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)