Spaces:
Running
Running
| import gradio as gr | |
| from PIL import Image | |
| import torch | |
| from diffusion import DiffusionPipeline | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| pipe = DiffusionPipeline(device) | |
| 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(input, dkernel, diffusion_step, q=False): | |
| lq = input["image"].convert("RGB") | |
| mask = input["mask"].convert("RGB") | |
| mask = mask.resize(lq.size, resample=Image.NEAREST) | |
| output = pipe(lq=lq, mask=mask, dkernel=dkernel, diffusion_step=diffusion_step) | |
| return output | |
| def qpredict(input, dkernel, diffusion_step, q=False): | |
| lq = input["image"].convert("RGB") | |
| mask = input["mask"].convert("RGB") | |
| mask = mask.resize(lq.size, resample=Image.NEAREST) | |
| for output in pipe.quick_solve(lq=lq, mask=mask, dkernel=dkernel, diffusion_step=diffusion_step): | |
| yield output | |
| 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); | |
| } | |
| } | |
| ''' | |
| 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="Shadow Image").style(height=400) | |
| dkernel = gr.Slider(minimum=11, maximum=55, step=2, value=11, label="Dilation Kernel Size") | |
| diffusion_step = gr.Slider(minimum=10, maximum=200, step=5, value=20, label="Diffusion Time Step") | |
| with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True): | |
| with gr.Column(): | |
| btn = gr.Button("Removal").style( | |
| margin=False, | |
| full_width=True, | |
| ) | |
| with gr.Column(): | |
| qbtn = gr.Button("Quick Removal").style( | |
| margin=False, | |
| full_width=True, | |
| ) | |
| with gr.Column(): | |
| image_out = gr.Image(label="Removal Result", elem_id="output-img") | |
| with gr.Row(): | |
| gr.Examples(examples=[ | |
| 'examples/lssd2025.jpg', | |
| 'examples/web-shadow0248.jpg', | |
| ], inputs=[image]) | |
| btn.click(fn=predict, inputs=[image, dkernel, diffusion_step], outputs=[image_out]) | |
| qbtn.click(fn=qpredict, inputs=[image, dkernel, diffusion_step], outputs=[image_out]) | |
| image_blocks.launch(enable_queue=True) | |