Spaces:
Running
Running
File size: 14,225 Bytes
307ac9d 508279d 0f32117 508279d dcb1657 508279d 0f32117 508279d 0f32117 508279d 0f32117 508279d 0f32117 508279d 1418aaa 508279d 1418aaa 508279d 0f32117 508279d dcb1657 508279d dcb1657 508279d dcb1657 508279d 307ac9d 508279d 307ac9d 508279d ba7b123 508279d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 |
'''
sudo apt-get update && sudo apt-get install git-lfs ffmpeg cbm
# Clone this repository
git clone https://huggingface.co/spaces/svjack/StableDelight
# Go into the repository
cd StableDelight
### Install dependencies ###
conda create --name py310 python=3.10
conda activate py310
# Install ipykernel and add the environment to Jupyter
pip install ipykernel
python -m ipykernel install --user --name py310 --display-name "py310"
pip install -r requirements.txt
python app.py
'''
# Copyright 2024 Anton Obukhov, ETH Zurich. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# --------------------------------------------------------------------------
# If you find this code useful, we kindly ask you to cite our paper in your work.
# Please find bibtex at: https://github.com/prs-eth/Marigold#-citation
# More information about the method can be found at https://marigoldmonodepth.github.io
# --------------------------------------------------------------------------
from __future__ import annotations
import functools
import os
import tempfile
import gradio as gr
import imageio as imageio
import numpy as np
import spaces
import torch as torch
torch.backends.cuda.matmul.allow_tf32 = True
from PIL import Image
from gradio_imageslider import ImageSlider
from tqdm import tqdm
from pathlib import Path
import gradio
from gradio.utils import get_cache_folder
from stablediffuse.pipeline_yoso_diffuse import YOSODiffusePipeline
class Examples(gradio.helpers.Examples):
def __init__(self, *args, directory_name=None, **kwargs):
super().__init__(*args, **kwargs, _initiated_directly=False)
if directory_name is not None:
self.cached_folder = get_cache_folder() / directory_name
self.cached_file = Path(self.cached_folder) / "log.csv"
self.create()
default_seed = 2024
default_batch_size = 1
default_image_processing_resolution = 2048
default_video_out_max_frames = 60
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 resize_image(input_image, resolution):
# Ensure input_image is a PIL Image object
if not isinstance(input_image, Image.Image):
raise ValueError("input_image should be a PIL Image object")
# Convert image to numpy array
input_image_np = np.asarray(input_image)
# Get image dimensions
H, W, C = input_image_np.shape
H = float(H)
W = float(W)
# Calculate the scaling factor
k = float(resolution) / min(H, W)
# Determine new dimensions
H *= k
W *= k
H = int(np.round(H / 64.0)) * 64
W = int(np.round(W / 64.0)) * 64
# Resize the image using PIL's resize method
img = input_image.resize((W, H), Image.Resampling.LANCZOS)
return img
def process_image(
pipe,
path_input,
):
name_base, name_ext = os.path.splitext(os.path.basename(path_input))
print(f"Processing image {name_base}{name_ext}")
path_output_dir = tempfile.mkdtemp()
path_out_png = os.path.join(path_output_dir, f"{name_base}_delight.png")
input_image = Image.open(path_input)
pipe_out = pipe(
input_image,
match_input_resolution=False,
processing_resolution=default_image_processing_resolution
)
processed_frame = (pipe_out.prediction.clip(-1, 1) + 1) / 2
processed_frame = (processed_frame[0] * 255).astype(np.uint8)
processed_frame = Image.fromarray(processed_frame)
processed_frame.save(path_out_png)
yield [input_image, path_out_png]
def process_video(
pipe,
path_input,
out_max_frames=default_video_out_max_frames,
target_fps=10,
progress=gr.Progress(),
):
if path_input is None:
raise gr.Error(
"Missing video in the first pane: upload a file or use one from the gallery below."
)
name_base, name_ext = os.path.splitext(os.path.basename(path_input))
print(f"Processing video {name_base}{name_ext}")
path_output_dir = tempfile.mkdtemp()
path_out_vis = os.path.join(path_output_dir, f"{name_base}_delight.mp4")
init_latents = None
reader, writer = None, None
try:
reader = imageio.get_reader(path_input)
meta_data = reader.get_meta_data()
fps = meta_data["fps"]
size = meta_data["size"]
duration_sec = meta_data["duration"]
writer = imageio.get_writer(path_out_vis, fps=target_fps)
out_frame_id = 0
pbar = tqdm(desc="Processing Video", total=duration_sec)
for frame_id, frame in enumerate(reader):
if frame_id % (fps // target_fps) != 0:
continue
else:
out_frame_id += 1
pbar.update(1)
if out_frame_id > out_max_frames:
break
frame_pil = Image.fromarray(frame)
pipe_out = pipe(
frame_pil,
match_input_resolution=False,
latents=init_latents,
processing_resolution=default_image_processing_resolution
)
if init_latents is None:
init_latents = pipe_out.gaus_noise
processed_frame = (pipe_out.prediction.clip(-1, 1) + 1) / 2
processed_frame = processed_frame[0]
_processed_frame = imageio.core.util.Array(processed_frame)
writer.append_data(_processed_frame)
yield (
[frame_pil, processed_frame],
None,
)
finally:
if writer is not None:
writer.close()
if reader is not None:
reader.close()
yield (
[frame_pil, processed_frame],
[path_out_vis,]
)
def run_demo_server(pipe):
process_pipe_image = spaces.GPU(functools.partial(process_image, pipe))
process_pipe_video = spaces.GPU(
functools.partial(process_video, pipe), duration=120
)
gradio_theme = gr.themes.Default()
with gr.Blocks(
theme=gradio_theme,
title="Stable Delight Estimation",
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(
"""
# StableDelight: Revealing Hidden Textures by Removing Specular Reflections
<p align="center">
<a title="Website" href="https://github.com/Stable-X/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
<img src="https://www.obukhov.ai/img/badges/badge-website.svg">
</a>
<a title="arXiv" href="https://arxiv.org/abs/2406.16864" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
<img src="https://www.obukhov.ai/img/badges/badge-pdf.svg">
</a>
<a title="Github" href="https://github.com/Stable-X/StableDelight" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
<img src="https://img.shields.io/github/stars/Stable-X/StableDelight?label=GitHub%20%E2%98%85&logo=github&color=C8C" alt="badge-github-stars">
</a>
<a title="Social" href="https://x.com/ychngji6" 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",
)
with gr.Row():
image_submit_btn = gr.Button(
value="Delightning", variant="primary"
)
image_reset_btn = gr.Button(value="Reset")
with gr.Column():
image_output_slider = ImageSlider(
label="Delight outputs",
type="filepath",
show_download_button=True,
show_share_button=True,
interactive=False,
elem_classes="slider",
position=0.25,
)
Examples(
fn=process_pipe_image,
examples=sorted([
os.path.join("files", "image", name)
for name in os.listdir(os.path.join("files", "image"))
]),
inputs=[image_input],
outputs=[image_output_slider],
cache_examples=False,
directory_name="examples_image",
)
with gr.Tab("Video"):
with gr.Row():
with gr.Column():
video_input = gr.Video(
label="Input Video",
sources=["upload", "webcam"],
)
with gr.Row():
video_submit_btn = gr.Button(
value="Delighting", variant="primary"
)
video_reset_btn = gr.Button(value="Reset")
with gr.Column():
processed_frames = ImageSlider(
label="Realtime Visualization",
type="filepath",
show_download_button=True,
show_share_button=True,
interactive=False,
elem_classes="slider",
position=0.25,
)
video_output_files = gr.Files(
label="Delight outputs",
elem_id="download",
interactive=False,
)
Examples(
fn=process_pipe_video,
examples=sorted([
os.path.join("files", "video", name)
for name in os.listdir(os.path.join("files", "video"))
]),
inputs=[video_input],
outputs=[processed_frames, video_output_files],
directory_name="examples_video",
cache_examples=False,
)
### Image tab
image_submit_btn.click(
fn=process_image_check,
inputs=image_input,
outputs=None,
preprocess=False,
queue=False,
).success(
fn=process_pipe_image,
inputs=[
image_input,
],
outputs=[image_output_slider],
concurrency_limit=1,
)
image_reset_btn.click(
fn=lambda: (
None,
None,
None,
),
inputs=[],
outputs=[
image_input,
image_output_slider,
],
queue=False,
)
### Video tab
video_submit_btn.click(
fn=process_pipe_video,
inputs=[video_input],
outputs=[processed_frames, video_output_files],
concurrency_limit=1,
)
video_reset_btn.click(
fn=lambda: (None, None, None),
inputs=[],
outputs=[video_input, processed_frames, video_output_files],
concurrency_limit=1,
)
### Server launch
demo.queue(
api_open=True,
).launch(
#server_name="0.0.0.0",
#server_port=7860,
share = True
)
def main():
os.system("pip freeze")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
pipe = YOSODiffusePipeline.from_pretrained(
'Stable-X/yoso-delight-v0-4-base', trust_remote_code=True, variant="fp16",
torch_dtype=torch.float16, t_start=0).to(device)
try:
import xformers
pipe.enable_xformers_memory_efficient_attention()
except:
pass # run without xformers
run_demo_server(pipe)
if __name__ == "__main__":
main()
|