Spaces:
Runtime error
Runtime error
| from __future__ import annotations | |
| from gradio_imageslider import ImageSlider | |
| import functools | |
| import os | |
| import tempfile | |
| import diffusers | |
| import gradio as gr | |
| import imageio as imageio | |
| import numpy as np | |
| import spaces | |
| import torch as torch | |
| from PIL import Image | |
| from tqdm import tqdm | |
| from pathlib import Path | |
| import gradio | |
| from gradio.utils import get_cache_folder | |
| from infer import lotus | |
| # def process_image_check(path_input): | |
| # if path_input is None: | |
| # raise gr.Error( | |
| # "Missing image in the first pane: upload a file or use one from the gallery below." | |
| # ) | |
| # def infer(path_input, seed=0): | |
| # print(f"==> Processing image {path_input}") | |
| # return path_input | |
| # return [path_input, path_input] | |
| # # name_base, name_ext = os.path.splitext(os.path.basename(path_input)) | |
| # # print(f"==> Processing image {name_base}{name_ext}") | |
| # # device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| # # print(f"==> Device: {device}") | |
| # # output_g, output_d = lotus(path_input, 'depth', seed, device) | |
| # # if not os.path.exists("files/output"): | |
| # # os.makedirs("files/output") | |
| # # g_save_path = os.path.join("files/output", f"{name_base}_g{name_ext}") | |
| # # d_save_path = os.path.join("files/output", f"{name_base}_d{name_ext}") | |
| # # output_g.save(g_save_path) | |
| # # output_d.save(d_save_path) | |
| # # yield [path_input, g_save_path], [path_input, d_save_path] | |
| # def run_demo_server(): | |
| # gradio_theme = gr.themes.Default() | |
| # with gr.Blocks( | |
| # theme=gradio_theme, | |
| # title="LOTUS (Depth)", | |
| # css=""" | |
| # #download { | |
| # height: 118px; | |
| # } | |
| # .slider .inner { | |
| # width: 5px; | |
| # background: #FFF; | |
| # } | |
| # .viewport { | |
| # aspect-ratio: 4/3; | |
| # } | |
| # .tabs button.selected { | |
| # font-size: 20px !important; | |
| # color: crimson !important; | |
| # } | |
| # h1 { | |
| # text-align: center; | |
| # display: block; | |
| # } | |
| # h2 { | |
| # text-align: center; | |
| # display: block; | |
| # } | |
| # h3 { | |
| # text-align: center; | |
| # display: block; | |
| # } | |
| # .md_feedback li { | |
| # margin-bottom: 0px !important; | |
| # } | |
| # """, | |
| # head=""" | |
| # <script async src="https://www.googletagmanager.com/gtag/js?id=G-1FWSVCGZTG"></script> | |
| # <script> | |
| # window.dataLayer = window.dataLayer || []; | |
| # function gtag() {dataLayer.push(arguments);} | |
| # gtag('js', new Date()); | |
| # gtag('config', 'G-1FWSVCGZTG'); | |
| # </script> | |
| # """, | |
| # ) as demo: | |
| # gr.Markdown( | |
| # """ | |
| # # LOTUS: Diffusion-based Visual Foundation Model for High-quality Dense Prediction | |
| # <p align="center"> | |
| # <a title="Page" href="https://lotus3d.github.io/" target="_blank" rel="noopener noreferrer" style="display: inline-block;"> | |
| # <img src="https://img.shields.io/badge/Project-Website-pink?logo=googlechrome&logoColor=white"> | |
| # </a> | |
| # <a title="arXiv" href="https://arxiv.org/abs/2409.18124" target="_blank" rel="noopener noreferrer" style="display: inline-block;"> | |
| # <img src="https://img.shields.io/badge/arXiv-Paper-b31b1b?logo=arxiv&logoColor=white"> | |
| # </a> | |
| # <a title="Github" href="https://github.com/EnVision-Research/Lotus" target="_blank" rel="noopener noreferrer" style="display: inline-block;"> | |
| # <img src="https://img.shields.io/github/stars/EnVision-Research/Lotus?label=GitHub%20%E2%98%85&logo=github&color=C8C" alt="badge-github-stars"> | |
| # </a> | |
| # <a title="Social" href="https://x.com/haodongli00/status/1839524569058582884" target="_blank" rel="noopener noreferrer" style="display: inline-block;"> | |
| # <img src="https://www.obukhov.ai/img/badges/badge-social.svg" alt="social"> | |
| # </a> | |
| # """ | |
| # ) | |
| # with gr.Tabs(elem_classes=["tabs"]): | |
| # with gr.Tab("IMAGE"): | |
| # with gr.Row(): | |
| # with gr.Column(): | |
| # image_input = gr.Image( | |
| # label="Input Image", | |
| # type="filepath", | |
| # ) | |
| # seed = gr.Number( | |
| # label="Seed", | |
| # minimum=0, | |
| # maximum=999999, | |
| # ) | |
| # with gr.Row(): | |
| # image_submit_btn = gr.Button( | |
| # value="Predict Depth!", variant="primary" | |
| # ) | |
| # # image_reset_btn = gr.Button(value="Reset") | |
| # with gr.Column(): | |
| # image_output_g = gr.Image( | |
| # label="Output (Generative)", | |
| # type="filepath", | |
| # ) | |
| # # image_output_g = ImageSlider( | |
| # # label="Output (Generative)", | |
| # # type="filepath", | |
| # # show_download_button=True, | |
| # # show_share_button=True, | |
| # # interactive=False, | |
| # # elem_classes="slider", | |
| # # position=0.25, | |
| # # ) | |
| # # with gr.Row(): | |
| # # image_output_d = gr.Image( | |
| # # label="Output (Generative)", | |
| # # type="filepath", | |
| # # ) | |
| # # image_output_d = ImageSlider( | |
| # # label="Output (Discriminative)", | |
| # # type="filepath", | |
| # # show_download_button=True, | |
| # # show_share_button=True, | |
| # # interactive=False, | |
| # # elem_classes="slider", | |
| # # position=0.25, | |
| # # ) | |
| # # gr.Examples( | |
| # # fn=infer, | |
| # # examples=sorted([ | |
| # # os.path.join("files", "images", name) | |
| # # for name in os.listdir(os.path.join("files", "images")) | |
| # # ]), | |
| # # inputs=[image_input], | |
| # # outputs=[image_output_g], | |
| # # cache_examples=True, | |
| # # ) | |
| # with gr.Tab("VIDEO"): | |
| # with gr.Column(): | |
| # gr.Markdown("Coming soon") | |
| # ### Image | |
| # image_submit_btn.click( | |
| # fn=infer, | |
| # inputs=[ | |
| # image_input | |
| # ], | |
| # outputs=image_output_g, | |
| # concurrency_limit=1, | |
| # ) | |
| # # image_reset_btn.click( | |
| # # fn=lambda: ( | |
| # # None, | |
| # # None, | |
| # # None, | |
| # # ), | |
| # # inputs=[], | |
| # # outputs=image_output_g, | |
| # # queue=False, | |
| # # ) | |
| # ### Video | |
| # ### Server launch | |
| # demo.queue( | |
| # api_open=False, | |
| # ).launch( | |
| # server_name="0.0.0.0", | |
| # server_port=7860, | |
| # ) | |
| # def main(): | |
| # os.system("pip freeze") | |
| # run_demo_server() | |
| # if __name__ == "__main__": | |
| # main() | |
| def flip_text(x): | |
| return x[::-1] | |
| def flip_image(x): | |
| return np.fliplr(x) | |
| with gr.Blocks() as demo: | |
| gr.Markdown("Flip text or image files using this demo.") | |
| with gr.Tab("Flip Text"): | |
| text_input = gr.Textbox() | |
| text_output = gr.Textbox() | |
| text_button = gr.Button("Flip") | |
| with gr.Tab("Flip Image"): | |
| with gr.Row(): | |
| image_input = gr.Image() | |
| image_output = gr.Image() | |
| image_button = gr.Button("Flip") | |
| with gr.Accordion("Open for More!", open=False): | |
| gr.Markdown("Look at me...") | |
| temp_slider = gr.Slider( | |
| 0, 1, | |
| value=0.1, | |
| step=0.1, | |
| interactive=True, | |
| label="Slide me", | |
| ) | |
| text_button.click(flip_text, inputs=text_input, outputs=text_output) | |
| image_button.click(flip_image, inputs=image_input, outputs=image_output) | |
| demo.launch(share=True) | |