Stable Diffusion 3 Image To Image API Introduction

Generate an image using a Stable Diffusion 3 model.Generating with a prompt and an image.

Credits

The service uses 8 credits per successful result. You will not be charged for failed results.

Example Request and Response

API Documentation

API Endpoint	Method
/api/generate/sdv3/imageToImage	POST

Request Header

Parameter	Description
Authentication	Use your API key to authentication requests to this App.

Request Body

The request should include a FormData object in the body with the following parameters:

Parameter	Type	Required	Description
image	File	Yes	Image used to initialize the diffusion process, in lieu of random noise.
prompt	string	Yes	The text description or prompt used to generate the image.
width	int	Yes	The desired pixel width for the generated image should be between 320 and 1536 pixels, in an increment divisible by 64.
height	int	Yes	The desired pixel height for the generated image should be between 320 and 1536 pixels, in an increment divisible by 64.
strength	int	Yes	Range: [0, 1] This parameter controls how much influence the image parameter has on the generated image. A value of 0 would yield an image that is identical to the input. A value of 1 would be as if you passed in no image at all.
model	string	No	Enum: sd3-large sd3-large-turbo sd3-medium Default: sd3-large The model to use for generation.
seed	init	No	Random noise seed (omit this option or use 0 for a random seed).
negative_prompt	string	No	Keywords of what you do not wish to see in the output image. This is an advanced feature.This parameter does not work with sd3-large-turbo.

Response Body

The response should include a JSON object in the body with the following parameters:

Parameter	Type	Description
code	int	Status Code, 0 for success callback, -1 for failure callback
message	string	Callback message, 'success' for success, failure reason for failure
data	object	Image Details

Image Details

Parameter	Type	Description
image	string	Return the base64 encoded image of the generated picture.
seed	int	The seed used as random noise for this generation.

Example Request

import requests
import base64
import os

image_path = './init_image.png'
with open(image_path, 'rb') as file:
    image_data = file.read()

payload = {
    'strength': 0.35,
    'prompt': 'black hair',
}
files = {'image': ('init_image.png', image_data)}

url = "https://www.aithriving.com/api/generate/sdv3/imageToImage"
headers = {'Authorization': "your-auth-token"}
response = requests.post(url, data=payload, files=files, headers=headers)

response_json = response.json()
if response_json.get('code') == 0:
    image_base64 = response_json['data']['image']
    image_bytes = base64.b64decode(image_base64)
    with open('./result.png', 'wb') as file:
        file.write(image_bytes)

Example Response

{
  "code": 0,
  "message": "success",
  "data": {
    "image": "base64 encoded image data",
    "seed": 1050625087
  }
}