import gradio as gr
import numpy as np
import random
from diffusers import DiffusionPipeline
import torch
from PIL import Image

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

base_model = 'stabilityai/stable-diffusion-2' 
prj_path = "bayndrysf/dreambooth-project-style"


if torch.cuda.is_available():
    torch.cuda.max_memory_allocated(device=device)
    pipe = DiffusionPipeline.from_pretrained(base_model)
    pipe.enable_xformers_memory_efficient_attention()
    pipe.to(device);
    pipe.load_lora_weights(prj_path, weight_name="pytorch_lora_weights.safetensors")
else: 
    pipe = DiffusionPipeline.from_pretrained(base_model)
    pipe.to(device);
    pipe.load_lora_weights(prj_path, weight_name="pytorch_lora_weights.safetensors")

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024



def image_grid(imgs, rows, cols, resize=256):
    assert len(imgs) == rows * cols

    if resize is not None:
        imgs = [img.resize((resize, resize)) for img in imgs]

    w, h = imgs[0].size
    grid_w, grid_h = cols * w, rows * h
    grid = Image.new("RGB", size=(grid_w, grid_h))

    for i, img in enumerate(imgs):
        x = i % cols * w
        y = i // cols * h
        grid.paste(img, box=(x, y))

    return grid


MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024


def generate_image(prompt):
    image = pipe(prompt=prompt, num_inference_steps=20, num_images_per_prompt = 1)
    return image_grid(image.images, 1, 1, 1024)



def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
    image = generate_image(prompt)
    return image

examples = [
    "A whirling dervish performing in a historic Istanbul courtyard, captured in the iconic style of Ara Güler.",
    "An elderly man sipping tea at a street café in Istanbul, captured in the iconic style of Ara Güler.",
    "A group of friends enjoying a ferry ride on the Bosphorus, captured in the iconic style of Ara Güler.",
]

css="""
#col-container {
    margin: 0 auto;
    max-width: 520px;
}
"""

if torch.cuda.is_available():
    power_device = "GPU"
else:
    power_device = "CPU"

with gr.Blocks(css=css) as demo:
    
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"""
        # Ara Güler's Istanbul: Image Generation with Stable Diffusion
        Currently running on {power_device}.
        """)
        
        with gr.Row():
            
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )
            
            run_button = gr.Button("Run", scale=0)
        
        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                visible=False,
            )
            
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )
            
            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
            
            with gr.Row():
                
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,
                )
                
                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,
                )
            
            with gr.Row():
                
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=10.0,
                    step=0.1,
                    value=0.0,
                )
                
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=12,
                    step=1,
                    value=2,
                )
        
        gr.Examples(
            examples = examples,
            inputs = [prompt]
        )

    run_button.click(
        fn = infer,
        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
        outputs = [result]
    )

demo.queue().launch()