crown = !draw_crown;
        if (draw_crown) {
            // Resize the flower crown to fit the face width
            let fit_crown = await smart_resize(
                flower,
                20 + cord.width, // Face width
                0 // Let Pixlab decide the best height for this picture
            );
            // Composite the flower crown on top of the bone most left region.
            console.log(`\tCrown flower at: X: ${landmarks.bone.outer_left.x}, Y: ${landmarks.bone.outer_left.y}`);
            coordinates.push({
                img: fit_crown, // The resized flower crown
                x: landmarks.bone.outer_left.x,
                y: landmarks.bone.outer_left.y
            });
        } else {
            // Do the dog parts using the bone left & right regions and the nose coordinates.
            console.log("\tDog Parts Regions...");
            coordinates.push({
                img: await smart_resize(dog_left_ear, cord.width/2, cord.height/2),
                x: landmarks.bone.outer_left.x, // Adjust to get optimal effect
                y: landmarks.bone.outer_left.y  // Adjust to get optimal effect
            });
            coordinates.push({
                img: await smart_resize(dog_right_ear, cord.width/2, cord.height/2),
                x: landmarks.bone.outer_right.x, // Adjust to get optimal effect
                y: landmarks.bone.outer_right.y  // Adjust to get optimal effect
            });
            coordinates.push({
                img: await smart_resize(dog_nose, cord.width/2, cord.height/2),
                x: landmarks.nose.x - 18, // Adjust to get optimal effect
                y: landmarks.nose.y - 10 // Adjust to get optimal effect
            });
        }
    }

    // Finally, Perform the composite operation when we exit the loop
    console.log("Composite operation...");
    response = await fetch('https://api.pixlab.io/merge', {
        method: 'POST',
        headers: {
            'Content-Type': 'application/json',
        },
        body: JSON.stringify({
            src: img, // The target image.
            key: key,
            cord: coordinates // The coordinates list filled earlier with the resized images (flower crown & dog members) and the regions of interest 
        })
    });
    reply = await response.json();
    if (reply.status !== 200) {
        console.log(reply.error);
    } else {
        // Optionally call blur, oilpaint, grayscale for cool background effects..
        console.log("Snap Filter Effect: " + reply.link);
    }
})();

<?php

// Mimic the two famous Snapchat filters: The flower crown & the dog parts filter.
// The target image must contain at least one human face. The more faces you got, the more funny it should be!

// Target image to composite stuff on. Must contain at least one face.
$img = 'https://trekkerscrapbook.files.wordpress.com/2013/09/face-08.jpg';

// The flower crown.
$flower = 'http://pixlab.xyz/images/flower_crown.png';

// The dog parts: Left & right ears, nose & optionally the tongue
$dog_left_ear  = 'http://pixlab.xyz/images/dog_left_ear.png';
$dog_right_ear = 'http://pixlab.xyz/images/dog_right_ear.png';
$dog_nose      = 'http://pixlab.xyz/images/dog_nose.png';
$dog_tongue    = 'http://pixlab.xyz/images/dog_tongue.png';

// Your PixLab API key
$key = 'My_PIXLAB_API_KEY';

// If set to true then composite the flower crown. Otherwise, composite the dog stuff.
$draw_crown = false;

// Resize an image (Dog parts or the flower crown) to fit the face dimension using smartresize.
function smart_resize($img, $width, $height, $key) {
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, 'https://api.pixlab.io/smartresize');
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_POST, 1);
    curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query([
        'img' => $img,
        'key' => $key,
        'width' => $width,
        'height' => $height
    ]));

    $response = curl_exec($ch);
    curl_close($ch);
    $reply = json_decode($response, true);
    
    if ($reply['status'] != 200) {
        die($reply['error']);
    }
    return $reply['link']; // Resized image
}

// First step, Detect & extract the landmarks for each human face present in the image.
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, 'https://api.pixlab.io/facelandmarks?'.http_build_query([
    'img' => $img,
    'key' => $key
]));
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
$response = curl_exec($ch);
curl_close($ch);
$reply = json_decode($response, true);

if ($reply['status'] != 200) {
    die($reply['error']);
}

$total = count($reply['faces']); // Total detected faces
if ($total < 1) {
    die("No faces were detected..exiting");
}

echo $total . " faces were detected\n";

// This list contain all the coordinates of the regions where the flower crown or the dog parts should be
$coordinates = [];

// Iterate all over the detected faces and make our stuff
foreach ($reply['faces'] as $face) {
    // Show the face coordinates
    echo "Coordinates...\n";
    $cord = $face['rectangle'];
    echo "\twidth: " . $cord['width'] . " height: " . $cord['height'] . " x: " . $cord['left'] . " y: " . $cord['top'] . "\n";

    // Show landmarks of interest:
    echo "Landmarks...\n";
    $landmarks = $face['landmarks'];
    echo "\tNose: X: " . $landmarks['nose']['x'] . ", Y: " . $landmarks['nose']['y'] . "\n";
    echo "\tBottom Lip: X: " . $landmarks['bottom_lip']['x'] . ", Y: " . $landmarks['bottom_lip']['y'] . "\n";
    echo "\tTop Lip: X: " . $landmarks['top_lip']['x'] . ", Y: " . $landmarks['top_lip']['y'] . "\n";
    echo "\tChin: X: " . $landmarks['chin']['x'] . ", Y: " . $landmarks['chin']['y'] . "\n";
    echo "\tMouth Left: X: " . $landmarks['mouth_left']['x'] . ", Y: " . $landmarks['mouth_left']['y'] . "\n";
    echo "\tMouth Right: X: " . $landmarks['mouth_right']['x'] . ", Y: " . $landmarks['mouth_right']['y'] . "\n";
    echo "\tBone Center: X: " . $landmarks['bone']['center']['x'] . ", Y: " . $landmarks['bone']['center']['y'] . "\n";
    echo "\tBone Outer Left: X: " . $landmarks['bone']['outer_left']['x'] . ", Y: " . $landmarks['bone']['outer_left']['y'] . "\n";
    echo "\tBone Outer Right: X: " . $landmarks['bone']['outer_right']['x'] . ", Y: " . $landmarks['bone']['outer_right']['y'] . "\n";
    echo "\tEye Pupil Left: X: " . $landmarks['eye']['pupil_left']['x'] . ", Y: " . $landmarks['eye']['pupil_left']['y'] . "\n";
    echo "\tEye Pupil Right: X: " . $landmarks['eye']['pupil_right']['x'] . ", Y: " . $landmarks['eye']['pupil_right']['y'] . "\n";
    echo "\tEye Left Brown Inner: X: " . $landmarks['eye']['left_brow_inner']['x'] . ", Y: " . $landmarks['eye']['left_brow_inner']['y'] . "\n";
    echo "\tEye Right Brown Inner: X: " . $landmarks['eye']['right_brow_inner']['x'] . ", Y: " . $landmarks['eye']['right_brow_inner']['y'] . "\n";
    echo "\tEye Left Outer: X: " . $landmarks['eye']['left_outer']['x'] . ", Y: " . $landmarks['eye']['left_outer']['y'] . "\n";
    echo "\tEye Right Outer: X: " . $landmarks['eye']['right_outer']['x'] . ", Y: " . $landmarks['eye']['right_outer']['y'] . "\n";

    $draw_crown = !$draw_crown;
    if ($draw_crown) {
        // Resize the flower crown to fit the face width
        $fit_crown = smart_resize(
            $flower,
            20 + $cord['width'], // Face width
            0, // Let Pixlab decide the best height
            $key
        );
        // Composite the flower crown on top of the bone most left region.
        echo "\tCrown flower at: X: " . $landmarks['bone']['outer_left']['x'] . ", Y: " . $landmarks['bone']['outer_left']['y'] . "\n";
        $coordinates[] = [
            'img' => $fit_crown,
            'x' => $landmarks['bone']['outer_left']['x'],
            'y' => $landmarks['bone']['outer_left']['y']
        ];
    } else {
        // Do the dog parts using the bone left & right regions and the nose coordinates.
        echo "\tDog Parts Regions...\n";
        $coordinates[] = [
            'img' => smart_resize($dog_left_ear, $cord['width']/2, $cord['height']/2, $key),
            'x' => $landmarks['bone']['outer_left']['x'],
            'y' => $landmarks['bone']['outer_left']['y']
        ];
        $coordinates[] = [
            'img' => smart_resize($dog_right_ear, $cord['width']/2, $cord['height']/2, $key),
            'x' => $landmarks['bone']['outer_right']['x'],
            'y' => $landmarks['bone']['outer_right']['y']
        ];
        $coordinates[] = [
            'img' => smart_resize($dog_nose, $cord['width']/2, $cord['height']/2, $key),
            'x' => $landmarks['nose']['x'] - 18,
            'y' => $landmarks['nose']['y'] - 10
        ];
    }
}

// Finally, Perform the composite operation
echo "Composite operation...\n";
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, 'https://api.pixlab.io/merge');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode([
    'src' => $img,
    'key' => $key,
    'cord' => $coordinates
]));
curl_setopt($ch, CURLOPT_HTTPHEADER, ['Content-Type: application/json']);

$response = curl_exec($ch);
curl_close($ch);
$reply = json_decode($response, true);

if ($reply['status'] != 200) {
    die($reply['error']);
} else {
    echo "Snap Filter Effect: " . $reply['link'] . "\n";
}


require 'net/http'
require 'uri'
require 'json'

# Target image to composite stuff on. Must contain at least one face.
img = 'https://trekkerscrapbook.files.wordpress.com/2013/09/face-08.jpg'

# The flower crown.
flower = 'http://pixlab.xyz/images/flower_crown.png'

# The dog parts: Left & right ears, nose & optionally the tongue
dog_left_ear  = 'http://pixlab.xyz/images/dog_left_ear.png'
dog_right_ear = 'http://pixlab.xyz/images/dog_right_ear.png'
dog_nose      = 'http://pixlab.xyz/images/dog_nose.png'
dog_tongue    = 'http://pixlab.xyz/images/dog_tongue.png'

# Your PixLab API key
key = 'My_PIXLAB_API_KEY'

# If set to True then composite the flower crown. Otherwise, composite the dog stuff.
draw_crown = false

# Resize an image (Dog parts or the flower crown) to fit the face dimension using smartresize.
def smart_resize(img, width, height)
  puts "Resizing images..."
  uri = URI.parse('https://api.pixlab.io/smartresize')
  params = {
    'img' => img,
    'key' => key,
    'width' => width,
    'height' => height
  }
  uri.query = URI.encode_www_form(params)
  req = Net::HTTP.get_response(uri)
  reply = JSON.parse(req.body)
  if reply['status'] != 200
    puts reply['error']
    exit
  else
    return reply['link'] # Resized image
  end
end

# First step, Detect & extract the landmarks for each human face present in the image.
uri = URI.parse('https://api.pixlab.io/facelandmarks')
params = {
  'img' => img,
  'key' => key
}
uri.query = URI.encode_www_form(params)
req = Net::HTTP.get_response(uri)
reply = JSON.parse(req.body)
if reply['status'] != 200
  puts reply['error']
  exit
end

total = reply['faces'].length # Total detected faces
if total < 1
  puts "No faces were detected..exiting"
  exit
end

puts "#{total} faces were detected"

# This list contain all the coordinates of the regions where the flower crown or the dog parts should be
# Composited on top of the target image later using the `merge` command.
coordinates = []

# Iterate all over the detected faces and make our stuff
reply['faces'].each do |face|
  # Show the face coordinates 
  puts "Coordinates..."
  cord = face['rectangle']
  puts "\twidth: #{cord['width']} height: #{cord['height']} x: #{cord['left']} y: #{cord['top']}"
  
  # Show landmarks of interest:
  puts "Landmarks..."
  landmarks = face['landmarks']
  puts "\tNose: X: #{landmarks['nose']['x']}, Y: #{landmarks['nose']['y']}"
  puts "\tBottom Lip: X: #{landmarks['bottom_lip']['x']}, Y: #{landmarks['bottom_lip']['y']}"
  puts "\tTop Lip: X: #{landmarks['top_lip']['x']}, Y: #{landmarks['top_lip']['y']}"
  puts "\tChin: X: #{landmarks['chin']['x']}, Y: #{landmarks['chin']['y']}"
  puts "\tMouth Left: X: #{landmarks['mouth_left']['x']}, Y: #{landmarks['mouth_left']['y']}"
  puts "\tMouth Right: X: #{landmarks['mouth_right']['x']}, Y: #{landmarks['mouth_right']['y']}"
  
  puts "\tBone Center: X: #{landmarks['bone']['center']['x']}, Y: #{landmarks['bone']['center']['y']}"
  puts "\tBone Outer Left: X: #{landmarks['bone']['outer_left']['x']}, Y: #{landmarks['bone']['outer_left']['y']}"
  puts "\tBone Outer Right: X: #{landmarks['bone']['outer_right']['x']}, Y: #{landmarks['bone']['outer_right']['y']}"
  
  puts "\tBone Center: X: #{landmarks['bone']['center']['x']}, Y: #{landmarks['bone']['center']['y']}"
  
  puts "\tEye Pupil Left: X: #{landmarks['eye']['pupil_left']['x']}, Y: #{landmarks['eye']['pupil_left']['y']}"
  puts "\tEye Pupil Right: X: #{landmarks['eye']['pupil_right']['x']}, Y: #{landmarks['eye']['pupil_right']['y']}"
  
  puts "\tEye Left Brown Inner: X: #{landmarks['eye']['left_brow_inner']['x']}, Y: #{landmarks['eye']['left_brow_inner']['y']}"
  puts "\tEye Right Brown Inner: X: #{landmarks['eye']['right_brow_inner']['x']}, Y: #{landmarks['eye']['right_brow_inner']['y']}"
  
  puts "\tEye Left Outer: X: #{landmarks['eye']['left_outer']['x']}, Y: #{landmarks['eye']['left_outer']['y']}"
  puts "\tEye Right Outer: X: #{landmarks['eye']['right_outer']['x']}, Y: #{landmarks['eye']['right_outer']['y']}"
  
  draw_crown = !draw_crown
  if draw_crown
    # Resize the flower crown to fit the face width
    fit_crown = smart_resize(
      flower,
      20 + cord['width'], # Face width
      0 # Let Pixlab decide the best height for this picture
    )
    # Composite the flower crown on top of the bone most left region.
    puts "\tCrown flower at: X: #{landmarks['bone']['outer_left']['x']}, Y: #{landmarks['bone']['outer_left']['y']}"
    coordinates << {
      'img' => fit_crown, # The resized flower crown
      'x' => landmarks['bone']['outer_left']['x'],
      'y' => landmarks['bone']['outer_left']['y']
    }
  else
    # Do the dog parts using the bone left & right regions and the nose coordinates.
    puts "\tDog Parts Regions..."
    coordinates << {
      'img' => smart_resize(dog_left_ear, cord['width']/2, cord['height']/2),
      'x' => landmarks['bone']['outer_left']['x'], # Adjust to get optimal effect
      'y' => landmarks['bone']['outer_left']['y']  # Adjust to get optimal effect
    }
    coordinates << {
      'img' => smart_resize(dog_right_ear, cord['width']/2, cord['height']/2),
      'x' => landmarks['bone']['outer_right']['x'], # Adjust to get optimal effect
      'y' => landmarks['bone']['outer_right']['y']  # Adjust to get optimal effect
    }
    coordinates << {
      'img' => smart_resize(dog_nose, cord['width']/2, cord['height']/2),
      'x' => landmarks['nose']['x'] - 18, # Adjust to get optimal effect
      'y' => landmarks['nose']['y'] - 10 # Adjust to get optimal effect
    }
  end
end

# Finally, Perform the composite operation when we exit the loop
puts "Composite operation..."
uri = URI.parse('https://api.pixlab.io/merge')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true
req = Net::HTTP::Post.new(uri.path, 'Content-Type' => 'application/json')
req.body = {
  'src' => img, # The target image.
  'key' => key,
  'cord' => coordinates # The coordinates list filled earlier with the resized images (flower crown & dog members) and the regions of interest 
}.to_json
res = http.request(req)
reply = JSON.parse(res.body)
if reply['status'] != 200
  puts reply['error']
else
  # Optionally call blur, oilpaint, grayscale for cool background effects..
  puts "Snap Filter Effect: #{reply['link']}"
end

Similar API Endpoints

bg-remove, nsfw, sfw, ocr, crop, imgdiff, grayscale, drawrectangles, mogrify, meme, tagimg, faceverify ↗, facelookup ↗, screencapture, merge, smartresize, composite