import gradio as gr
import numpy as np
import random
import spaces
import torch
from diffusers.pipelines.prx import PRXPipeline

dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the PRX pipeline with the distilled DC-AE model
pipe = PRXPipeline.from_pretrained(
    "Photoroom/prx-512-t2i-dc-ae-sft-distilled",
    torch_dtype=dtype
)
pipe = pipe.to(device)

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


@spaces.GPU()
def infer(
    prompt,
    seed=42,
    randomize_seed=False,
    width=512,
    height=512,
    num_inference_steps=8,
    guidance_scale=1.0,
    progress=gr.Progress(track_tqdm=True)
):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

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

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

    return image, seed


examples = [
    "A front-facing portrait of a lion on the golden savanna at sunset.",
    "A serene mountain landscape with a crystal clear lake reflecting snow-capped peaks.",
    "A futuristic cityscape at night with neon lights and flying vehicles.",
    "A whimsical illustration of a cat wearing a wizard hat and casting spells.",
    "A cozy coffee shop interior with warm lighting and plants on the windowsill.",
]

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("# PRX Image Generator")
        gr.Markdown(
            "Generate high-quality images using the PRX distilled model with DC-AE compression. "
            "This model uses 8-step distillation for fast inference with cfg=1.0. "
            "Works best with less detailed prompts in natural language."
        )

        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)

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

        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=512,
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,
                )

            with gr.Row():
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=28,
                    step=1,
                    value=8,
                )

                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=5.0,
                    step=0.1,
                    value=1.0,
                )

        gr.Examples(
            examples=examples,
            fn=infer,
            inputs=[prompt],
            outputs=[result, seed],
            cache_examples="lazy"
        )

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

demo.launch()