app.py

import spaces
import gradio as gr
from gradio_imageslider import ImageSlider
import torch
from diffusers import DiffusionPipeline, AutoencoderKL, ControlNetModel
from compel import Compel, ReturnedEmbeddingsType
from PIL import Image
from torchvision import transforms
import tempfile
import os
import time
import uuid
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}")


vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=dtype)
controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float16
)
pipe = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    custom_pipeline="pipeline_demofusion_sdxl_controlnet.py",
    controlnet=controlnet,
    custom_revision="main",
    torch_dtype=dtype,
    variant="fp16",
    use_safetensors=True,
    vae=vae,
)
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 load_and_process_image(pil_image):
    transform = transforms.Compose(
        [
            transforms.Resize((1024, 1024)),
            transforms.ToTensor(),
            transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),
        ]
    )
    image = transform(pil_image)
    image = image.unsqueeze(0).half()
    return image


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,
    cosine_scale_1=3,
    cosine_scale_2=1,
    cosine_scale_3=1,
    sigma=0.8,
    scale=2,
    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")
    image_lr = load_and_process_image(padded_image).to(device)
    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(
        prompt_embeds=conditioning[0:1],
        pooled_prompt_embeds=pooled[0:1],
        negative_prompt_embeds=conditioning[1:2],
        negative_pooled_prompt_embeds=pooled[1:2],
        image_lr=image_lr,
        width=1024 * scale,
        height=1024 * scale,
        view_batch_size=16,
        controlnet_conditioning_scale=controlnet_conditioning_scale,
        condition_image=canny_image,
        stride=64,
        generator=generator,
        num_inference_steps=40,
        guidance_scale=guidance_scale,
        cosine_scale_1=cosine_scale_1,
        cosine_scale_2=cosine_scale_2,
        cosine_scale_3=cosine_scale_3,
        sigma=sigma,
        multi_decoder=1024 * scale > 2048,
        show_image=False,
        lowvram=LOW_MEMORY,
    )
    print(f"Time taken: {time.time() - last_time}")
    images_path = tempfile.mkdtemp()
    paths = []
    uuid_name = uuid.uuid4()
    for i, img in enumerate(images):
        img.save(images_path + f"/img_{uuid_name}_{img.size[0]}.jpg")
        paths.append(images_path + f"/img_{uuid_name}_{img.size[0]}.jpg")
    return (images[0], images[-1]), paths


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="DemoFusion Params", 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,
                )
                cosine_scale_1 = gr.Slider(
                    minimum=0,
                    maximum=5,
                    value=3,
                    step=0.01,
                    label="Cosine Scale 1",
                )
                cosine_scale_2 = gr.Slider(
                    minimum=0,
                    maximum=5,
                    value=1,
                    step=0.01,
                    label="Cosine Scale 2",
                )
                cosine_scale_3 = gr.Slider(
                    minimum=0,
                    maximum=5,
                    value=1,
                    step=0.01,
                    label="Cosine Scale 3",
                )
                sigma = gr.Slider(
                    minimum=0,
                    maximum=1,
                    value=0.8,
                    step=0.01,
                    label="Sigma",
                )
            with gr.Accordion(label="ControlNet Params", open=False):
                controlnet_conditioning_scale = gr.Slider(
                    minimum=0,
                    maximum=1,
                    step=0.001,
                    value=0.5,
                    label="ControlNet Conditioning Scale",
                )
                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)
            files = gr.Files()
    inputs = [
        image_input,
        prompt,
        negative_prompt,
        seed,
        controlnet_conditioning_scale,
        guidance_scale,
        cosine_scale_1,
        cosine_scale_2,
        cosine_scale_3,
        sigma,
        # scale,
    ]
    outputs = [image_slider, files]
    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,
                1,
                1,
                0.8,
                2,
            ],
            [
                "./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,
                1,
                1,
                0.8,
                2,
            ],
            [
                "./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,
                1,
                1,
                0.8,
                2,
            ],
            [
                "./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,
                1,
                1,
                0.8,
                2,
            ],
            [
                "./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,
                1,
                1,
                0.8,
                2,
            ],
            [
                "./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,
                1,
                1,
                0.49,
                3,
            ],
        ],
        inputs=inputs,
        outputs=outputs,
        cache_examples=True,
    )


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