import gradio as gr
import numpy as np
import random
import logging
import sys

# 设置日志记录
logging.basicConfig(level=logging.INFO, 
                    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
                    stream=sys.stdout)
logger = logging.getLogger(__name__)

# 修复 Gradio JSON Schema 错误
try:
    import gradio_client.utils
    # 添加对布尔值的检查
    original_get_type = gradio_client.utils.get_type
    def patched_get_type(schema):
        if isinstance(schema, bool):
            return "bool"
        if not isinstance(schema, dict):
            return "any"
        return original_get_type(schema)
    gradio_client.utils.get_type = patched_get_type
    logger.info("Successfully patched Gradio JSON schema processing")
except Exception as e:
    logger.error(f"Failed to patch Gradio: {str(e)}")

# import spaces #[uncomment to use ZeroGPU]
from diffusers import DiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use

logger.info(f"Using device: {device}")
logger.info(f"Loading model: {model_repo_id}")

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

try:
    pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
    pipe = pipe.to(device)
    logger.info("Model loaded successfully")
except Exception as e:
    logger.error(f"Error loading model: {str(e)}")
    raise

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

# @spaces.GPU #[uncomment to use ZeroGPU]
def infer(
    prompt,
    negative_prompt,
    seed,
    randomize_seed,
    width,
    height,
    guidance_scale,
    num_inference_steps,
    progress=gr.Progress(track_tqdm=True),
):
    try:
        logger.info(f"Processing prompt: {prompt}")
        
        if randomize_seed:
            seed = random.randint(0, MAX_SEED)
            
        logger.info(f"Using seed: {seed}, width: {width}, height: {height}")
        
        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]

        logger.info("Image generation successful")
        return image, seed
    except Exception as e:
        logger.error(f"Error in inference: {str(e)}")
        raise gr.Error(f"Error generating image: {str(e)}")

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;
}
"""

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

            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, 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,
                    placeholder="Enter a negative prompt",
                    visible=True, # 改为可见
                )

                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=1024,
                    )

                    height = gr.Slider(
                        label="Height",
                        minimum=256,
                        maximum=MAX_IMAGE_SIZE,
                        step=32,
                        value=1024,
                    )

                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=50,
                        step=1,
                        value=2,
                    )

            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],
        )
    
    logger.info("Gradio interface created successfully")
except Exception as e:
    logger.error(f"Error creating Gradio interface: {str(e)}")
    raise

if __name__ == "__main__":
    try:
        logger.info("Starting Gradio app")
        demo.launch()
    except Exception as e:
        logger.error(f"Error launching app: {str(e)}")