app.py

import gradio as gr
import torch

from diffusers import AutoPipelineForInpainting, UNet2DConditionModel
import diffusers
from share_btn import community_icon_html, loading_icon_html, share_js

unet = UNet2DConditionModel.from_pretrained("valhalla/sdxl-inpaint-ema", torch_dtype=torch.float16)
pipe = AutoPipelineForInpainting.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", unet=unet, torch_dtype=torch.float16, variant="fp16").to("cuda")

def read_content(file_path: str) -> str:
    """read the content of target file
    """
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()

    return content

def predict(dict, prompt="", guidance_scale=7.5, steps=20, strength=1.0, scheduler="EulerDiscreteScheduler"):
    scheduler_class_name = scheduler.split("-")[0]

    add_kwargs = {}
    if len(scheduler.split("-")) > 1:
        add_kwargs["use_karras"] = True
    if len(scheduler.split("-")) > 2:
        add_kwargs["algorithm_type"] = "sde-dpmsolver++"

    scheduler = getattr(diffusers, scheduler_class_name)
    pipe.scheduler = scheduler.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", subfolder="scheduler", **add_kwargs)
    
    init_image = dict["image"].convert("RGB").resize((1024, 1024))
    mask = dict["mask"].convert("RGB").resize((1024, 1024))
    
    output = pipe(prompt = prompt, image=init_image, mask_image=mask, guidance_scale=guidance_scale, num_inference_steps=int(steps), strength=strength)
    
    return output.images[0], gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)


css = '''
.container {max-width: 1150px;margin: auto;padding-top: 1.5rem}
#image_upload{min-height:400px}
#image_upload [data-testid="image"], #image_upload [data-testid="image"] > div{min-height: 400px}
#mask_radio .gr-form{background:transparent; border: none}
#word_mask{margin-top: .75em !important}
#word_mask textarea:disabled{opacity: 0.3}
.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%}
#image_upload .touch-none{display: flex}
@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;
}
#share-btn-container div:nth-child(-n+2){
    width: auto !important;
    min-height: 0px !important;
}
#share-btn-container .wrap {
    display: none !important;
}
'''

image_blocks = gr.Blocks(css=css)
with image_blocks as demo:
    gr.HTML(read_content("header.html"))
    with gr.Group():
        with gr.Box():
            with gr.Row():
                with gr.Column():
                    image = gr.Image(source='upload', tool='sketch', elem_id="image_upload", type="pil", label="Upload").style(height=400)
                    with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
                        prompt = gr.Textbox(placeholder = 'Your prompt (what you want in place of what is erased)', show_label=False, elem_id="input-text")

                    with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
                        guidance_scale = gr.Number(value=7.5, minimum=1.0, maximum=20.0, step=0.1, label="guidance_scale")
                        steps = gr.Number(value=20, minimum=10, maximum=50, step=0.1, label="steps")
                        strength = gr.Number(value=1.0, minimum=0.0, maximum=1.0, step=0.05, label="strength")

                    with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
                        schedulers = ["DEISMultistepScheduler", "HeunDiscreteScheduler", "EulerDiscreteScheduler", "DPMSolverMultistepScheduler", "DPMSolverMultistepScheduler-Karras", "DPMSolverMultistepScheduler-Karras-SDE"]
                        scheduler = gr.Dropdown(choices=schedulers, value="EulerDiscreteScheduler")
                        
                        btn = gr.Button("Inpaint!").style(
                            margin=False,
                            rounded=(False, True, True, False),
                            full_width=False,
                        )
                with gr.Column():
                    image_out = gr.Image(label="Output", elem_id="output-img").style(height=400)
                    with gr.Group(elem_id="share-btn-container"):
                        community_icon = gr.HTML(community_icon_html, visible=False)
                        loading_icon = gr.HTML(loading_icon_html, visible=False)
                        share_button = gr.Button("Share to community", elem_id="share-btn", visible=False)
            

            btn.click(fn=predict, inputs=[image, prompt, guidance_scale, steps, strength, scheduler], outputs=[image_out, community_icon, loading_icon, share_button])
            share_button.click(None, [], [], _js=share_js)

            gr.HTML(
                """
                    <div class="footer">
                        <p>Model by <a href="https://huggingface.co/diffusers" style="text-decoration: underline;" target="_blank">Diffusers</a> - Gradio Demo by 🤗 Hugging Face
                        </p>
                    </div>
                """
            )

image_blocks.launch()