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 gradio as gr 

controlnet_conditioning_scale = 0.5  # recommended for good generalization

controlnet = ControlNetModel.from_pretrained(
    "briaai/ControlNet-Canny",
    torch_dtype=torch.float16
)

pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
    "briaai/BRIA-2.0",
    controlnet=controlnet,
    vae=vae,
    torch_dtype=torch.float16,
)
pipe.enable_model_cpu_offload()

low_threshold = 100
high_threshold = 200

def get_canny_filter(image):
    
    if not isinstance(image, np.ndarray):
        image = np.array(image) 
        
    image = cv2.Canny(image, low_threshold, high_threshold)
    image = image[:, :, None]
    image = np.concatenate([image, image, image], axis=2)
    canny_image = Image.fromarray(image)
    return canny_image

def process(input_image, prompt):
    canny_image = get_canny_filter(input_image)
    images = pipe(
        prompt,image=canny_image, controlnet_conditioning_scale=controlnet_conditioning_scale,
        ).images

    return [canny_image,images[0]]
    
block = gr.Blocks().queue()

with block:
    gr.Markdown("## BRIA 2.0 ControlNet Canny")
    gr.HTML('''
     <p style="margin-bottom: 10px; font-size: 94%">
                This is a demo for BRIA 2.0 ControlNet Canny, a fully legal and safe T2I model. 
              </p>
              ''')
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            prompt = gr.Textbox(label="Prompt")
            run_button = gr.Button(label="Run")
            
            
        with gr.Column():
            result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery").style(grid_cols=2, height='auto')
    ips = [input_image, prompt]
    run_button.click(fn=process, inputs=ips, outputs=[result_gallery])

block.launch(debug = True)