After being signed up you will get credentials for API access. You must keep them safe. These credentials should be used for basic access authentication.
The versioning of API is a part of URI. To use v1 of the API the request URI should begin with /v1 followed by API method.
https://api.everypixel.com/v1By sending an image to this method you can get a list of suggested keywords. You may specify a number of returned words or a threshold of its minimum score. Just provide num_keywords or threshold parameters to this method.
Image should be specified by its url or uploaded with multipart form by parameter 'data'. You should use, respectively, GET and POST methods.
Language can be specified via lang parameters, which have value en by default. Possible parameters:
en, ru, es, fr, de, pt, it
Also keywords have the option to return colors keywords. This behavior is controlled by colors and num_colors parameters. Colors is a boolean flag to toggle between returning colors in response and not returning it. Parameter num_colors is the controlling number of returned colors.
curl --user "<your-client-id>:<your-client-secret>" "https://api.everypixel.com/v1/keywords?url=http://image.everypixel.com/2014.12/67439828186edc79b9be81a4dedea8b03c09a12825b_b.jpg&num_keywords=10&colors=True&num_colors=5&lang=en"import requests
client_id = '<your-client-id>'
client_secret = '<your-client-secret>'
params = {'url': 'http://image.everypixel.com/2014.12/67439828186edc79b9be81a4dedea8b03c09a12825b_b.jpg', 'num_keywords': 10, 'colors': True, 'num_colors': 5, 'lang': 'en'}
keywords = requests.get('https://api.everypixel.com/v1/keywords', params=params, auth=(client_id, client_secret)).json()
with open('image.jpg','rb') as image:
data = {'data': image}
keywords = requests.post('https://api.everypixel.com/v1/keywords', files=data, auth=(client_id, client_secret)).json()
print(keywords)<?php
// Your client credentials
$client_id = '<your-client-id>';
$client_secret = '<your-client-secret>';
// The image URL and parameters
$params = [
'url' => 'http://image.everypixel.com/2014.12/67439828186edc79b9be81a4dedea8b03c09a12825b_b.jpg',
'num_keywords' => 10,
'colors' => true,
'num_colors' => 5,
'lang' => 'en'
];
// Build the query string from parameters
$query = http_build_query($params);
// The API endpoint
$url = "https://api.everypixel.com/v1/keywords?$query";
// Initialize a cURL session
$ch = curl_init($url);
// Set the basic authentication
curl_setopt($ch, CURLOPT_USERPWD, "$client_id:$client_secret");
// Set options to return the response as a string
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
// Execute the request and fetch the response
$response = curl_exec($ch);
// Check for cURL errors
if (curl_errno($ch)) {
echo 'cURL error: ' . curl_error($ch);
exit;
}
// Close the cURL session
curl_close($ch);
// Decode the JSON response
$keywords = json_decode($response, true);
// Print the response (for debugging)
print_r($keywords);
?>{
"keywords": [
{"keyword": "animal", "score": 0.9718916489849907},
{"keyword": "cute", "score": 0.9601239529000117},
{"keyword": "pets", "score": 0.949350643787409},
{"keyword": "kitten", "score": 0.9039852518100446},
{"keyword": "domestic cat", "score": 0.8818465735911328},
{"keyword": "domestic animals", "score": 0.773913246291121},
{"keyword": "young animal", "score": 0.6324827753197934},
{"keyword": "mammal", "score": 0.5434195324260841},
{"keyword": "feline", "score": 0.4977278418785077},
{"keyword": "small", "score": 0.46956064184549734}
],
"colors": [
{"name": "WhiteSmoke", "rgb": [237, 238, 240], "hex": "#edeef0", "percentage": 42.88},
{"name": "Sienna", "rgb": [123, 79, 50], "hex": "#7b4f32", "percentage": 7.43},
{"name": "Tan", "rgb": [195, 171, 146], "hex": "#c3ab92", "percentage": 16.71},
{"name": "Peru", "rgb": [168, 130, 96], "hex": "#a88260", "percentage": 15.34},
{"name": "PeachPuff", "rgb": [215, 207, 200], "hex": "#d7cfc8", "percentage": 17.64}
],
"status": "ok"
}This method allows you to get the quality score for your photo. This service doesn't measure how cool or beautiful a person or an object on a photo may look. It cares only about technical parts like brightness, contrast, noise and so on. The service is not dedicated for scoring historical photos, illustrations or 3D visualizations.
Image should be specified by its url or uploaded with multipart form by parameter 'data'. You should use, respectively, GET and POST methods.
curl --user "<your-client-id>:<your-client-secret>" "https://api.everypixel.com/v1/quality?url=http://image.everypixel.com/2014.12/67439828186edc79b9be81a4dedea8b03c09a12825b_b.jpg"client_id = '<your-client-id>'
client_secret = '<your-client-secret>'
params = {'url': 'http://image.everypixel.com/2014.12/67439828186edc79b9be81a4dedea8b03c09a12825b_b.jpg'}
quality = requests.get('https://api.everypixel.com/v1/quality', params=params, auth=(client_id, client_secret)).json()
with open('image.jpg','rb') as image:
data = {'data': image}
quality = requests.post('https://api.everypixel.com/v1/quality', files=data, auth=(client_id, client_secret)).json()$authorization = "<your-client-id>" . ":" . "<your-client-secret>";
$url = "https://api.everypixel.com/v1/quality?url=http://image.everypixel.com/2014.12/67439828186edc79b9be81a4dedea8b03c09a12825b_b.jpg";
$curl = curl_init();
curl_setopt($curl, CURLOPT_USERPWD, $authorization);
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
$data = curl_exec($curl);
curl_close($curl);
$json = json_decode($data);{
"quality": {
"score": 0.9729430521699124
},
"status": "ok"
}The main difference between Stock photo scoring and this model is in the training dataset. User-Generated Photo Scoring is a model trained on a 347 000 of user photos from Instagram. Estimation parameters for this model were prepared by a group of 10 professional photographers. Scoring methods are based on five classes: very bad (0-20), bad (20-40), normal (40-60), good (60-80) and excellent (80-100).
This model is designed to evaluate user photos taken both by a professional camera and by a camera of a smartphone. It doesn't estimate the plot and do not measure how cool or beautiful a person or an object on a photo may look. It cares only about technical parts like brightness, contrast, noise and so on. The service is not dedicated for scoring historical photos, illustrations or 3D visualizations.
Image should be specified by its url or uploaded with multipart form by parameter 'data'. You should use, respectively, GET and POST methods.
curl --user "<your-client-id>:<your-client-secret>" "https://api.everypixel.com/v1/quality_ugc?url=http://image.everypixel.com/2014.12/67439828186edc79b9be81a4dedea8b03c09a12825b_b.jpg"client_id = '<your-client-id>'
client_secret = '<your-client-secret>'
params = {'url': 'http://image.everypixel.com/2014.12/67439828186edc79b9be81a4dedea8b03c09a12825b_b.jpg'}
quality = requests.get('https://api.everypixel.com/v1/quality_ugc', params=params, auth=(client_id, client_secret)).json()
with open('image.jpg','rb') as image:
data = {'data': image}
quality = requests.post('https://api.everypixel.com/v1/quality_ugc', files=data, auth=(client_id, client_secret)).json()$authorization = "<your-client-id>" . ":" . "<your-client-secret>";
$url = "https://api.everypixel.com/v1/quality_ugc?url=http://image.everypixel.com/2014.12/67439828186edc79b9be81a4dedea8b03c09a12825b_b.jpg";
$curl = curl_init();
curl_setopt($curl, CURLOPT_USERPWD, $authorization);
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
$data = curl_exec($curl);
curl_close($curl);
$json = json_decode($data);{
"quality": {
"score": 0.5947988033294678,
"class": 3
},
"status": "ok"
}By sending a video to this method you can get a list of suggested keywords. You may specify a number of returned words or a threshold of its minimum score. Just provide num_keywords or threshold parameter to this method.
The method successfully works only with video files with a duration of 5 to 60 seconds. Increasing the duration of the video decreases the relevance of keywords.
Video should be specified by its url or uploaded with multipart form by parameter 'data'. You should use, respectively, GET and POST methods.
curl --user "<your-client-id>:<your-client-secret>" "https://api.everypixel.com/v1/video_keywords?url=https://media.gettyimages.com/videos/man-talking-with-colleague-in-the-office-video-id843434746&num_keywords=10"client_id = '<your-client-id>'
client_secret = '<your-client-secret>'
params = {'url': 'https://media.gettyimages.com/videos/man-talking-with-colleague-in-the-office-video-id843434746', 'num_keywords': 10}
keywords = requests.get('https://api.everypixel.com/v1/video_keywords', params=params, auth=(client_id, client_secret)).json()
with open('video.mp4','rb') as file:
data = {'data': file}
keywords = requests.post('https://api.everypixel.com/v1/video_keywords', files=data, auth=(client_id, client_secret)).json()$authorization = "<your-client-id>" . ":" . "<your-client-secret>";
$url = "https://api.everypixel.com/v1/video_keywords?url=https://media.gettyimages.com/videos/man-talking-with-colleague-in-the-office-video-id843434746&num_keywords=10";
$curl = curl_init();
curl_setopt($curl, CURLOPT_USERPWD, $authorization);
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
$data = curl_exec($curl);
curl_close($curl);
$json = json_decode($data);{
"keywords": [
{"keyword": "Medium shot", "score": 0.8536547422409058},
{"keyword": "Real time", "score": 0.8485572934150696},
{"keyword": "Animal", "score": 0.7466279963652293},
{"keyword": "Men", "score": 0.86750519275665283},
{"keyword": "Business", "score": 0.7157746723720005},
{"keyword": "Indoors", "score": 0.6314120207514081},
{"keyword": "Adult", "score": 0.6239697535832723},
{"keyword": "People", "score": 0.6199291689055306},
{"keyword": "Caucasian Ethnicity", "score": 0.6174033582210541},
{"keyword": "Office", "score": 0.6139942705631256}
],
"status": "ok"
}This method allows you to find faces on your photo and estimate ages of them. The output is a list of estimated ages and bounding box coordinates of each face detected in the image. Also you will get confidence score of face recognition.
Image should be specified by its url or uploaded with multipart form by parameter 'data'. You should use, respectively, GET and POST methods.
curl --user "<your-client-id>:<your-client-secret>" "https://api.everypixel.com/v1/faces?url=https://labs.everypixel.com/static/i/estest_sample3.jpg"client_id = '<your-client-id>'
client_secret = '<your-client-secret>'
params = {'url': 'https://labs.everypixel.com/static/i/estest_sample3.jpg'}
quality = requests.get('https://api.everypixel.com/v1/faces', params=params, auth=(client_id, client_secret)).json()
with open('image.jpg','rb') as image:
data = {'data': image}
quality = requests.post('https://api.everypixel.com/v1/faces', files=data, auth=(client_id, client_secret)).json()$authorization = "<your-client-id>" . ":" . "<your-client-secret>";
$url = "https://api.everypixel.com/v1/faces?url=https://labs.everypixel.com/static/i/estest_sample3.jpg";
$curl = curl_init();
curl_setopt($curl, CURLOPT_USERPWD, $authorization);
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
$data = curl_exec($curl);
curl_close($curl);
$json = json_decode($data);{
"faces": [{
"age": 20.553737561567686,
"score": 0.9999862909317017,
"bbox": [488.1020906694572, 147.58440036790006, 824.1707326180912, 581.0635042573758],
"class": "Age - Young Adult"
}],
"status": "ok"
}Lipsync API uses advanced machine learning algorithms and deep neural networks to synchronize lip movements with speech audio in videos.
This process results in high-quality, localized content that accurately reflects the speaker's expressions.
Sending a POST or GET request to createclient_id = '<your-client-id>'
client_secret = '<your-client-secret>'
audio_path = Path('folder/example.wav')
video_path = Path('folder/example.mp4')
audio_file = open(audio_path, 'rb')
video_file = open(video_path, 'rb')
# POST request
response = requests.post(
url="https://api.everypixel.com/v1/lipsync/create",
files={'audio': (audio_path.name, audio_file),
'video': (video_path.name, video_file)},
data={
"title": "<my_video: str>", # OPTIONAL, default=task_id, affects the file name
"callback": <url: str> # OPTIONAL, default=None, see the callback section
},
auth=(client_id, client_secret)
)
audio_file.close()
video_file.close()
# or GET request
response = requests.get(
url="https://api.everypixel.com/v1/lipsync/create",
params={
"audio_url": "https://labs.everypixel.com/media/tts/audio_samples_demo/ascend.mp3",
"video_url": "https://labs.everypixel.com/static/v/lipsync.mp4",
"title": "<my_video: str>" # OPTIONAL, default=task_id, affects the file name
"callback": <url: str> # OPTIONAL, default=None
},
auth=(client_id, client_secret)
)
# Save task_id to check the status
task_id = response.json().get("task_id"){
"task_id": "uuid",
"status": "str",
"progress": "float",
"queue": "int",
"result": "str"
}status = ""
while not status in ["SUCCESS", "FAILURE", "REVOKED"]:
sleep(5)
response = requests.get(
url= "https://api.everypixel.com/v1/lipsync/status?task_id={task_id}"
)
print(response.status_code, response.json())
status = response.json().get("status"){
"task_id": "uuid",
"status": "str",
"progress": "float",
"queue": "int",
"result": "str"
}Text-to-Speech is a powerful API that simplifies the process of converting text into speech and integrating it into a wide range of applications, including business, sales, customer support, and technical environments.
client_id = '<your-client-id>'
client_secret = '<your-client-secret>'
response = requests.post(
url="https://api.everypixel.com/v1/tts/create",
data={"voice": "<voice: str>",
"text": "<text to read: str>",
"title": "<my_audio: str>",
"callback": "url" # OPTIONAL, default=None, see the callback section
},
auth=(client_id, client_secret)
)
# Save task_id to check the status
task_id = response.json().get("task_id"){
"task_id": "uuid",
"status": "str",
"eta": "float",
"queue": "int",
"result": "str"
}status = ""
while not status in ["SUCCESS", "FAILURE", "REVOKED"]:
sleep(5)
response = requests.get(
url="https://api.everypixel.com/v1/tts/status?task_id={task_id}"
)
print(response.status_code, response.json())
status = response.json().get("status"){
"task_id": "uuid",
"status": "str",
"eta": "float",
"queue": "int",
"result": "str"
}
Image Face Swap API — Effortlessly replace faces in photos with our versatile API. Create amusing or transformative visuals with ease, enhancing your image editing capabilities.
client_id = '<your-client-id>'
client_secret = '<your-client-secret>'
source_path = Path('folder/source.png')
target_path = Path('folder/target.png')
source_file = open(source_path, 'rb')
target_file = open(target_path, 'rb')
response = requests.post(
url= "https://api.everypixel.com/v1/imageswap/create",
files={'source': (source_path.name, source_file),
'target': (target_path.name, target_file)},
data={
"use_gfpgan": <False: bool>,
"title": "<title: str>", # OPTIONAL, default=task_id, affects the file name
"callback": "<url: str>" # OPTIONAL, default=None, see the callback section
},
auth=(client_id, client_secret)
)
source_file.close()
target_file.close()
# Save task_id to check the status
task_id = response.json().get("task_id"){
"task_id": "uuid",
"status": "str",
"eta": "float",
"queue": "int",
"result": "str"
}status = ""
while not status in ["SUCCESS", "FAILURE", "REVOKED"]:
sleep(5)
response = requests.get(
url=f"https://api.everypixel.com/v1/imageswap/status?task_id={task_id}"
)
print(response.status_code, response.json())
status = response.json().get("status"){
"task_id": "uuid",
"status": "str",
"eta": "float",
"queue": "int",
"result": "str"
}
Video Face Swap API — Revolutionize video content by seamlessly swapping faces using our API. Unleash creativity as you effortlessly exchange faces in videos for captivating results.
client_id = '<your-client-id>'
client_secret = '<your-client-secret>'
source_path = Path('folder/source.png')
target_path = Path('folder/target.mp4')
source_file = open(source_path, 'rb')
target_file = open(target_path, 'rb')
response = requests.post(
url= "https://api.everypixel.com/v1/videoswap/create",
files={'source': (source_path.name, source_file),
'target': (target_path.name, target_file)},
data={
"use_gfpgan": <False: bool>,
"title": "<title: str>", # OPTIONAL, default=task_id, affects the file name
"callback": "<url: str>" # OPTIONAL, default=None, see the callback section
},
auth=(client_id, client_secret)
)
source_file.close()
target_file.close()
# Save task_id to check the status
task_id = response.json().get("task_id"){
"task_id": "uuid",
"status": "str",
"eta": "float",
"queue": "int",
"result": "str"
}status = ""
while not status in ["SUCCESS", "FAILURE", "REVOKED"]:
sleep(5)
response = requests.get(
url=f"https://api.everypixel.com/v1/videoswap/status?task_id={task_id}"
)
print(response.status_code, response.json())
status = response.json().get("status"){
"task_id": "uuid",
"status": "str",
"eta": "float",
"queue": "int",
"result": "str"
}
Integrate image caption generation effortlessly with our API. Automatically analyze images and obtain precise, contextually relevant captions for improved content enrichment.
By sending an image to this method you can get a suggested title.
Image should be uploaded with multipart form by parameter 'file'. You should use POST method.
curl -X POST -u <your-client-id>:<your-client-secret> \ -F "data=@/path/to/image.jpg" \ https://api.everypixel.com/v1/image_captioningclient_id = '<your-client-id>'
client_secret = '<your-client-secret>'
with open('image.jpg','rb') as image:
data = {'data': image}
title = requests.post('https://api.everypixel.com/v1/image_captioning', files=data, auth=(client_id, client_secret)).json()$authorization = "<your-client-id>" . ":" . "<your-client-secret>";
$url = "https://api.everypixel.com/v1/image_captioning";
$curl = curl_init();
curl_setopt($curl, CURLOPT_USERPWD, $authorization);
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
curl_setopt($curl, CURLOPT_POST, true);
curl_setopt($curl, CURLOPT_POSTFIELDS, ['data' => new CURLFile('/path/to/image.jpg')]);
$data = curl_exec($curl);
curl_close($curl);
$json = json_decode($data);{
"result": {
"caption": "<caption>"
},
"status": True
}When using Text-to-Speech, Lipsync, Imageswap and Videoswap API's, you can pass a URL of an endpoint on your machine as a callback parameter, expecting to receive a POST request with a JSON data containing status of the task and file url.
Make sure the specified endpoint is accessible from the internet.
{
"task_id": "<uuid: str>",
"status": "<status: str>",
"file_url": "<url: str>", # OPTIONAL, when status is SUCCESS
"video_duration": <20: int>, # OPTIONAL, in seconds, when the output file type is video
}Most of the errors returned by the API have json formatted text.
{
"status": "error",
"message": "Threshold must be float."
}Also, you can receive non-successful HTTP status codes:
401 - you have no access to a specified endpoint. It might happen if your access token has been expired.
429 - you have exceeded available requests from your plan.