Sign In
home
models
images
videos
posts
articles
bounties
tools
challenges
events
shop

Make a Stable Diffusion easy interface with python

MisterMR's Avatar
MisterMR
Gold Writer Badge
Feb 12, 2024
tool guide
python utilitycode
Make a Stable Diffusion easy interface with python

Objective

Make a python script with your own interface

Preface

I quite new in Python world and I am learning the language (I already kwon other languages) .

I you see mistake or you want to improve my code.. you are welcome.. write in the comments.

This is guide for people with some experience, I won't explain every single step (because it will be a book , there are too many).

Environment

For this test I will use:

Visual Studio Code (https://code.visualstudio.com/ ) it is a free light code editor from Microsoft that work in Windows, Linux and Mac.

  • Python Plugin (that will install when you start to create a python file in Visual Studio Code)

Check The API

Go to http://127.0.0.1:7860/docs

I want to use the API to generate images.

I will user this Json code to generate the images.

Graphics of my Tool - Gradio- https://www.gradio.app/

To write my interface I will use Gradio , which is the standard library used in Stable Diffusion

You can notice from the website.. with few lines of code you are able to generate a cool interface.

Code

After doing some test I wrote the code below

# is used for comments

You can notice below I use the link http://127.0.0.1:7860/sdapi/v1/txt2img for the API .

The data takes only 2 values "prompt" and "negative prompt" for the rest will use the default values. Of course you can change it.

# Import the libraries
import gradio as gr
import requests
import json
from PIL import Image
from io import BytesIO
import base64

# Define the function to call the API
def call_api(prompt, negative_prompt):
    # Define the URL of the API endpoint
    url = 'http://127.0.0.1:7860/sdapi/v1/txt2img'

    # Define the JSON data to send in the request
    data = {
        "prompt": prompt,
        "negative_prompt": negative_prompt,
        "styles": [
            "string"
        ],
        "seed": -1,
        "subseed": -1,
        # Include other fields as needed
    }

    # Convert the data to JSON format
    json_data = json.dumps(data)

    # Set the headers for the request
    headers = {'Content-Type': 'application/json'}

    # Send the POST request to the API
    response = requests.post(url, data=json_data, headers=headers)

    # Check if the request was successful (status code 200)
    if response.status_code == 200:
       # Decode the JSON response
        json_response = response.json()

        # Extract the base64 image data from the response
        image_data = json_response.get('images', [''])[0]

        # Decode the base64 image data
        image_bytes = base64.b64decode(image_data)

        # Open the image using PIL
        image = Image.open(BytesIO(image_bytes))

        # Display the image
        return image
    else:
        # Return an error message if the request was not successful
        return "Error:", response.status_code

# Create the Gradio interface
iface = gr.Interface(fn=call_api, 
                     inputs=[gr.inputs.Textbox(label="Prompt"),
                             gr.inputs.Textbox(label="Negative Prompt")],
                     outputs="image")

# Launch the interface
iface.launch(share=True)

Visual Studio Code

After download Visuali Studio Code from here https://code.visualstudio.com/download

For installation do the default settings, you can check the site https://code.visualstudio.com/ for more information.

You have to create a .py file and paste the code above.. Visual Studio will ask you to install the python plug-in.. when it done you will see the file in colors.

Run the code

now press Play and if everything is confifure correctly

You will see the http://127.0.0.1:7681 link below.

Going to the link

You will se an interface with 2 options and output.

If you press the submit button it will show the image

You need to know python a little bit, but this code is a good start if you want to create your own interface of run a script after the other.

When I will have time I would like to make a script in python that generate the images and remove automatically the background.

Something like what I am already doing with https://misterm.itch.io/mr-stable-diffusion-quick-sprite . (this app is written in C# , windows Form only for windows and calls the same APIs)

I hope you enjoy my article. If you have any question write in the comments.

5

Comments