Stable Diffusion 3

Text to image with Stable Diffusion 3

Python

import requests
import json

url = "https://api.imagepipeline.io/sd3/v1"
headers = {
    "API-Key": "Your API Key",
    "Content-Type": "application/json"
}
data = {
  "samples": 2,
  "prompt": "High end wildlife photography, beautiful colourful toucan sitting on a tree branch, trending on artstation",
  "negative_prompt": "censored, worst quality, normal quality, low quality, low res, blurry, distorted facial, missing eyes, distorted eyes, distorted nose, bad mouth, watermark, weird faces, extra digits, cropped, jpeg artifacts, signature, username, error, sketch, duplicate, ugly, monochrome, horror, geometry, mutation, disgusting, low resolution",
  "guidance_scale": 7,
  "width": 1024,
  "height": 1024,
  "num_inference_steps": 29
}
response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json())

JavaScript

const url = "https://api.imagepipeline.io/sd3/v1";
const headers = {
  "API-Key": "Your API Key",
  "Content-Type": "application/json"
};
const data = {
  "samples": 2,
  "prompt": "High end wildlife photography, beautiful colourful toucan sitting on a tree branch, trending on artstation",
  "negative_prompt": "censored, worst quality, normal quality, low quality, low res, blurry, distorted facial, missing eyes, distorted eyes, distorted nose, bad mouth, watermark, weird faces, extra digits, cropped, jpeg artifacts, signature, username, error, sketch, duplicate, ugly, monochrome, horror, geometry, mutation, disgusting, low resolution",
  "guidance_scale": 7,
  "width": 1024,
  "height": 1024,
  "num_inference_steps": 29
};
fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch((error) => console.error('Error:', error));

PHP

<?php
$url = "https://api.imagepipeline.io/sd3/v1";
$headers = array(
  "API-Key: Your-API-Key",
  "Content-Type: application/json"
);
$data = array(
  "samples" => 2,
  "prompt" => "High end wildlife photography, beautiful colourful toucan sitting on a tree branch, trending on artstation",
  "negative_prompt" => "censored, worst quality, normal quality, low quality, low res, blurry, distorted facial, missing eyes, distorted eyes, distorted nose, bad mouth, watermark, weird faces, extra digits, cropped, jpeg artifacts, signature, username, error, sketch, duplicate, ugly, monochrome, horror, geometry, mutation, disgusting, low resolution",
  "guidance_scale" => 7,
  "width" => 1024,
  "height" => 1024,
  "num_inference_steps" => 29
);
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
$response = curl_exec($ch);
if($response === FALSE){
  die(curl_error($ch));
}
$responseData = json_decode($response, TRUE);
curl_close($ch);
var_dump($responseData);
?>

Available JSON Parameters for Control

Parameter	Type	Notes
prompt	string	Required. Description of the image to generate.
negative_prompt	string	Required. Description of what should not appear in the image.
num_inference_steps	integer	Required. Number of inference steps.
samples	integer	Required. Max: 4. Number of images to generate.
guidance_scale	number	Required. Max: 20. Controls how much the image should adhere to the prompt.
height	integer	Default: 1024. Optional image height.
width	integer	Default: 1024. Optional image width.
webhook	string	Generated image will be sent to this webhook.
direct_link	boolean	Fetches the friendly URL in PNG format.
batch_id	string	Adds a batch_id.
file_prefix	string	Adds a file_prefix.
queued_image_urls	boolean	Returns the links of the images prematurely. The link will have the image once the task is completed.

Status

Your response will include a status.

• If the status = SUCCESS, you will also have download_urls that will have the links to your generated image based on the number of samples you have entered. The maximum number of samples that can be generated is 4.
• If the status = PENDING, you will receive an id. You can use the status endpoint to fetch your image using the id.
• If the status = FAILURE, you will receive only an error message.

Endpoint: [GET]

• https://api.imagepipeline.io/sd3/v1/status/{{id}}

Pass the API-Key as the authorization in the header.