models/philschmid/stable-diffusion-2-inpainting-endpoint/handler.py

from typing import  Dict, List, Any
import torch
from diffusers import DPMSolverMultistepScheduler, StableDiffusionInpaintPipeline
from PIL import Image
import base64
from io import BytesIO


# set device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

if device.type != 'cuda':
    raise ValueError("need to run on GPU")

class EndpointHandler():
    def __init__(self, path=""):
        # load StableDiffusionInpaintPipeline pipeline
        self.pipe = StableDiffusionInpaintPipeline.from_pretrained(path, torch_dtype=torch.float16)
        # use DPMSolverMultistepScheduler
        self.pipe.scheduler = DPMSolverMultistepScheduler.from_config(self.pipe.scheduler.config)
        # move to device        
        self.pipe = self.pipe.to(device)


    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
        """
        :param data: A dictionary contains `inputs` and optional `image` field.
        :return: A dictionary with `image` field contains image in base64.
        """
        inputs = data.pop("inputs", data)
        encoded_image = data.pop("image", None)
        encoded_mask_image = data.pop("mask_image", None)
        
        # hyperparamters
        num_inference_steps = data.pop("num_inference_steps", 25)
        guidance_scale = data.pop("guidance_scale", 7.5)
        negative_prompt = data.pop("negative_prompt", None)
        height = data.pop("height", None)
        width = data.pop("width", None)
        
        # process image
        if encoded_image is not None and encoded_mask_image is not None:
            image = self.decode_base64_image(encoded_image)
            mask_image = self.decode_base64_image(encoded_mask_image)
        else:
            image = None
            mask_image = None 
        
        # run inference pipeline
        out = self.pipe(inputs, 
                        image=image,             
                        mask_image=mask_image,             
                        num_inference_steps=num_inference_steps,
                        guidance_scale=guidance_scale,
                        num_images_per_prompt=1,
                        negative_prompt=negative_prompt,
                        height=height,
                        width=width
        )
            
        # return first generate PIL image
        return out.images[0]
    
    # helper to decode input image
    def decode_base64_image(self, image_string):
        base64_image = base64.b64decode(image_string)
        buffer = BytesIO(base64_image)
        image = Image.open(buffer)
        return image