Use Python script to automate Stable Diffusion WebUI img2img process with Roop extension enabled

[shivanraptor]

I would like to create a Python script to automate Stable Diffusion WebUI img2img process with Roop extension enabled.

Input:

• a source image for img2img
• a reference image for Roop extension

Output:

• an image, or a series of images in a batch

Here is my attempt (given that SD WebUI is already running at http://127.0.0.1:7860:

import json
import base64
import requests
import os
from tqdm import tqdm
import time

stdip = 'http://127.0.0.1:7860' # Default running on localhost
filefolderpath = '/home/myusername/automatic1111/outputdata/' # Directory to store images, modify images to change this. Output images are also in this directory. The directory should contain image and mask folders

def submit_post(url: str, data: dict):
    return requests.post(url, data=json.dumps(data), timeout=10)

def image_to_base64(image_path):
    with open(image_path, "rb") as image_file:
    encoded_string = base64.b64encode(image_file.read())
    base64_string = encoded_string.decode("utf-8")
    return base64_string

def save_encoded_image(b64_image, output_path):
    # Check if file exists, create if it doesn't exist
    if not os.path.exists(output_path):
        open(output_path, 'wb').close()

    # Open file in binary mode     
    with open(output_path, 'wb') as f:
        f.write(base64.b64decode(b64_image))
        f.flush()
        f.close()
    if name == 'main':
        img2img_url = stdip + '/sdapi/v1/img2img'

    for root, dirs, files in os.walk(filefolderpath + '/image/'):
        for file_name in files:
            if os.path.exists(filefolderpath + '/mask/' + file_name):
                data = {
                    "init_images": [image_to_base64(filefolderpath + '/image/' + file_name)], # Original image address
                    "denoising_strength": 0.45, # Range 0-1, smaller value closer to original image. Larger value more likely to let imagination fly
                    "image_cfg_scale": 0, # I've never seen this either, don't know what it is
                    "mask": image_to_base64(filefolderpath + '/mask/' + file_name), # Mask image address
                    "mask_blur": 5, # I also forgot what this parameter is, it seems to control the strength of feathering the mask
                    "masked content":"original", # I'm not sure if this parameter is correct, maybe need to delete the whole key-value pair, keep it for now
                    "inpainting_mask_invert": 1, # Probably controls what color the masked area is. No need to change, now this state is opaque part black redraw, white no operation
                    "initial_noise_multiplier": 0, # Initial noise, I feel the bigger it is, the more unrelated to the original image. Also no need to change
                    #"prompt": "healthy right eye,healthy left eye,white conjunctiva,both eyes are the same size,eyes are sparking,Asian,hypernet:eye_surgery_predictionv3:1", # Positive words, no need to change
                    "prompt": "healthy right eye,healthy left eye,white conjunctiva,both eyes are the same size,eyes are sparking,Asian,", # Positive words, no need to change
                    "negative_prompt": "bad right eye,bad left eye,bad eyes,ugly face,blurry,simple", # Negative words, also no need to change
                    "styles": [], # I've never controlled this parameter, so no need to change if not used
                    "seed": -1, # Initial seed. I feel images with the same seed are similar but not identical. -1 is random
                    "subseed": -1, # Subseed
                    "subseed_strength": 0, # Strength of subseed above
                    "batch_size": 1, # How many images generated each time. Default is 1 here, maybe 4090 can be set bigger?
                    "n_iter": 1, # "n_iter" is usually used to control number of iterations, but I haven't tried it, so just set to 1
                    "steps": 70, # Number of runs, this value can be fine tuned, converging when too high, max 150 in webui, maybe can go higher here?
                    "cfg_scale": 7, # Influence of prompt text on image, usually 5-15, max 30 in webui, can fine tune
                    "width": 848, # Width
                    "height": 544, # Height
                    "restore_faces": False, # Whether to correct faces, for 3D, test later if open or not. Suggest False for now
                    "tiling": False, # Tiling, meaning left and right edges match, top and bottom match. Usually False
                    "eta": 0, # "eta" is a common parameter for controlling learning rate or step size in ML algorithms. But I don't know what it does for image generation, so just set to 0
                    "script_args": [], # Parameters I haven't tried, keep this empty list
                    "sampler_index": "DPM++ 2M Karras", # Sampling method, recommend DPM++ 2M Karras, good quality and fast. Can fine tune
                    "resize_mode": 1, # Resize mode, stretch, crop, pad, scale (upsample latent), recommend crop, don't know which one 1 refers to here, can reselect later
                    "inpainting_fill": 1, # Don't know, keep all 3 inpaint params unchanged
                    "inpaint_full_res": True, # Don't know, keep all 3 inpaint params unchanged
                    "inpaint_full_res_padding": 4, # Don't know, keep all 3 inpaint params unchanged
                    "override_settings": {"sd_model_checkpoint": "photon_v1.safetensors",},
                    "hypernetwork_model": ["dic_demosaicing.pt"],
                    "script_args": [0,True,True,"hypernetwork_model","dic_demosaicing.pt",1,1],
                    "sd_vae":"Automatic"
                }

response = submit_post(img2img_url, data)
save_image_path = filefolderpath+ file_name
save_encoded_image(response.json()['images'][0], save_image_path)

But how can I set the Roop extension parameters (input image and other settings) in the script? Thanks.

[freeshard]

Add Roop params to the data dictionary under the key "roop_extension" and make sure to adjust the values of "roop_reference_images", "roop_extension_strength" and "roop_extension_blur" according to your requirements before making the POST request, assuming you have Roop reference images in the specified directory (filefolderpath + '/roop_reference/')