Spaces:
Running
Running
File size: 13,090 Bytes
6c85792 c8cb9bb 6c85792 45faff1 6c85792 a5ca5a6 a18a2d9 a5ca5a6 a18a2d9 a5ca5a6 774d798 a5ca5a6 344868a a5ca5a6 ec107df 6c85792 8d01019 6c85792 21fc719 6c85792 8d01019 a5ca5a6 bb4525d 45faff1 f73b71e c8cb9bb f73b71e c8cb9bb f73b71e 8202902 a18a2d9 f73b71e 0e4c0f7 f73b71e c8cb9bb f73b71e 3079cc3 f73b71e 3079cc3 f73b71e 3079cc3 f73b71e a5ca5a6 2976d00 8997d74 a5ca5a6 fc4f76a a5ca5a6 60be08d 6c85792 60be08d 6c85792 bf8d6fe bb4525d 856d473 bf8d6fe 5a166e2 856d473 45faff1 f73b71e bf8d6fe 6c85792 9251ce3 6c85792 de5109e 6c85792 cd73099 6c85792 3f34a00 cd73099 3f34a00 cd73099 6521610 5eb2692 b5bbd1f d8dc6b8 5eb2692 d8dc6b8 6c85792 6521610 99108df 7942d31 6521610 7942d31 6521610 bb01b85 99108df 6521610 99108df 6521610 3f34a00 fc4f76a 6c85792 fc4f76a 6c85792 fc4f76a 6c85792 e2718c0 93b8a3e bb4525d e2718c0 6c85792 e2718c0 6c85792 e2718c0 f9e0e97 9251ce3 fc4f76a |
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 |
import gradio as gr
import PIL
from PIL import Image
import numpy as np
import os
import uuid
import torch
from torch import autocast
import cv2
from io import BytesIO
import requests
import PIL
from PIL import Image
import numpy as np
import os
import uuid
import torch
from torch import autocast
import cv2
from matplotlib import pyplot as plt
from torchvision import transforms
from diffusers import DiffusionPipeline
import io
import logging
import multiprocessing
import random
import time
import imghdr
from pathlib import Path
from typing import Union
from loguru import logger
from lama_cleaner.model_manager import ModelManager
from lama_cleaner.schema import Config
try:
torch._C._jit_override_can_fuse_on_cpu(False)
torch._C._jit_override_can_fuse_on_gpu(False)
torch._C._jit_set_texpr_fuser_enabled(False)
torch._C._jit_set_nvfuser_enabled(False)
except:
pass
from lama_cleaner.helper import (
load_img,
numpy_to_bytes,
resize_max_size,
)
NUM_THREADS = str(multiprocessing.cpu_count())
# fix libomp problem on windows https://github.com/Sanster/lama-cleaner/issues/56
os.environ["KMP_DUPLICATE_LIB_OK"] = "True"
os.environ["OMP_NUM_THREADS"] = NUM_THREADS
os.environ["OPENBLAS_NUM_THREADS"] = NUM_THREADS
os.environ["MKL_NUM_THREADS"] = NUM_THREADS
os.environ["VECLIB_MAXIMUM_THREADS"] = NUM_THREADS
os.environ["NUMEXPR_NUM_THREADS"] = NUM_THREADS
if os.environ.get("CACHE_DIR"):
os.environ["TORCH_HOME"] = os.environ["CACHE_DIR"]
os.environ["TORCH_HOME"] = './'
BUILD_DIR = os.environ.get("LAMA_CLEANER_BUILD_DIR", "app/build")
from share_btn import community_icon_html, loading_icon_html, share_js
HF_TOKEN_SD = os.environ.get('HF_TOKEN_SD')
device = "cuda" if torch.cuda.is_available() else "cpu"
print(f'device = {device}')
def get_image_ext(img_bytes):
w = imghdr.what("", img_bytes)
if w is None:
w = "jpeg"
return w
def diffuser_callback(i, t, latents):
pass
def preprocess_image(image):
w, h = image.size
w, h = map(lambda x: x - x % 32, (w, h)) # resize to integer multiple of 32
image = image.resize((w, h), resample=PIL.Image.LANCZOS)
image = np.array(image).astype(np.float32) / 255.0
image = image[None].transpose(0, 3, 1, 2)
image = torch.from_numpy(image)
return 2.0 * image - 1.0
def preprocess_mask(mask):
mask = mask.convert("L")
w, h = mask.size
w, h = map(lambda x: x - x % 32, (w, h)) # resize to integer multiple of 32
mask = mask.resize((w // 8, h // 8), resample=PIL.Image.NEAREST)
mask = np.array(mask).astype(np.float32) / 255.0
mask = np.tile(mask, (4, 1, 1))
mask = mask[None].transpose(0, 1, 2, 3) # what does this step do?
mask = 1 - mask # repaint white, keep black
mask = torch.from_numpy(mask)
return mask
def model_process(init_image, mask):
global model
# input = request.files
# RGB
# origin_image_bytes = input["image"].read()
print(f'liuyz_2_here_')
# image, alpha_channel = load_img(origin_image_bytes)
# Origin image shape: (512, 512, 3)
original_shape = init_image.shape
interpolation = cv2.INTER_CUBIC
# form = request.form
size_limit = 1080 # : Union[int, str] = form.get("sizeLimit", "1080")
if size_limit == "Original":
size_limit = max(image.shape)
else:
size_limit = int(size_limit)
config = Config(
ldm_steps=25,
ldm_sampler='plms',
zits_wireframe=True,
hd_strategy='Original',
hd_strategy_crop_margin=196,
hd_strategy_crop_trigger_size=1280,
hd_strategy_resize_limit=2048,
prompt='',
use_croper=False,
croper_x=0,
croper_y=0,
croper_height=512,
croper_width=512,
sd_mask_blur=5,
sd_strength=0.75,
sd_steps=50,
sd_guidance_scale=7.5,
sd_sampler='ddim',
sd_seed=42,
cv2_flag='INPAINT_NS',
cv2_radius=5,
)
if config.sd_seed == -1:
config.sd_seed = random.randint(1, 999999999)
# logger.info(f"Origin image shape: {original_shape}")
print(f"Origin image shape: {original_shape}")
image = resize_max_size(image, size_limit=size_limit, interpolation=interpolation)
# logger.info(f"Resized image shape: {image.shape}")
print(f"Resized image shape: {image.shape}")
mask, _ = load_img(input["mask"].read(), gray=True)
mask = resize_max_size(mask, size_limit=size_limit, interpolation=interpolation)
start = time.time()
res_np_img = model(image, mask, config)
logger.info(f"process time: {(time.time() - start) * 1000}ms")
torch.cuda.empty_cache()
if alpha_channel is not None:
if alpha_channel.shape[:2] != res_np_img.shape[:2]:
alpha_channel = cv2.resize(
alpha_channel, dsize=(res_np_img.shape[1], res_np_img.shape[0])
)
res_np_img = np.concatenate(
(res_np_img, alpha_channel[:, :, np.newaxis]), axis=-1
)
ext = get_image_ext(origin_image_bytes)
return ext
model = ModelManager(
name='lama',
device=device,
# hf_access_token=HF_TOKEN_SD,
# sd_disable_nsfw=False,
# sd_cpu_textencoder=True,
# sd_run_local=True,
# callback=diffuser_callback,
)
'''
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", dtype=torch.float16, revision="fp16", use_auth_token=auth_token).to(device)
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
transforms.Resize((512, 512)),
])
'''
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):
print(f'liuyz_0_', dict)
init_image = dict["image"] # .convert("RGB") #.resize((512, 512))
target_size = (init_image.shape[0], init_image.shape[1])
print(f'liuyz_1_', init_image, target_size)
print(f'liuyz_2_', init_image.convert("RGB"))
print(f'liuyz_3_', init_image.convert("RGB").resize((512, 512)))
mask = dict["mask"] # .convert("RGB") #.resize((512, 512))
# output = model_process(init_image, mask)
output = None # output.images[0]
# output = pipe(prompt = prompt, image=init_image, mask_image=mask,guidance_scale=7.5)
return output #, gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)
print(f'liuyz_400_here_')
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);
}
}
#share-btn-container {
display: flex; padding-left: 0.5rem !important; padding-right: 0.5rem !important; background-color: #000000; justify-content: center; align-items: center; border-radius: 9999px !important; width: 13rem;
}
#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: 0.25rem !important; padding-bottom: 0.25rem !important;
}
#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;
}
'''
'''
sketchpad = Sketchpad()
imageupload = ImageUplaod()
interface = gr.Interface(fn=predict, inputs="image", outputs="image", sketchpad, imageupload)
interface.launch(share=True)
'''
'''
# gr.Interface(fn=predict, inputs="image", outputs="image").launch(share=True)
image = gr.Image(source='upload', tool='sketch', type="pil", label="Upload")# .style(height=400)
image_blocks = gr.Interface(
fn=predict,
inputs=image,
outputs=image,
# examples=[["cheetah.jpg"]],
)
image_blocks.launch(inline=True)
import gradio as gr
def greet(dict, name, is_morning, temperature):
image = dict['image']
target_size = (image.shape[0], image.shape[1])
print(f'liuyz_1_', target_size)
salutation = "Good morning" if is_morning else "Good evening"
greeting = f"{salutation} {name}. It is {temperature} degrees today"
celsius = (temperature - 32) * 5 / 9
return image, greeting, round(celsius, 2)
image = gr.Image(source='upload', tool='sketch', label="上传")# .style(height=400)
demo = gr.Interface(
fn=greet,
inputs=[image, "text", "checkbox", gr.Slider(0, 100)],
outputs=['image', "text", "number"],
)
demo.launch()
'''
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", label="Upload") #.style(height=400)
with gr.Row(elem_id="prompt-container").style(mobile_collapse=False, equal_height=True):
prompt = gr.Textbox(placeholder = 'Your prompt (what you want in place of what is erased)', show_label=False, elem_id="input-text")
btn = gr.Button("Done!").style(
margin=True,
rounded=(True, True, True, True),
full_width=True,
)
with gr.Column():
image_out = gr.Image(label="Output", elem_id="output-img").style(height=400)
with gr.Group(elem_id="share-btn-container"):
community_icon = gr.HTML(community_icon_html, visible=False)
loading_icon = gr.HTML(loading_icon_html, visible=False)
share_button = gr.Button("Share to community", elem_id="share-btn", visible=False)
btn.click(fn=predict, inputs=[image, prompt], outputs=[image_out, community_icon, loading_icon, share_button])
#btn.click(fn=predict, inputs=[image], outputs=[image]) #, community_icon, loading_icon, share_button])
share_button.click(None, [], [], _js=share_js)
gr.HTML(
"""
<div class="footer">
<p>Model by <a href="https://huggingface.co/runwayml" style="text-decoration: underline;" target="_blank">RunwayML</a> - Gradio Demo by 🤗 Hugging Face
</p>
</div>
<div class="acknowledgments">
<p><h4>LICENSE</h4>
The model is licensed with a <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" style="text-decoration: underline;" target="_blank">CreativeML Open RAIL-M</a> license. The authors claim no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in this license. The license forbids you from sharing any content that violates any laws, produce any harm to a person, disseminate any personal information that would be meant for harm, spread misinformation and target vulnerable groups. For the full list of restrictions please <a href="https://huggingface.co/spaces/CompVis/stable-diffusion-license" target="_blank" style="text-decoration: underline;" target="_blank">read the license</a></p>
<p><h4>Biases and content acknowledgment</h4>
Despite how impressive being able to turn text into image is, beware to the fact that this model may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography and violence. The model was trained on the <a href="https://laion.ai/blog/laion-5b/" style="text-decoration: underline;" target="_blank">LAION-5B dataset</a>, which scraped non-curated image-text-pairs from the internet (the exception being the removal of illegal content) and is meant for research purposes. You can read more in the <a href="https://huggingface.co/CompVis/stable-diffusion-v1-4" style="text-decoration: underline;" target="_blank">model card</a></p>
</div>
"""
)
image_blocks.launch()
|