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

# Ensure sentencepiece is installed in your environment
try:
    import sentencepiece
except ImportError:
    raise ImportError("The 'sentencepiece' library is required but not installed. Please add it to your environment.")

# Set the device and dtype
dtype = torch.float16
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the diffusion pipeline
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=dtype).to(device)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048

def infer(prompt, negative_prompt, seed, randomize_seed, width, height, num_inference_steps, guidance_scale, progress=gr.Progress(track_tqdm=True)):
    start_time = time.time()

    if width > MAX_IMAGE_SIZE or height > MAX_IMAGE_SIZE:
        raise ValueError("Image size exceeds the maximum allowed dimensions.")

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    generator = torch.Generator(device=device).manual_seed(seed)

    try:
        image = pipe(
            prompt=prompt,
            negative_prompt=negative_prompt,
            width=width,
            height=height,
            num_inference_steps=num_inference_steps,
            generator=generator,
            guidance_scale=guidance_scale
        ).images[0]
    except Exception as e:
        print(f"Error generating image: {e}")
        return None, seed, f"Error: {str(e)}"

    if time.time() - start_time > 60:
        return None, seed, "Image generation took too long and was cancelled."

    return image, seed, None

examples = [
    ["a tiny astronaut hatching from an egg on the moon", "blurry, low quality"],
    ["a cat holding a sign that says hello world", "dog, text, writing"],
    ["an anime illustration of a wiener schnitzel", "realistic, photograph"],
]

with gr.Blocks(theme=gr.themes.Soft()) as demo:
    gr.Markdown("""
    # Custom Image Creator
    12B param rectified flow transformer distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/) for 4 step generation
    [[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1)]
    """)

    with gr.Row():
        with gr.Column(scale=2):
            prompt = gr.Textbox(
                label="Prompt",
                placeholder="Enter your prompt",
                lines=3
            )
            negative_prompt = gr.Textbox(
                label="Negative Prompt",
                placeholder="Enter things to avoid in the image",
                lines=2
            )
            run_button = gr.Button("Generate Image", variant="primary")

        with gr.Column(scale=2):
            result = gr.Image(label="Generated Image")
            seed_output = gr.Number(label="Seed Used")

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

        with gr.Row():
            num_inference_steps = gr.Slider(label="Number of inference steps", minimum=1, maximum=50, step=1, value=4)
            guidance_scale = gr.Slider(label="Guidance Scale", minimum=0.0, maximum=20.0, step=0.5, value=7.5)

    gr.Examples(
        examples=examples,
        inputs=[prompt, negative_prompt],
        outputs=[result, seed_output],
        fn=infer,
        cache_examples=True
    )

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

    gr.Markdown("""
    ## Save Your Image
    Right-click on the generated image and select 'Save image as' to download it.
    """)

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