import spaces
import gradio as gr
from gradio_imageslider import ImageSlider
import torch
from hidiffusion import apply_hidiffusion
from diffusers import (
    ControlNetModel,
    StableDiffusionXLControlNetImg2ImgPipeline,
    DDIMScheduler,
)

from compel import Compel, ReturnedEmbeddingsType
from PIL import Image
import os
import time
import cv2
import numpy as np


device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16

LOW_MEMORY = os.getenv("LOW_MEMORY", "0") == "1"

print(f"device: {device}")
print(f"dtype: {dtype}")
print(f"low memory: {LOW_MEMORY}")


model = "stabilityai/stable-diffusion-xl-base-1.0"
# vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=dtype)
scheduler = DDIMScheduler.from_pretrained(model, subfolder="scheduler")
controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float16
)
pipe = StableDiffusionXLControlNetImg2ImgPipeline.from_pretrained(
    model,
    controlnet=controlnet,
    torch_dtype=dtype,
    variant="fp16",
    use_safetensors=True,
    scheduler=scheduler,
)
pipe.enable_xformers_memory_efficient_attention()
# pipe.enable_model_cpu_offload()
pipe.enable_vae_tiling()
apply_hidiffusion(pipe)

compel = Compel(
    tokenizer=[pipe.tokenizer, pipe.tokenizer_2],
    text_encoder=[pipe.text_encoder, pipe.text_encoder_2],
    returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED,
    requires_pooled=[False, True],
)
pipe = pipe.to(device)


def pad_image(image):
    w, h = image.size
    if w == h:
        return image
    elif w > h:
        new_image = Image.new(image.mode, (w, w), (0, 0, 0))
        pad_w = 0
        pad_h = (w - h) // 2
        new_image.paste(image, (0, pad_h))
        return new_image
    else:
        new_image = Image.new(image.mode, (h, h), (0, 0, 0))
        pad_w = (h - w) // 2
        pad_h = 0
        new_image.paste(image, (pad_w, 0))
        return new_image


@spaces.GPU
def predict(
    input_image,
    prompt,
    negative_prompt,
    seed,
    controlnet_conditioning_scale,
    guidance_scale=8.5,
    scale=2,
    strength=1.0,
    controlnet_start=0.0,
    controlnet_end=1.0,
    progress=gr.Progress(track_tqdm=True),
):
    if input_image is None:
        raise gr.Error("Please upload an image.")
    padded_image = pad_image(input_image).resize((1024, 1024)).convert("RGB")
    conditioning, pooled = compel([prompt, negative_prompt])
    generator = torch.manual_seed(seed)
    last_time = time.time()
    canny_image = np.array(padded_image)
    canny_image = cv2.Canny(canny_image, 100, 200)
    canny_image = canny_image[:, :, None]
    canny_image = np.concatenate([canny_image, canny_image, canny_image], axis=2)
    canny_image = Image.fromarray(canny_image)
    images = pipe(
        image=padded_image,
        control_image=canny_image,
        strength=strength,
        prompt_embeds=conditioning[0:1],
        pooled_prompt_embeds=pooled[0:1],
        negative_prompt_embeds=conditioning[1:2],
        negative_pooled_prompt_embeds=pooled[1:2],
        width=1024 * scale,
        height=1024 * scale,
        controlnet_conditioning_scale=controlnet_conditioning_scale,
        controlnet_start=controlnet_start,
        controlnet_end=controlnet_end,
        generator=generator,
        num_inference_steps=40,
        guidance_scale=guidance_scale,
        eta=1.0,
    )
    print(f"Time taken: {time.time() - last_time}")
    return (padded_image, images.images[0])


css = """
#intro{
    # max-width: 32rem;
    # text-align: center;
    # margin: 0 auto;
}
"""

with gr.Blocks(css=css) as demo:
    gr.Markdown(
        """
# Enhance This  
### DemoFusion SDXL

[DemoFusion](https://ruoyidu.github.io/demofusion/demofusion.html) enables higher-resolution image generation.  
You can upload an initial image and prompt to generate an enhanced version. 
[Duplicate Space](https://huggingface.co/spaces/radames/Enhance-This-DemoFusion-SDXL?duplicate=true) to avoid the queue.  
GPU Time Comparison: T4: ~276s - A10G: ~113.6s A100: ~43.5s RTX 4090: ~48.1s

<small>
<b>Notes</b> The author advises against the term "super resolution" because it's more like image-to-image generation than enhancement, but it's still a lot of fun!

</small>
        """,
        elem_id="intro",
    )
    with gr.Row():
        with gr.Column(scale=1):
            image_input = gr.Image(type="pil", label="Input Image")
            prompt = gr.Textbox(
                label="Prompt",
                info="The prompt is very important to get the desired results. Please try to describe the image as best as you can. Accepts Compel Syntax",
            )
            negative_prompt = gr.Textbox(
                label="Negative Prompt",
                value="blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
            )
            seed = gr.Slider(
                minimum=0,
                maximum=2**64 - 1,
                value=1415926535897932,
                step=1,
                label="Seed",
                randomize=True,
            )
            with gr.Accordion(label="Advanced", open=False):
                guidance_scale = gr.Slider(
                    minimum=0,
                    maximum=50,
                    value=8.5,
                    step=0.001,
                    label="Guidance Scale",
                )
                scale = gr.Slider(
                    minimum=1,
                    maximum=5,
                    value=2,
                    step=1,
                    label="Magnification Scale",
                    # interactive=False,
                )
                controlnet_conditioning_scale = gr.Slider(
                    minimum=0,
                    maximum=1,
                    step=0.001,
                    value=0.5,
                    label="ControlNet Conditioning Scale",
                )
                strength = gr.Slider(
                    minimum=0,
                    maximum=2,
                    step=0.001,
                    value=1,
                    label="Strength",
                )
                controlnet_start = gr.Slider(
                    minimum=0,
                    maximum=1,
                    step=0.001,
                    value=0.0,
                    label="ControlNet Start",
                )
                controlnet_end = gr.Slider(
                    minimum=0.0,
                    maximum=1.0,
                    step=0.001,
                    value=1.0,
                    label="ControlNet End",
                )

            btn = gr.Button()
        with gr.Column(scale=2):
            image_slider = ImageSlider(position=0.5)
    inputs = [
        image_input,
        prompt,
        negative_prompt,
        seed,
        controlnet_conditioning_scale,
        guidance_scale,
        scale,
        strength,
        controlnet_start,
        controlnet_end,
    ]
    outputs = [image_slider]
    btn.click(predict, inputs=inputs, outputs=outputs, concurrency_limit=1)
    gr.Examples(
        fn=predict,
        examples=[
            [
                "./examples/lara.jpeg",
                "photography of lara croft 8k high definition award winning",
                "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
                5436236241,
                0.5,
                8.5,
                3,
                0.8,
                0.0,
                1.0,
            ],
            [
                "./examples/cybetruck.jpeg",
                "photo of tesla cybertruck futuristic car 8k high definition on a sand dune in mars, future",
                "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
                383472451451,
                0.5,
                8.5,
                3,
                0.8,
                0.0,
                1.0,
            ],
            [
                "./examples/jesus.png",
                "a photorealistic painting of Jesus Christ, 4k high definition",
                "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
                13317204146129588000,
                0.5,
                8.5,
                3,
                0.8,
                0.0,
                1.0,
            ],
            [
                "./examples/anna-sullivan-DioLM8ViiO8-unsplash.jpg",
                "A crowded stadium with enthusiastic fans watching a daytime sporting event, the stands filled with colorful attire and the sun casting a warm glow",
                "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
                5623124123512,
                0.5,
                8.5,
                3,
                0.8,
                0.0,
                1.0,
            ],
            [
                "./examples/img_aef651cb-2919-499d-aa49-6d4e2e21a56e_1024.jpg",
                "a large red flower on a black background 4k high definition",
                "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
                23123412341234,
                0.5,
                8.5,
                3,
                0.8,
                0.0,
                1.0,
            ],
            [
                "./examples/huggingface.jpg",
                "photo realistic huggingface human+++ emoji costume, round, yellow, skin+++ texture+++",
                "blurry, ugly, duplicate, poorly drawn, deformed, mosaic, emoji cartoon,  drawing, pixelated",
                5532144938416372000,
                0.101,
                25.206,
                4.64,
                0.8,
                0.0,
                1.0,
            ],
        ],
        inputs=inputs,
        outputs=outputs,
        cache_examples="lazy",
    )


demo.queue(api_open=False)
demo.launch(show_api=False)