from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
from diffusers.utils import load_image
import numpy as np
import torch

import cv2
from PIL import Image


device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device


# load control net and stable diffusion v1-5
base_model_path = "runwayml/stable-diffusion-v1-5"
controlnet_path = "LuyangZ/controlnet_Neufert4_64_100"
controlnet = ControlNetModel.from_pretrained(controlnet_path, use_safetensors=True)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
    base_model_path, controlnet=controlnet, use_safetensors=True)

# speed up diffusion process with faster scheduler and memory optimization
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to(device)
# pipe.set_progress_bar_config(disable=True)


# generate image
control_image = load_image("C:/Users/luyan/diffusers/examples/controlnet/Test/1030_4465_8e4734b920a2be9f0e7d85b734b7fa7e.png")



# speed up diffusion process with faster scheduler and memory optimization
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)

# generate image
control_image = load_image("C:/Users/luyan/diffusers/examples/controlnet/Test/2179_9871_432b1fbf16d04cd8371cd9ece543cb28.png")

# pipe = pipe.to(device)
# generator = torch.manual_seed(0)
# generator = torch.Generator(device=device).manual_seed(999)
# generator = None

# images = []
# for i in range(5):
#     image = pipe(
#         "floor plan,2 bedrooms", num_inference_steps=100, image=control_image
#     ).images[0]
#     images.append(image)

generator = torch.Generator(device=device).manual_seed(333)
images = []
for i in range(5):
    image = pipe(
        "floor plan,2 bedrooms", num_inference_steps=20, generator=generator, image=control_image
    ).images[0]
    images.append(image)


def make_grid(images, size=512):
    """Given a list of PIL images, stack them together into a line for easy viewing"""
    output_im = Image.new("RGB", (size * len(images), size))
    for i, im in enumerate(images):
        output_im.paste(im.resize((size, size)), (i * size, 0))
    return output_im



make_grid(images, size=512)