Fork of stabilityai/stable-diffusion-2-inpainting

Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion with 🧨Diffusers blog.

For more information about the model, license and limitations check the original model card at stabilityai/stable-diffusion-2-inpainting.

This repository implements a custom handler task for text-guided-to-image-inpainting for 🤗 Inference Endpoints. The code for the customized pipeline is in the handler.py.

There is also a notebook included, on how to create the handler.py

expected Request payload

{
    "inputs": "A prompt used for image generation",
    "image" : "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAABGdBTUEAALGPC",
    "mask_image": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAAABGdBTUEAALGPC",
}

below is an example on how to run a request using Python and requests.

Run Request

import json
from typing import List
import requests as r
import base64
from PIL import Image
from io import BytesIO

ENDPOINT_URL = ""
HF_TOKEN = ""

# helper image utils
def encode_image(image_path):
  with open(image_path, "rb") as i:
    b64 = base64.b64encode(i.read())
  return b64.decode("utf-8")


def predict(prompt, image, mask_image):
    image = encode_image(image)
    mask_image = encode_image(mask_image)

    # prepare sample payload
    request = {"inputs": prompt, "image": image, "mask_image": mask_image}
    # headers
    headers = {
        "Authorization": f"Bearer {HF_TOKEN}",
        "Content-Type": "application/json",
        "Accept": "image/png" # important to get an image back
    }

    response = r.post(ENDPOINT_URL, headers=headers, json=payload)
    img = Image.open(BytesIO(response.content))
    return img

prediction = predict(
    prompt="Face of a bengal cat, high resolution, sitting on a park bench",
    image="dog.png",
    mask_image="mask_dog.png"
)

expected output