app.py

import gradio 
from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
from diffusers.utils import load_image
from PIL import Image
import torch
import numpy as np
import cv2
import os 

controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-canny-sdxl-1.0",
    torch_dtype=torch.float16
)
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    controlnet=controlnet,
    vae=vae,
    torch_dtype=torch.float16,
)
pipe.enable_model_cpu_offload()

def infer(image_in):
    prompt = "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting"
    negative_prompt = 'low quality, bad quality, sketches'

    image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png")

    controlnet_conditioning_scale = 0.5  # recommended for good generalization



    image = np.array(image)
    image = cv2.Canny(image, 100, 200)
    image = image[:, :, None]
    image = np.concatenate([image, image, image], axis=2)
    image = Image.fromarray(image)

    images = pipe(
        prompt, negative_prompt=negative_prompt, image=image, controlnet_conditioning_scale=controlnet_conditioning_scale,
        ).images

    images[0].save(f"hug_lab.png")

with gr.Blocks() as demo:
    with gr.Column():
        image_in = gr.Image(source="upload", type="filepath")
        prompt = gr.Textbox(label="Prompt")
        submit_btn = gr.Button("Submit")
        result = gr.Image(label="Result")

    submit_btn.click(
        fn = infer,
        inputs = [image_in, prompt],
        outputs = [result]
    )

demo.queue().launch()