import gradio as gr
import numpy as np
import random


from diffusers import DiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/sdxl-turbo" 

if torch.cuda.is_available():
    torch_dtype = torch.float16
else:
    torch_dtype = torch.float32

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
pipe = pipe.to(device)

MAX_SEED = 666
MAX_IMAGE_SIZE = 1280



def infer(
    prompt,
    negative_prompt,
    seed,
    randomize_seed,
    width,
    height,
    guidance_scale,
    num_inference_steps,
    progress=gr.Progress(track_tqdm=True),
):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

    generator = torch.Generator().manual_seed(seed)

    image = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).images[0]

    return image, seed


examples = [
    "two soldiers wearing gas masks, clad in military digital camo jungle fatigues, djing on futuristic mixers, synth, mpcs. location jungle rave.",
    "in a dark jungle, a wizard and a warlock face each other as in a epic battle,  casting spells to operate vintage machines like mixers, synths, turntable.",
    "A mesmerizing, bioluminescent DNA double helix, illuminated by a kaleidoscope of vibrant, pulsating light beams from colorful lasers, suspended in a futuristic, setting.",
    "little rasta bunny dancing at a rave in the Jungle. cute street art, cartoon style.",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 600px;
}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # ߙߛߕ-ߊ - ϕ - |θ_θ| - ϕ -  ")

        with gr.Row():
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1.3,
                placeholder="Enter your prompt",
                container=False,
            )

            run_button = gr.Button("Run", scale=0, variant="primary")

        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1.3,
                placeholder="Enter a negative prompt",
                visible=False,
            )

            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1.6,
                value=0.3,
            )

            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)

            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=600,
                    maximum=MAX_IMAGE_SIZE,
                    step=1.3,
                    value=600,  
                )

                height = gr.Slider(
                    label="Height",
                    minimum=400,
                    maximum=MAX_IMAGE_SIZE,
                    step=1.6,
                    value=400, 
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=2,
                    step=0.6,
                    value=0.3, 
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=6,
                    step=3,
                    value=3,  
                )

        gr.Examples(examples=examples, inputs=[prompt])
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            prompt,
            negative_prompt,
            seed,
            randomize_seed,
            width,
            height,
            guidance_scale,
            num_inference_steps,
        ],
        outputs=[result, seed],
    )

if __name__ == "__main__":
    demo.launch()