import gradio as gr
import numpy as np
import torch
from diffusers import DiffusionPipeline

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/sdxl-turbo"  # Текущая/последняя загруженная модель
if torch.cuda.is_available():
    torch_dtype = torch.float16
else:
    torch_dtype = torch.float32

# Изначально загружаем модель по умолчанию
pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
pipe = pipe.to(device)

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

def infer(
    model,
    prompt,
    negative_prompt,
    seed,
    width,
    height,
    guidance_scale,
    num_inference_steps,
    progress=gr.Progress(track_tqdm=True),
):
    global model_repo_id, pipe
    
    # Проверяем, нужно ли менять модель
    if model != model_repo_id:
        try:
            # Пробуем загрузить новую модель
            new_pipe = DiffusionPipeline.from_pretrained(model, torch_dtype=torch_dtype)
            new_pipe = new_pipe.to(device)
            # Если успешно, то обновляем pipe и модель
            pipe = new_pipe
            model_repo_id = model
        except Exception as e:
            raise gr.Error(f"Не удалось загрузить модель {model}. Ошибка: {str(e)}")

    generator = torch.Generator(device=device).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 = [
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    "An astronaut riding a green horse",
    "A delicious ceviche cheesecake slice",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # Text-to-Image App")

        # Вместо выпадающего списка — текстовое поле для ввода модели
        model = gr.Textbox(
            label="Model name or path",
            value="stabilityai/sdxl-turbo",  # Значение по умолчанию
            interactive=True
        )
        
        prompt = gr.Text(
            label="Prompt",
            show_label=False,
            max_lines=1,
            placeholder="Enter your prompt",
            container=False,
        )
        
        negative_prompt = gr.Text(
            label="Negative prompt",
            max_lines=1,
            placeholder="Enter a negative prompt",
            visible=True,
        )
        
        seed = gr.Slider(
            label="Seed",
            minimum=0,
            maximum=MAX_SEED,
            step=1,
            value=42,
        )

        guidance_scale = gr.Slider(
            label="Guidance scale",
            minimum=0.0,
            maximum=10.0,
            step=0.1,
            value=7.0,
        )

        num_inference_steps = gr.Slider(
            label="Number of inference steps",
            minimum=1,
            maximum=50,
            step=1,
            value=20,
        )
        
        run_button = gr.Button("Run", scale=0, variant="primary")
        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )
                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )

        gr.Examples(examples=examples, inputs=[prompt])

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

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