Stable Diffusion XL

The optimised base model of SDXL designed to create high quality images with a simple prompt description

Python

import requests
import json
url = "https://api.imagepipeline.io/generate/v2"
headers = {
    "API-Key": "Your API Key"
}
data = {
  
    "prompt": "cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k"

}
response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json())

JavaScript

const url = "https://api.imagepipeline.io/generate/v2";
const headers = {
  "API-Key": "Your API Key",
  "Content-Type": "application/json"
};
const data = {
  "prompt": "cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k"
};
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/generate/v2";
$headers = array(
  "API-Key: Your-API-Key",
  "Content-Type: application/json"
);
$data = array(
  
  "prompt" => "cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k"
);
$ch = curl_init($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	Permissible values	Notes
prompt	string	Required. Check our Prompt Guide for tips.
negative_prompt	string	Required. Check our Prompt Guide for tips.
model_id	string	Default: 6b760847-792b-46c0-a7f3-a53f952d6836.
num_inference_steps	integer	Default: 20. Integer numbers. Ideal value: 20-30.
samples	integer	Max: 4. Default: 1. Generates a maximum of 4 samples per API call.
clip_skip	integer	Max: 12. Integer numbers.
strength	number	Max: 1. Default: 0.8. Optional denoise strength.
guidance_scale	number	Max: 20. Default: 7.5. Higher guidance scale prioritizes text prompt relevance.
height	integer	Max: 1536. Default: 1024. Optional image height.
width	integer	Max: 1536. Default: 1024. Optional image width.
lora_models	array string[]	Default: []. Optional LoRa models (comma separated).
lora_weights	array number[]	Default: []. Optional LoRa weights (comma separated).
embeddings	array string[]	Default: []. Optional embeddings (comma separated).
seed	integer	Default: -1. Controlling the seed can help generate reproducible images.
safety_checker	boolean	Checks for NSFW images and filters explicit images.
webhook	string	Generated image will be sent to this webhook.
base64	boolean	If base64 output is needed.
server_id	string	Optional server_id to use enterprise subscription. Load-balance with any or specific id.
scheduler	allOf	Choose an appropriate scheduler. Valid values:
		- EulerDiscreteScheduler
		- DDIMScheduler
		- DDPMScheduler
		- HeunDiscreteScheduler
		- UniPCMultistepScheduler
		- DPMSolverMultistepScheduler
		- DEISMultistepScheduler
		- PNDMScheduler
		- EulerAncestralDiscreteScheduler
		- KDPM2DiscreteScheduler
		- LCMScheduler
		- DPMSolverMultistepSchedulerSDE
ip_adapter_style_images	array string[]	Default: []. Reference images for multi-ip-adapter.
ip_adapter_image	string	Reference image for ip-adapter.
ip_adapter	array string[]	Default: []. Valid values:
		- ip-adapter_sdxl
		- ip-adapter_sdxl_vit-h
		- ip-adapter-plus_sdxl_vit-h
		- ip-adapter-plus-face_sdxl_vit-h
ip_adapter_scale	array number[]	Default: []. Adjust the text prompt and image prompt condition ratio.
hires	boolean	Fixes small imperfections.
hidiffusion	boolean	Applies hidiffusion.
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 generation 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 a 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:

• https://api.imagepipeline.io/generate/v2/status/{{id}}

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