app.py

import logging
import random
import warnings
import os
import gradio as gr
import numpy as np
import spaces
import torch
from diffusers import FluxControlNetModel
from diffusers.pipelines import FluxControlNetPipeline
from gradio_imageslider import ImageSlider
from PIL import Image
from huggingface_hub import snapshot_download

css = """
#col-container {
    margin: 0 auto;
    max-width: 512px;
}
"""

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


huggingface_token = os.getenv("HF_TOKEN")

model_path = snapshot_download(
    repo_id="black-forest-labs/FLUX.1-dev", 
    repo_type="model", 
    ignore_patterns=["*.md", "*..gitattributes"],
    local_dir="FLUX.1-dev",
    token=huggingface_token, # type a new token-id.
)


# Load pipeline
controlnet = FluxControlNetModel.from_pretrained(
    "jasperai/Flux.1-dev-Controlnet-Upscaler", torch_dtype=torch.bfloat16
).to(device)
pipe = FluxControlNetPipeline.from_pretrained(
    model_path, controlnet=controlnet, torch_dtype=torch.bfloat16
)
pipe.to(device)

MAX_SEED = 1000000
MAX_PIXEL_BUDGET = 1024 * 1024


def process_input(input_image, upscale_factor, **kwargs):
    w, h = input_image.size
    w_original, h_original = w, h
    aspect_ratio = w / h

    was_resized = False

    if w * h * upscale_factor**2 > MAX_PIXEL_BUDGET:
        warnings.warn(
            f"Requested output image is too large ({w * upscale_factor}x{h * upscale_factor}). Resizing to ({int(aspect_ratio * MAX_PIXEL_BUDGET ** 0.5 // upscale_factor), int(MAX_PIXEL_BUDGET ** 0.5 // aspect_ratio // upscale_factor)}) pixels."
        )
        gr.Info(
            f"Requested output image is too large ({w * upscale_factor}x{h * upscale_factor}). Resizing input to ({int(aspect_ratio * MAX_PIXEL_BUDGET ** 0.5 // upscale_factor), int(MAX_PIXEL_BUDGET ** 0.5 // aspect_ratio // upscale_factor)}) pixels budget."
        )
        input_image = input_image.resize(
            (
                int(aspect_ratio * MAX_PIXEL_BUDGET**0.5 // upscale_factor),
                int(MAX_PIXEL_BUDGET**0.5 // aspect_ratio // upscale_factor),
            )
        )
        was_resized = True

    # resize to multiple of 8
    w, h = input_image.size
    w = w - w % 8
    h = h - h % 8

    return input_image.resize((w, h)), w_original, h_original, was_resized


@spaces.GPU#(duration=42)
def infer(
    seed,
    randomize_seed,
    input_image,
    num_inference_steps,
    upscale_factor,
    controlnet_conditioning_scale,
    progress=gr.Progress(track_tqdm=True),
):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    true_input_image = input_image
    input_image, w_original, h_original, was_resized = process_input(
        input_image, upscale_factor
    )

    # rescale with upscale factor
    w, h = input_image.size
    control_image = input_image.resize((w * upscale_factor, h * upscale_factor))

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

    gr.Info("Upscaling image...")
    image = pipe(
        prompt="",
        control_image=control_image,
        controlnet_conditioning_scale=controlnet_conditioning_scale,
        num_inference_steps=num_inference_steps,
        guidance_scale=3.5,
        height=control_image.size[1],
        width=control_image.size[0],
        generator=generator,
    ).images[0]

    if was_resized:
        gr.Info(
            f"Resizing output image to targeted {w_original * upscale_factor}x{h_original * upscale_factor} size."
        )

    # resize to target desired size
    image = image.resize((w_original * upscale_factor, h_original * upscale_factor))
    image.save("output.jpg")
    # convert to numpy
    return [true_input_image, image, seed]



def create_snow_effect():
    # CSS 스타일 정의
    snow_css = """
    @keyframes snowfall {
        0% {
            transform: translateY(-10vh) translateX(0);
            opacity: 1;
        }
        100% {
            transform: translateY(100vh) translateX(100px);
            opacity: 0.3;
        }
    }
    .snowflake {
        position: fixed;
        color: white;
        font-size: 1.5em;
        user-select: none;
        z-index: 1000;
        pointer-events: none;
        animation: snowfall linear infinite;
    }
    """

    # JavaScript 코드 정의
    snow_js = """
    function createSnowflake() {
        const snowflake = document.createElement('div');
        snowflake.innerHTML = '❄';
        snowflake.className = 'snowflake';
        snowflake.style.left = Math.random() * 100 + 'vw';
        snowflake.style.animationDuration = Math.random() * 3 + 2 + 's';
        snowflake.style.opacity = Math.random();
        document.body.appendChild(snowflake);
        
        setTimeout(() => {
            snowflake.remove();
        }, 5000);
    }
    setInterval(createSnowflake, 200);
    """

    # CSS와 JavaScript를 결합한 HTML 
    snow_html = f"""
    <style>
        {snow_css}
    </style>
    <script>
        {snow_js}
    </script>
    """
    
    return gr.HTML(snow_html)


with gr.Blocks(theme="soft", css=css) as demo:

    gr.HTML(
        """
        <div class='container' style='display:flex; justify-content:center; gap:12px;'>
            <a href="https://huggingface.co/spaces/openfree/Best-AI" target="_blank">
                <img src="https://img.shields.io/static/v1?label=OpenFree&message=BEST%20AI%20Services&color=%230000ff&labelColor=%23000080&logo=huggingface&logoColor=%23ffa500&style=for-the-badge" alt="OpenFree badge">
            </a>
    
            <a href="https://discord.gg/openfreeai" target="_blank">
                <img src="https://img.shields.io/static/v1?label=Discord&message=Openfree%20AI&color=%230000ff&labelColor=%23800080&logo=discord&logoColor=white&style=for-the-badge" alt="Discord badge">
            </a>
        </div>
            """
    )
    
    create_snow_effect()    
    with gr.Row():
        run_button = gr.Button(value="Run")

    with gr.Row():
        with gr.Column(scale=4):
            input_im = gr.Image(label="Input Image", type="pil")
        with gr.Column(scale=1):
            num_inference_steps = gr.Slider(
                label="Number of Inference Steps",
                minimum=8,
                maximum=50,
                step=1,
                value=28,
            )
            upscale_factor = gr.Slider(
                label="Upscale Factor",
                minimum=1,
                maximum=4,
                step=1,
                value=4,
            )
            controlnet_conditioning_scale = gr.Slider(
                label="Controlnet Conditioning Scale",
                minimum=0.1,
                maximum=1.5,
                step=0.1,
                value=0.6,
            )
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=42,
            )

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

    with gr.Row():
        result = ImageSlider(label="Input / Output", type="pil", interactive=True)

    examples = gr.Examples(
        examples=[
            [42, False, "z1.webp", 28, 4, 0.6],
            [42, False, "z2.webp", 28, 4, 0.6],
 
        ],
        inputs=[
            seed,
            randomize_seed,
            input_im,
            num_inference_steps,
            upscale_factor,
            controlnet_conditioning_scale,
        ],
        fn=infer,
        outputs=result,
        cache_examples="lazy",
    )



    gr.on(
        [run_button.click],
        fn=infer,
        inputs=[
            seed,
            randomize_seed,
            input_im,
            num_inference_steps,
            upscale_factor,
            controlnet_conditioning_scale,
        ],
        outputs=result,
        show_api=False,
        # show_progress="minimal",
    )

demo.queue().launch(share=False, show_api=False)