#!/usr/bin/env python

import os
import random
import uuid

import gradio as gr
import numpy as np
from PIL import Image
import spaces
from typing import Tuple
import torch
from diffusers import StableCascadeDecoderPipeline, StableCascadePriorPipeline

DESCRIPTION = """ """

def save_image(img):
    unique_name = str(uuid.uuid4()) + ".png"
    img.save(unique_name)
    return unique_name

def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    return seed

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

if not torch.cuda.is_available():
    DESCRIPTION += "\n<p>Running on CPU, This may not work on CPU.</p>"

USE_TORCH_COMPILE = 0
ENABLE_CPU_OFFLOAD = 0

style_list = [

    {
    "name": "3840 x 2160",
    "prompt": "hyper-realistic 8K image of {prompt} . ultra-detailed, lifelike, high-resolution, sharp, vibrant colors, photorealistic",
    "negative_prompt": "cartoonish, low resolution, blurry, simplistic, abstract, deformed, ugly",
    },
    {
    "name": "2560 × 1440",
    "prompt": "hyper-realistic 4K image of {prompt} . ultra-detailed, lifelike, high-resolution, sharp, vibrant colors, photorealistic",
    "negative_prompt": "cartoonish, low resolution, blurry, simplistic, abstract, deformed, ugly",
    },
    {
    "name": "HDR",
    "prompt": "HDR photo of {prompt} . high dynamic range, vivid colors, sharp contrast, realistic, detailed, high resolution, professional",
    "negative_prompt": "dull, low contrast, blurry, unrealistic, cartoonish, ugly, deformed",
    },
    {
        "name": "Cinematic",
        "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
    },
    {
        "name": "Photo",
        "prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed",
        "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly",
    },
    {
        "name": "Anime",
        "prompt": "anime artwork {prompt} . anime style, key visual, vibrant, studio anime,  highly detailed",
        "negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast",
    },
    {
        "name": "Manga",
        "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style",
        "negative_prompt": "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, Western comic style",
    },
    {
        "name": "Digital",
        "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed",
        "negative_prompt": "photo, photorealistic, realism, ugly",
    },
    {
        "name": "3D Model",
        "prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting",
        "negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting",
    },

    {
        "name": "(No style)",
        "prompt": "{prompt}",
        "negative_prompt": "",
    },
]

styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
STYLE_NAMES = list(styles.keys())
DEFAULT_STYLE_NAME = "3840 x 2160"

def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str, str]:
    p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
    if not negative:
        negative = ""
    return p.replace("{prompt}", positive), n + negative

@spaces.GPU(enable_queue=True)
def stab(
    prompt: str,
    negative_prompt: str = "",
    style: str = DEFAULT_STYLE_NAME,
    use_negative_prompt: bool = False,
    num_inference_steps: int = 30,
    num_images_per_prompt: int = 2,
    seed: int = 0,
    width: int = 1024,
    height: int = 1024,
    guidance_scale: float = 3,
    randomize_seed: bool = False,
    progress=gr.Progress(track_tqdm=True),
):
    seed = int(randomize_seed_fn(seed, randomize_seed))

    if not use_negative_prompt:
        negative_prompt = ""
    prompt, negative_prompt = apply_style(style, prompt, negative_prompt)

    prior = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", variant="bf16", torch_dtype=torch.bfloat16)
    decoder = StableCascadeDecoderPipeline.from_pretrained("stabilityai/stable-cascade", variant="bf16", torch_dtype=torch.float16)

    prior.enable_model_cpu_offload()
    prior_output = prior(
        prompt=prompt,
        height=height,
        width=width,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_images_per_prompt=num_images_per_prompt,
        num_inference_steps=num_inference_steps
    )

    decoder.enable_model_cpu_offload()
    images = decoder(
        image_embeddings=prior_output.image_embeddings.to(torch.float16),
        prompt=prompt,
        negative_prompt=negative_prompt,
        guidance_scale=0.0,
        output_type="pil",
        num_inference_steps=10
    ).images

    image_paths = [save_image(img) for img in images]
    print(image_paths)
    return image_paths, seed

examples = [
    "a time traveler meeting their past self in a Victorian-era street",
    "a carnival at night with colorful lights and whimsical rides",
    "a Viking ship sailing through a storm with lightning in the background",
    "a cyberpunk street market with neon lights and holographic signs",
    "a space station orbiting a distant planet, serving as a hub for intergalactic travelers",
    "a surreal landscape with floating islands and waterfalls cascading into the void"
]

css = '''
.gradio-container{max-width: 560px !important}
h1{text-align:center}
footer {
    visibility: hidden
}
'''

with gr.Blocks(css=css, theme="xiaobaiyuan/theme_brief") as demo:
    gr.Markdown(DESCRIPTION)
    gr.DuplicateButton(
        value="Duplicate Space for private use",
        elem_id="duplicate-button",
        visible=False,
    )

    with gr.Group():
        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")
        result = gr.Gallery(label="Result", columns=1, preview=True)
    with gr.Accordion("Advanced options", open=False):
        use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True, visible=True)
        negative_prompt = gr.Text(
            label="Negative prompt",
            max_lines=1,
            placeholder="Enter a negative prompt",
            value="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW",
            visible=True,
        )
        with gr.Row():
            num_inference_steps = gr.Slider(
                label="Steps",
                minimum=10,
                maximum=60,
                step=1,
                value=30,
            )
        with gr.Row():
            num_images_per_prompt = gr.Slider(
                label="Images",
                minimum=1,
                maximum=5,
                step=1,
                value=2,
            )
        seed = gr.Slider(
            label="Seed",
            minimum=0,
            maximum=MAX_SEED,
            step=1,
            value=0,
            visible=True
        )
        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
        with gr.Row(visible=True):
            width = gr.Slider(
                label="Width",
                minimum=512,
                maximum=2048,
                step=8,
                value=1024,
            )
            height = gr.Slider(
                label="Height",
                minimum=512,
                maximum=2048,
                step=8,
                value=1024,
            )
        with gr.Row():
            guidance_scale = gr.Slider(
                label="Guidance Scale",
                minimum=0.1,
                maximum=20.0,
                step=0.1,
                value=6,
            )
    with gr.Row(visible=True):
        style_selection = gr.Radio(
            show_label=True,
            container=True,
            interactive=True,
            choices=STYLE_NAMES,
            value=DEFAULT_STYLE_NAME,
            label="Image Style",
        )

    gr.Examples(
        examples=examples,
        inputs=prompt,
        outputs=[result, seed],
        fn=stab,
        cache_examples=False,
    )

    use_negative_prompt.change(
        fn=lambda x: gr.update(visible=x),
        inputs=use_negative_prompt,
        outputs=negative_prompt,
        api_name=False,
    )

    gr.on(
        triggers=[
            prompt.submit,
            negative_prompt.submit,
            run_button.click,
        ],
        fn=stab,
        inputs=[
            prompt,
            negative_prompt,
            style_selection,
            use_negative_prompt,
            num_inference_steps,
            num_images_per_prompt,
            seed,
            width,
            height,
            guidance_scale,
            randomize_seed,
        ],
        outputs=[result, seed],
        api_name="run",
    )

if __name__ == "__main__":
    demo.queue(max_size=20).launch(show_api=False, debug=False, share=True)