"""The model used in this Space alters the underlying Stable Diffusion model available at
https://huggingface.co/CompVis/stable-diffusion-v1-4 through the addition of new embedding vectors
in order to capture the likeness of the Determined AI logo.  These alternations are fully captured
in the learned_embeddings_dict.pt pickle file in the root of the repository."""

import pathlib
import os
from PIL import Image

import gradio as gr
import torch
from diffusers import StableDiffusionPipeline

import utils

use_auth_token = os.environ["HF_AUTH_TOKEN"]
NSFW_IMAGE = Image.open("nsfw.png")
BATCH_SIZE = 2

# Instantiate the pipeline.
device, revision, torch_dtype = (
    ("cuda", "fp16", torch.float16)
    if torch.cuda.is_available()
    else ("cpu", "main", torch.float32)
)
pipeline = StableDiffusionPipeline.from_pretrained(
    pretrained_model_name_or_path="CompVis/stable-diffusion-v1-4",
    use_auth_token=use_auth_token,
    revision=revision,
    torch_dtype=torch_dtype,
).to(device)

# Load in the new concepts.
CONCEPT_PATH = pathlib.Path("learned_embeddings_dict.pt")
learned_embeddings_dict = torch.load(CONCEPT_PATH)

concept_to_dummy_tokens_map = {}
for concept_token, embedding_dict in learned_embeddings_dict.items():
    initializer_tokens = embedding_dict["initializer_tokens"]
    learned_embeddings = embedding_dict["learned_embeddings"]
    (
        initializer_ids,
        dummy_placeholder_ids,
        dummy_placeholder_tokens,
    ) = utils.add_new_tokens_to_tokenizer(
        concept_token=concept_token,
        initializer_tokens=initializer_tokens,
        tokenizer=pipeline.tokenizer,
    )
    pipeline.text_encoder.resize_token_embeddings(len(pipeline.tokenizer))
    token_embeddings = pipeline.text_encoder.get_input_embeddings().weight.data
    for d_id, tensor in zip(dummy_placeholder_ids, learned_embeddings):
        token_embeddings[d_id] = tensor
    concept_to_dummy_tokens_map[concept_token] = dummy_placeholder_tokens


def replace_concept_tokens(text: str):
    for concept_token, dummy_tokens in concept_to_dummy_tokens_map.items():
        text = text.replace(concept_token, dummy_tokens)
    return text


all_imgs = []


def inference(prompt: str, guidance_scale: int, num_inference_steps: int, seed: int):
    prompt = replace_concept_tokens(prompt)
    generator = torch.Generator(device=device).manual_seed(seed)
    output = pipeline(
        prompt=[prompt] * BATCH_SIZE,
        num_inference_steps=num_inference_steps,
        guidance_scale=guidance_scale,
        generator=generator,
    )
    img_list, nsfw_list = output.images, output.nsfw_content_detected
    filtered_imgs = [
        img if not nsfw else NSFW_IMAGE for img, nsfw in zip(img_list, nsfw_list)
    ]
    all_imgs.extend(filtered_imgs)
    return all_imgs


css = """
        .gradio-container {
            font-family: 'IBM Plex Sans', sans-serif;
        }
        .gr-button {
            color: white;
            border-color: black;
            background: black;
        }
        input[type='range'] {
            accent-color: black;
        }
        .dark input[type='range'] {
            accent-color: #dfdfdf;
        }
        .container {
            max-width: 730px;
            margin: auto;
            padding-top: 1.5rem;
        }
        #gallery {
            min-height: 22rem;
            margin-bottom: 15px;
            margin-left: auto;
            margin-right: auto;
            border-bottom-right-radius: .5rem !important;
            border-bottom-left-radius: .5rem !important;
        }
        #gallery>div>.h-full {
            min-height: 20rem;
        }
        .details:hover {
            text-decoration: underline;
        }
        .gr-button {
            white-space: nowrap;
        }
        .gr-button:focus {
            border-color: rgb(147 197 253 / var(--tw-border-opacity));
            outline: none;
            box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
            --tw-border-opacity: 1;
            --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
            --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(3px var(--tw-ring-offset-width)) var(--tw-ring-color);
            --tw-ring-color: rgb(191 219 254 / var(--tw-ring-opacity));
            --tw-ring-opacity: .5;
        }
        #advanced-btn {
            font-size: .7rem !important;
            line-height: 19px;
            margin-top: 12px;
            margin-bottom: 12px;
            padding: 2px 8px;
            border-radius: 14px !important;
        }
        #advanced-options {
            display: none;
            margin-bottom: 20px;
        }
        .footer {
            margin-bottom: 45px;
            margin-top: 35px;
            text-align: center;
            border-bottom: 1px solid #e5e5e5;
        }
        .footer>p {
            font-size: .8rem;
            display: inline-block;
            padding: 0 10px;
            transform: translateY(10px);
            background: white;
        }
        .dark .footer {
            border-color: #303030;
        }
        .dark .footer>p {
            background: #0b0f19;
        }
        .acknowledgments h4{
            margin: 1.25em 0 .25em 0;
            font-weight: bold;
            font-size: 115%;
        }
        #container-advanced-btns{
            display: flex;
            flex-wrap: wrap;
            justify-content: space-between;
            align-items: center;
        }
        .animate-spin {
            animation: spin 1s linear infinite;
        }
        @keyframes spin {
            from {
                transform: rotate(0deg);
            }
            to {
                transform: rotate(360deg);
            }
        }
        #share-btn-container {
            display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
        }
        #share-btn {
            all: initial; color: #ffffff;font-weight: 600; cursor:pointer; font-family: 'IBM Plex Sans', sans-serif; margin-left: 0.5rem !important; padding-top: 0.25rem !important; padding-bottom: 0.25rem !important;
        }
        #share-btn * {
            all: unset;
        }
        .gr-form{
            flex: 1 1 50%; border-top-right-radius: 0; border-bottom-right-radius: 0;
        }
        #prompt-container{
            gap: 0;
        }
"""

block = gr.Blocks(css=css)

examples = [
    [
        "a Van Gogh painting of a <det-logo> with thick strokes, masterful composition",
        #        4,
        #        45,
        #        7.5,
        #        1024,
    ],
    [
        "Futuristic <det-logo> in a desert, painting, octane render, 4 k, anime sky, warm colors",
        #        4,
        #        45,
        #        7,
        #        1024,
    ],
    [
        "cell shaded cartoon of a <det-logo>, subtle colors, post grunge, concept art by josan gonzales and wlop, by james jean, victo ngai, david rubin, mike mignola, deviantart, art by artgem",
        #        4,
        #        45,
        #        7,
        #        1024,
    ],
    [
        "a <det-logo> cloudy sky background lush landscape illustration concept art anime key visual trending pixiv fanbox by wlop and greg rutkowski and makoto shinkai and studio ghibli",
        #        4,
        #        45,
        #        7,
        #        1024,
    ],
    [
        "Immense <det-logo> advanced technology scifi architectural structure desert planet alien wardrobe tim hildebrandt, wayne barlowe, bruce pennington, donato giancola, larry elmore, oil on canvas, masterpiece, trending on artstation, featured on pixiv, cinematic composition, dramatic, beautiful lighting",
        #        4,
        #        45,
        #        7,
        #        1024,
    ],
]


with block:
    gr.HTML(
        """
            <div style="text-align: center; max-width: 650px; margin: 0 auto;">
              <div
                style="
                  display: inline-flex;
                  align-items: center;
                  gap: 0.8rem;
                  font-size: 1.75rem;
                "
              >
                <h1 style="font-weight: 900; margin-bottom: 7px;">
                  Determined AI Textual Inversion Demo
                </h1>
              </div>
            </div>
        """
    )
    with gr.Group():
        with gr.Box():
            with gr.Row(elem_id="prompt-container").style(equal_height=True):
                prompt = gr.Textbox(
                    label="Enter a prompt including '<det-logo>'",
                    show_label=False,
                    max_lines=1,
                    placeholder="Enter a prompt including '<det-logo>'",
                    elem_id="prompt-text-input",
                ).style(
                    container=False,
                )
                btn = gr.Button("Generate image").style(
                    full_width=False,
                )

        gallery = gr.Gallery(
            label="Generated images", show_label=False, elem_id="gallery"
        ).style(grid=[BATCH_SIZE], height="auto")

        with gr.Group(elem_id="container-advanced-btns"):
            advanced_button = gr.Button("Advanced options", elem_id="advanced-btn")

        with gr.Row(elem_id="advanced-options"):
            num_inference_steps = gr.Slider(
                label="Steps", minimum=20, maximum=60, value=40, step=1
            )
            guidance_scale = gr.Slider(
                label="Guidance Scale", minimum=1.0, maximum=30.0, value=4.0, step=0.1
            )
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=2147483647,
                step=1,
                randomize=True,
            )

        ex = gr.Examples(
            examples=examples,
            fn=inference,
            inputs=[prompt, guidance_scale, num_inference_steps, seed],
            outputs=[gallery],
            cache_examples=False,
        )
        ex.dataset.headers = [""]

        prompt.submit(
            inference,
            inputs=[prompt, guidance_scale, num_inference_steps, seed],
            outputs=[gallery],
        )
        btn.click(
            inference,
            inputs=[prompt, guidance_scale, num_inference_steps, seed],
            outputs=[gallery],
        )
        advanced_button.click(
            None,
            [],
            prompt,
            _js="""
            () => {
                var appDom = document.querySelector("body > gradio-app");
                var options = appDom.querySelector("#advanced-options")
                if (options == null) {options = appDom.shadowRoot.querySelector("#advanced-options")}
                options.style.display = ["none", ""].includes(options.style.display) ? "flex" : "none";
            }""",
        )
        gr.HTML(
            """
                <div class="footer">
                    <p>Underlying model by <a href="https://huggingface.co/CompVis" style="text-decoration: underline;" target="_blank">CompVis</a> and <a href="https://huggingface.co/stabilityai" style="text-decoration: underline;" target="_blank">Stability AI</a> - Gradio code based on the <a href="https://huggingface.co/spaces/stabilityai/stable-diffusion" style="text-decoration: underline;" target="_blank">Stability AI Demo</a>
                    </p>
                </div>
                <div class="acknowledgments">
                    <p><h4>LICENSE</h4>
The model is licensed with a <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" style="text-decoration: underline;" target="_blank">CreativeML Open RAIL-M</a> license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" target="_blank" style="text-decoration: underline;" target="_blank">read the license</a></p>
<p><h4>Model Changes</h4>
The model used in this Space alters the underlying <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4" style="text-decoration: underline;" target="_blank">stable-diffusion-v1-4</a> model through the addition of new embedding vectors in order to capture the likeness of the <a href="https://www.determined.ai" style="text-decoration: underline;" target="_blank">Determined AI</a> logo.</p>
                    <p><h4>Biases and content acknowledgment</h4>
Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the <a href="https://laion.ai/blog/laion-5b/" style="text-decoration: underline;" target="_blank">LAION-5B dataset</a>, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4" style="text-decoration: underline;" target="_blank">model card</a></p>
               </div>
           """
        )

block.queue(max_size=10).launch(share=True, enable_queue=True)