app.py

import gradio as gr
import torch
import numpy as np
from PIL import Image,ImageFilter
from diffusers.models import AutoencoderKL
from diffusers import AutoPipelineForInpainting, UNet2DConditionModel, DiffusionPipeline, StableDiffusionInpaintPipeline
import diffusers
from share_btn import community_icon_html, loading_icon_html, share_js


vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse")


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="", negative_prompt="", guidance_scale=7.5, steps=30, strength=0.8,model="Realistic_V5.0", scheduler="DPMSolverMultistepScheduler-Karras"):
    
    pipe = AutoPipelineForInpainting.from_pretrained("SG161222/Realistic_Vision_V5.0_noVAE",vae=vae).to("cuda")
    
    if model == "Realistic_V5.1":
        pipe = AutoPipelineForInpainting.from_pretrained("SG161222/Realistic_Vision_V5.1_noVAE", vae=vae).to("cuda")
    if model == "EpicRealism":
        pipe = AutoPipelineForInpainting.from_pretrained("emilianJR/epiCRealism", vae=vae).to("cuda")
    if model == "Realistic_V6.0":
        pipe = AutoPipelineForInpainting.from_pretrained("SG161222/Realistic_Vision_V6.0_B1_noVAE", vae=vae).to("cuda")
        pipe.safety_checker = lambda images, **kwargs: (images, [False] * len(images))

        
    if negative_prompt == "":
        negative_prompt = None
    scheduler_class_name = scheduler.split("-")[0]

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

    scheduler = getattr(diffusers, scheduler_class_name)
    pipe.scheduler = scheduler.from_pretrained("emilianJR/epiCRealism", subfolder="scheduler", **add_kwargs)

    
    
    init_image = dict["image"]
    mask_image = dict["mask"]

    width, height = init_image.size
    mask_image = mask_image.convert("RGBA")
    data = mask_image.getdata()
    new_data = []
    for item in data:
        if item[:3] == (0, 0, 0):  # Check if the pixel is black
            new_data.append((0, 0, 0, 0))  # Add transparent pixel
        else:
            new_data.append(item)
    
    mask_image.putdata(new_data)
    mask_image = mask_image.resize(init_image.size, resample=Image.LANCZOS)
    mask_image = mask_image.filter(ImageFilter.GaussianBlur(5))
    #mask_image = pipe.mask_processor.blur(mask_image, blur_factor=15)
    with torch.cuda.amp.autocast():
        output = pipe(
            prompt=prompt,
            negative_prompt=negative_prompt,
            image=init_image,
            mask_image=mask_image,
            guidance_scale=guidance_scale,
            num_inference_steps=int(steps),
            strength=strength,
            clip_skip=1
        )
    inpainted_image = output.images[0]
    inpainted_image = inpainted_image.resize(init_image.size, resample=Image.LANCZOS)
    # Combine the original and inpainted images using the mask
    combined_image = Image.composite(inpainted_image, init_image, mask_image.split()[3])

    print("Positive:", prompt)
    print("Negative:", negative_prompt)
    print("Guidance_scale:", guidance_scale)
    print("Steps:", steps)
    print("Strength:", strength)
    print("Scheduler:", scheduler)

    return inpainted_image, combined_image, gr.update(visible=True)


css = '''
.gradio-container{max-width: 1100px !important}
#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 {padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; max-width: 13rem; margin-left: auto;}
div#share-btn-container > div {flex-direction: row;background: black;align-items: center}
#share-btn-container:hover {background-color: #060606}
#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: 0.5rem !important; padding-bottom: 0.5rem !important;right:0;}
#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}
#share-btn-container.hidden {display: none!important}
#prompt input{width: calc(100% - 160px);border-top-right-radius: 0px;border-bottom-right-radius: 0px;}
#prompt-container{margin-top:-18px;}
#prompt-container .form{border-top-left-radius: 0;border-top-right-radius: 0}
#image_upload{border-bottom-left-radius: 0px;border-bottom-right-radius: 0px}
'''

image_blocks = gr.Blocks(css=css, elem_id="total-container")
with image_blocks as demo:
    gr.HTML(read_content("header.html"))
    with gr.Row():
                with gr.Column():
                    image = gr.Image(source='upload', tool='sketch', elem_id="image_upload", type="pil", label="Upload",height=512)
                    with gr.Row(elem_id="prompt-container",equal_height=True):
                        with gr.Row():
                            prompt = gr.Textbox(placeholder="Your prompt", show_label=False, elem_id="prompt", lines=5)
                    with gr.Row(equal_height=True):
                        btn = gr.Button("Inpaint!", elem_id="run_button")
                    
                    with gr.Accordion(label="Advanced Settings", open=False):
                        with gr.Row(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=40, minimum=10, maximum=100, step=1, label="steps")
                            strength = gr.Number(value=0.8, minimum=0.01, maximum=1.0, step=0.01, label="strength")
                            negative_prompt = gr.Textbox(label="negative_prompt", placeholder="Your negative prompt", info="what you don't want to see in the image")
                        with gr.Row(equal_height=True):
                            models = ["Realistic_V5.0","Realistic_V5.1","Realistic_V6.0","Epic_Realism"]
                            model = gr.Dropdown(label="Models",choices=models,value="Realistic_V5.0")
                        with gr.Row(equal_height=True):
                            schedulers = ["DEISMultistepScheduler", "HeunDiscreteScheduler", "EulerDiscreteScheduler", "DPMSolverMultistepScheduler", "DPMSolverMultistepScheduler-Karras", "DPMSolverMultistepScheduler-Karras-SDE"]
                            scheduler = gr.Dropdown(label="Schedulers", choices=schedulers, value="DPMSolverMultistepScheduler-Karras")
                        
                with gr.Column():
                    image_out = gr.Image(label="Output", elem_id="output-img", height=512, width=512)
                    image_out1 = gr.Image(label="Output", elem_id="output-img", height=512, width=512)
                    with gr.Group(elem_id="share-btn-container", visible=False) as share_btn_container:
                        community_icon = gr.HTML(community_icon_html)
                        loading_icon = gr.HTML(loading_icon_html)
                        share_button = gr.Button("Share to community", elem_id="share-btn",visible=True)
            

    btn.click(fn=predict, inputs=[image, prompt, negative_prompt, guidance_scale, steps, strength, model, scheduler], outputs=[image_out,image_out1,share_btn_container], api_name='run')
    prompt.submit(fn=predict, inputs=[image, prompt, negative_prompt, guidance_scale, steps, strength, model, scheduler], outputs=[image_out,image_out1,share_btn_container])
    share_button.click(None, [], [], _js=share_js)


image_blocks.queue(max_size=25,api_open=True).launch(show_api=True)