import base64

import requests

HF_TOKEN = 'hf_xxxxxxxxxxxxx'
API_ENDPOINT = 'https://xxxxxxxxxxx.us-east-1.aws.endpoints.huggingface.cloud'

def load_image(path):
    try:
        with open(path, 'rb') as file:
            return file.read()
    except FileNotFoundError as error:
        print('Error reading image:', error)


def get_b64_image(path):
    image_buffer = load_image(path)
    if image_buffer:
        return base64.b64encode(image_buffer).decode('utf-8')


def process_images(original_image_path, mask_image_path, result_path, prompt, width, height):
    original_b64 = get_b64_image(original_image_path)
    mask_b64 = get_b64_image(mask_image_path)

    if not original_b64 or not mask_b64:
        return

    body = {
        'inputs': prompt,
        'image': original_b64,
        'mask_image': mask_b64,
        'width': width,
        'height': height
    }

    headers = {
        'Authorization': f'Bearer {HF_TOKEN}',
        'Content-Type': 'application/json',
        'Accept': 'image/png'
    }

    response = requests.post(
        API_ENDPOINT,
        json=body,
        headers=headers
    )
    blob = response.content

    save_image(blob, result_path)


def save_image(blob, file_path):
    with open(file_path, 'wb') as file:
        file.write(blob)
    print('File saved successfully!')


if __name__ == '__main__':
    original_image_path = 'images/original.png'
    mask_image_path = 'images/mask.png'
    result_path = 'images/result.png'
    process_images(original_image_path, mask_image_path, result_path, 'cyberpunk mona lisa', 512, 768)

1. Let's install `diffusers` and related packages:

2. Run code:
```python
import torch
import os
from diffusers.utils import load_image
from PIL import Image
import numpy as np
from diffusers import (
    ControlNetModel,
    StableDiffusionControlNetPipeline,
    UniPCMultistepScheduler,
)
checkpoint = "lllyasviel/control_v11p_sd15_inpaint"
original_image = load_image(
    "https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint/resolve/main/images/original.png"
)
mask_image = load_image(
    "https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint/resolve/main/images/mask.png"
)

def make_inpaint_condition(image, image_mask):
    image = np.array(image.convert("RGB")).astype(np.float32) / 255.0
    image_mask = np.array(image_mask.convert("L"))
    assert image.shape[0:1] == image_mask.shape[0:1], "image and image_mask must have the same image size"
    image[image_mask < 128] = -1.0 # set as masked pixel 
    image = np.expand_dims(image, 0).transpose(0, 3, 1, 2)
    image = torch.from_numpy(image)
    return image

control_image = make_inpaint_condition(original_image, mask_image)
prompt = "best quality"
negative_prompt="lowres, bad anatomy, bad hands, cropped, worst quality"
controlnet = ControlNetModel.from_pretrained(checkpoint, torch_dtype=torch.float16)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()
generator = torch.manual_seed(2)
image = pipe(prompt, negative_prompt=negative_prompt, num_inference_steps=30, 
             generator=generator, image=control_image).images[0]
image.save('images/output.png')