1const axios = require('axios');
3const fs = require('fs');
4const path = require('path');
6async function toB64(imgPath) {
7    const data = fs.readFileSync(path.resolve(imgPath));
8    return Buffer.from(data).toString('base64');
11const api_key = "YOUR API-KEY";
12const url = "";
14const data = {
15  "image": "toB64('')",
16  "mask": "toB64('')",
17  "prompt": "A man with black sun glasses",
18  "negative_prompt": "bad quality, painting, blur",
19  "samples": 1,
20  "scheduler": "DDIM",
21  "num_inference_steps": 25,
22  "guidance_scale": 7.5,
23  "seed": 12467,
24  "strength": 0.9,
25  "base64": false
28(async function() {
29    try {
30        const response = await, data, { headers: { 'x-api-key': api_key } });
31        console.log(;
32    } catch (error) {
33        console.error('Error:',;
34    }
HTTP Response Codes
200 - OKImage Generated
401 - UnauthorizedUser authentication failed
404 - Not FoundThe requested URL does not exist
405 - Method Not AllowedThe requested HTTP method is not allowed
406 - Not AcceptableNot enough credits
500 - Server ErrorServer had some issue with processing


imageimage *

Input Image.

maskimage *

Mask Image

promptstr *

Prompt to render

negative_promptstr ( default: None )

Prompts to exclude, eg. 'bad anatomy, bad hands, missing fingers'

samplesint ( default: 1 ) Affects Pricing

Number of samples to generate.

min : 1,

min : 4

schedulerenum:str ( default: DPM2 Karras )

Type of scheduler.

Allowed values:

num_inference_stepsint ( default: 25 ) Affects Pricing

Number of denoising steps.

min : 20,

min : 100

guidance_scalefloat ( default: 7.5 )

Scale for classifier-free guidance

min : 1,

min : 25

seedint ( default: -1 )

Seed for image generation.

min : -1,

min : 999999999999999

strengthfloat ( default: 7.5 )

Scale for classifier-free guidance

min : 0,

min : 0.99

base64boolean ( default: 1 )

Base64 encoding of the output image.

To keep track of your credit usage, you can inspect the response headers of each API call. The x-remaining-credits property will indicate the number of remaining credits in your account. Ensure you monitor this value to avoid any disruptions in your API usage.

SDXL Inpainting

Stable Diffusion XL Inpainting is a state-of-the-art model that represents the pinnacle of image inpainting technology. This model is a specialized variant of the renowned Stable Diffusion series, designed to seamlessly fill in and reconstruct parts of images with astonishing accuracy and detail. It's a transformative tool for artists, designers, and photo editors who require the highest fidelity in image restoration and manipulation.

SDXL Inpainting operates on a sophisticated neural network architecture that excels in understanding context and texture to perform inpainting tasks. It leverages a deep understanding of image composition to predict and regenerate missing or damaged portions of images, making them whole with a level of detail that rivals the original. The model's nuanced approach ensures that the inpainted areas blend indistinguishably with the surrounding pixels, maintaining the integrity of the artwork or photograph.


  1. High-Fidelity Inpainting: Delivers exceptional quality inpainting, capable of handling complex textures and patterns.

  2. Context-Aware Regeneration: Intuitively understands the surrounding image context to provide coherent and seamless inpainting results.

  3. Advanced Neural Network: Built on the robust Stable Diffusion XL framework, ensuring reliability and performance.

  4. Versatile Application: Ideal for a wide range of use cases, from restoring historical photographs to creating new art pieces.

Use Cases

  1. Art Restoration: Enables artists and restorers to repair damaged artwork with results that respect the original creator's vision.

  2. Photo Editing: Provides photographers with a powerful tool to remove unwanted elements or repair imperfections in images.

  3. Creative Design: Assists designers in creating cohesive visual content, even when working with incomplete elements.

  4. Research and Archiving: Offers a solution for archivists to restore aged or deteriorating photographic documents.

  5. Entertainment Industry: Can be used in film and game development to refine visual assets or generate new content from existing materials.