Spaces:
Running
Running
File size: 28,157 Bytes
bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 24546c1 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 d51cc1f f95d001 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 24546c1 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 24546c1 bf62248 255a121 24546c1 bf62248 f95d001 bf62248 255a121 bf62248 255a121 bf62248 24546c1 bf62248 255a121 bf62248 255a121 bf62248 24546c1 255a121 24546c1 bf62248 255a121 24546c1 255a121 24546c1 bf62248 255a121 24546c1 255a121 24546c1 255a121 bf62248 255a121 24546c1 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 255a121 bf62248 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 |
# cc @2024 COPAINT
# troubleshooting: groueix@copaint.com
"""
# usage
python copaint.py --input data/input_design.png --back data/back_design.png --outputfolder output
# install dependencies
pip install torch torchvision reportlab PyPDF2 Pillow argparse
# if you are using a mac, you might need to install cairosvg and cairo to load SVG files
pip install cairosvg ; brew install cairo libffi
export PKG_CONFIG_PATH="/usr/local/lib/pkgconfig:/opt/homebrew/lib/pkgconfig:$PKG_CONFIG_PATH"
export DYLD_LIBRARY_PATH="/usr/local/lib:/opt/homebrew/lib:$DYLD_LIBRARY_PATH"
"""
import argparse
import os
import numpy as np
import torchvision
import torch
import time # Add this import for timing
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter, A4
from reportlab.lib.units import inch
import PyPDF2
import logging
from functools import lru_cache
from matplotlib import font_manager
from PIL import Image, ImageDraw, ImageFont
# Configure logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
datefmt='%Y-%m-%d %H:%M:%S'
)
logger = logging.getLogger(__name__)
# Configure debug logging based on environment variable
logger.setLevel(logging.DEBUG)
Image.MAX_IMAGE_PIXELS = None # Removes the limit entirely
fromPIltoTensor = torchvision.transforms.ToTensor()
fromTensortoPIL = torchvision.transforms.ToPILImage()
pre_loaded_images = {}
@lru_cache(maxsize=1)
def get_font(debug=False) -> str:
"""
Get the path to the Bradley Hand font, cached after first call.
"""
start_time = time.time()
good_font_options = ["Avenir Next", "HelveticaNeue", "AdobeClean-Regular", "Arial"] # "Bradley Hand"
font_paths = ["/System/Library/Fonts/Avenir Next.ttc"]
for font_path in font_paths:
if os.path.exists(font_path):
logger.info(f"Found '{font_path}' font")
return font_path
available_fonts = font_manager.findSystemFonts(fontpaths=None, fontext='ttf')
font_path = None
for good_font in good_font_options:
font_path = next((font for font in available_fonts if good_font in font), None)
if font_path:
logger.info(f"Found '{good_font}' font: {font_path}")
break
if font_path is None:
font_path = available_fonts[0]
logger.warning(f"No good fonts found. Using default: {font_path}")
logger.warning("Please install one of the recommended fonts.")
if debug:
logger.debug(f"Font loading took {time.time() - start_time:.4f} seconds")
return font_path
font_path = get_font()
def load_image(image_path, debug=False):
""" Load an image from a file path and return a tensor. """
start_time = time.time()
# check if the path exists
assert os.path.exists(image_path), f"File not found: {image_path}"
# check if the file is an SVG
if image_path.endswith(".svg"):
import cairosvg
import io
# Convert SVG to PNG
with open(image_path, "rb") as svg_file:
png_data = cairosvg.svg2png(file_obj=svg_file)
# Load the PNG data into a Pillow Image
image = Image.open(io.BytesIO(png_data))
else:
image = Image.open(image_path)
# convert to RGBA
image = image.convert("RGBA")
# Apply a white background
background = Image.new("RGB", image.size, (255, 255, 255))
background.paste(image, mask=image.split()[3])
image = background
image_open_time = time.time()
if debug:
logger.debug(f"Image opening took {image_open_time - start_time:.4f} seconds")
image = fromPIltoTensor(image).unsqueeze(0)
logger.info(f"Loaded image of shape {image.shape}, from {image_path}")
if debug:
logger.debug(f"Image to tensor conversion took {time.time() - image_open_time:.4f} seconds")
logger.debug(f"Total image loading took {time.time() - start_time:.4f} seconds")
return image
def save_image(tensor, image_path, debug=False):
""" Save a tensor to an image file. """
start_time = time.time()
logger.info(f"Saving image of shape {tensor.shape} to {image_path}")
image = fromTensortoPIL(tensor.squeeze(0))
conversion_time = time.time()
if debug:
logger.debug(f"Tensor to PIL conversion took {conversion_time - start_time:.4f} seconds")
image.save(image_path)
if debug:
logger.debug(f"Image saving took {time.time() - conversion_time:.4f} seconds")
logger.debug(f"Total save_image took {time.time() - start_time:.4f} seconds")
def save_tensor_to_pdf(tensor, pdf_path, is_front=True, margin=0.25, img_small_side_in_cm=None, a4=False, high_res=False, scale=None, debug=False):
"""
Save a tensor to a PDF, the tensor is assumed to be a single image, and is centered on the page.
"""
start_time = time.time()
image = fromTensortoPIL(tensor.squeeze(0))
img_width, img_height = image.size
# 1 Inch = 72 Points : ad-hoc metric used in typography and the printing industry.
# The US Letter format is US Letter size: 8.5 by 11 inches
W, H = 8.5, 11 # the unit is inch
if a4:
logger.info("Using A4 format")
W, H = 8.27, 11.69 # the unit is inch
page_width_in_pt = (W - 2*margin) * inch
page_height_in_pt = (H - 2*margin) * inch
img_small_side_in_pt = None
img_large_side_in_pt = None
if img_small_side_in_cm is not None:
img_small_side_in_pt = img_small_side_in_cm * inch * 0.393701 # 1 cm = 0.393701 inches
img_large_side_in_pt = img_small_side_in_pt * max(img_width, img_height) / min(img_width, img_height)
assert(img_small_side_in_pt < page_width_in_pt and img_large_side_in_pt < page_height_in_pt), f"Cell size in cm is too large for the page, max in pt unit is {page_width_in_pt}x{page_height_in_pt}, got {img_small_side_in_pt}x{img_large_side_in_pt}. It looks you manually set the size of the cell in cm, but the image is too large for the page, try a smaller cell size."
logger.info(f"Saving tensor of shape {tensor.shape} to {pdf_path}")
# Convert tensor to image
t1 = time.time()
if debug:
logger.debug(f"Tensor to PIL conversion took {time.time() - t1:.4f} seconds")
t2 = time.time()
# Check if image should be rotated
scale_1, rotated = None, True
if scale is not None:
scale_1, rotated = scale
if image.width > image.height and rotated:
logger.info(f"Rotating image. Size in pixels: {image.width}, {image.height}")
image = image.rotate(90, expand=True)
logger.info(f"Rotated image. Size in pixels: {image.width}, {image.height}")
img_width, img_height = image.width, image.height
rotated = True
else:
rotated = False
# check if it's better to maxout width or height
if scale_1 is None:
if img_small_side_in_pt is not None:
scale_1 = img_small_side_in_pt / min(img_width, img_height) # this might go over the page
else:
# Calculate the scaling factor to fit the image within the page
scale_width = page_width_in_pt / img_width
scale_height = page_height_in_pt / img_height
scale_1 = min(scale_width, scale_height) # Choose the smaller scale to preserve aspect ratio
# Calculate the resized image dimensions
new_width = img_width * scale_1
new_height = img_height * scale_1
# Calculate offsets to center the image on the page
x_offset = (page_width_in_pt - new_width) // 2
y_offset = (page_height_in_pt - new_height) // 2
if debug:
logger.debug(f"Image calculations took {time.time() - t2:.4f} seconds")
# Save image to PDF
t3 = time.time()
# Use PNG for high-res mode instead of JPG
image_path = "temp.png" if high_res else "temp.jpg"
ram_folder_linux = "/dev/shm/"
if os.path.exists(ram_folder_linux):
image_path = os.path.join(ram_folder_linux, image_path)
image.save(image_path)
if debug:
logger.debug(f"Temporary image saving took {time.time() - t3:.4f} seconds")
# Create a PDF
t4 = time.time()
if a4:
c = canvas.Canvas(pdf_path, pagesize = A4)
else:
c = canvas.Canvas(pdf_path, pagesize = letter)
c.drawImage(image_path, x_offset+margin*inch, y_offset+margin*inch, width=new_width, height=new_height, preserveAspectRatio=True)
c.save()
if debug:
logger.debug(f"PDF creation took {time.time() - t4:.4f} seconds")
os.remove(image_path)
if debug:
logger.debug(f"Total PDF saving took {time.time() - start_time:.4f} seconds")
return pdf_path, (scale_1, rotated)
def merge_pdf_list(pdfs, output_path, debug=False):
""" Merge a list of PDFs into a single PDF. """
start_time = time.time()
merger = PyPDF2.PdfMerger()
for pdf in pdfs:
merger.append(pdf)
merger.write(output_path)
merger.close()
if debug:
logger.debug(f"PDF merging took {time.time() - start_time:.4f} seconds")
return output_path
def create_image_with_text(text: str = "1", size: int = 400, underline: bool = True, debug=False) -> torch.Tensor:
""" Create an image with text using PIL. Returns a torch tensor. """
start_time = time.time()
# Create a blank image (200x200 pixels, white background)
if isinstance(size, int):
size = (size, size)
image = Image.new("RGB", size, "white")
# Create a drawing object
draw = ImageDraw.Draw(image)
# Set the font (optional)
try:
font = ImageFont.truetype(font_path, size=int(size[1]/1.3)) # Ensure the font is available
except IOError:
font = ImageFont.load_default()
# turn size to 100
# Use textbbox to measure the text dimensions
visual_bbox = draw.textbbox((0, 0), text, font=font)
# (-4, 101, 340, 260)
text_width = visual_bbox[2] - visual_bbox[0] # Width of the text
text_height = visual_bbox[3] - visual_bbox[1] # Height of the text
center_point = (size[0] // 2, size[1] // 2)
top_left_of_BB = (center_point[0] - text_width // 2, center_point[1] - text_height // 2)
baseline = (top_left_of_BB[0] - visual_bbox[0], top_left_of_BB[1] - visual_bbox[1])
visual_bbox = draw.textbbox(baseline, text, font=font)
# draw.rectangle(visual_bbox, outline="red", width=2)
# print(f" text {text} Text width: {text_width}, Text height: {text_height}", f"Image width: {image.width}, Image height: {image.height}", f"Text position: {baseline}")
# # Draw the text
draw.text(baseline, text, fill="black", font=font)
if underline:
# # Add a line under the text
x = baseline[0]
y = visual_bbox[3] + 20
draw.line((x, y, x+text_width, y), fill="black", width=5)
tensor = fromPIltoTensor(image).unsqueeze(0)
if debug and len(text) <= 2: # Only log for short texts (cell numbers) when debugging
logger.debug(f"Creating image with text '{text}' took {time.time() - start_time:.4f} seconds")
return tensor
def create_back_image(h, w, h_cells, w_cells, logo_image, logo_insta_image, unique_identifier, list_of_cell_idx=None, debug=False):
"""
Create back image tensor, of size hxw -
Black pixels at the separation of cells to draw the lines
The logo is in each cell, with the cell number underlined
logo_image : tensor of size 1x3xhxw
"""
logger.info(f"Creating back image of size {h}x{w} for {h_cells}x{w_cells} cells")
start_time = time.time()
num_channels = 3 # do not consider the alpha channel
back_image = torch.ones(1, num_channels, h, w)
# cell size in pixels
cell_h = h // h_cells
cell_w = w // w_cells
# hyperparameters controlling the thickness of the lines and the logo size
line_thickness = min(cell_h, cell_w) // 100
logo_size = min(cell_h, cell_w) // 4
logo_offset = min(cell_h, cell_w) // 50
number_size = min(cell_h, cell_w) // 2
if debug:
logger.debug(f"thickness of the lines: {line_thickness}")
logger.debug(f"Initialization took {time.time() - start_time:.4f} seconds")
# Create the grid lines
grid_start_time = time.time()
line_half_thickness = line_thickness // 2
for i in range(h_cells):
for j in range(w_cells):
h0 = i * cell_h # height start
h1 = (i + 1) * cell_h # height end
w0 = j * cell_w # width start
w1 = (j + 1) * cell_w # width end
if h0+line_half_thickness < h:
back_image[:, :num_channels, h0:(h0+line_half_thickness), :] = 0
if w0+line_half_thickness < w:
back_image[:, :num_channels, :, w0:(w0+line_half_thickness)] = 0
if h1 - line_half_thickness > 0:
back_image[:, :num_channels, (h1-line_half_thickness):h1, :] = 0
if w1 - line_half_thickness > 0:
back_image[:, :num_channels, :, (w1-line_half_thickness):w1] = 0
if debug:
logger.debug(f"Creating grid lines took {time.time() - grid_start_time:.4f} seconds")
# Resize logo for all cells
logo_resize_time = time.time()
_, _, h, w = logo_image.size()
scale_logo = min(logo_size / h, logo_size / w)
new_h, new_w = int(h * scale_logo), int(w * scale_logo)
logo_image_resized = torch.nn.functional.interpolate(logo_image, size=(new_h, new_w), mode='bilinear')
t_insta = time.time()
_, _, h_insta, w_insta = logo_insta_image.size()
scale_insta = min(logo_size / h_insta, logo_size / w_insta) / 5
new_h_insta, new_w_insta = int(h_insta * scale_insta), int(w_insta * scale_insta)
logo_insta_image_resized = torch.nn.functional.interpolate(logo_insta_image, size=(new_h_insta, new_w_insta), mode='bilinear')
if debug:
logger.debug(f"Logo resizing took {time.time() - logo_resize_time:.4f} seconds ({time.time() - t_insta:.4f} for insta and {t_insta - logo_resize_time:.4f} for copaint logo)")
# save logo_insta_image_resized
save_image(logo_insta_image_resized, "logo_insta_image_resized.png", debug=debug)
# Add content to cells
cell_content_time = time.time()
letscopaint = create_image_with_text("copaint.art", underline=False,
size=(int(0.8*number_size), number_size//8),
debug=debug)
# add unique identifier
unique_identifier_size_w = number_size
unique_identifier_size_h = number_size // 4
image_with_unique_identifier = create_image_with_text(unique_identifier, underline=False,
size=(unique_identifier_size_w, unique_identifier_size_h),
debug=debug)
for i in range(h_cells):
for j in range(w_cells):
h0 = i * cell_h # height start
h1 = (i + 1) * cell_h # height end
w0 = j * cell_w # width start
w1 = (j + 1) * cell_w # width end
# add logo at the bottom right of the cell
logo_size_h, logo_size_w = logo_image_resized.shape[2:]
back_image[:, :, h1-logo_size_h-logo_offset:h1-logo_offset, w1-logo_size_w-logo_offset:w1-logo_offset] = logo_image_resized[:, :num_channels, :, :]
# add cell number at the center of the cell
# invert cell number to match the order of the canvas. 1 is at the top right, and w_cells is at the top left
if list_of_cell_idx is not None:
logger.info(f"list_of_cell_idx: {list_of_cell_idx}")
if list_of_cell_idx is not None:
cell_number = list_of_cell_idx[i*w_cells+j]
else:
cell_number = i*w_cells+(w_cells-j)
image_with_number = create_image_with_text(f"{cell_number}", size=number_size, debug=debug)
start_h_big = h0 + (h1 - h0) // 2 - number_size // 2
start_w_big = w0 + (w1 - w0) // 2 - number_size // 2
back_image[:, :, start_h_big:start_h_big+number_size, start_w_big:start_w_big+number_size] = image_with_number[:, :num_channels, :, :]
start_h = h0 + unique_identifier_size_h // 2 # Fix
start_w = w0 + unique_identifier_size_h // 2 # Fix
back_image[:, :, start_h:start_h+unique_identifier_size_h, start_w:start_w+unique_identifier_size_w] = image_with_unique_identifier[:, :num_channels, :, :]
start_letscopaint_h = h1-logo_offset # Fix
start_letscopaint_w = w0 + unique_identifier_size_h // 16 # Fix
back_image[:, :, start_letscopaint_h-(number_size//8):start_letscopaint_h, start_letscopaint_w:start_letscopaint_w+(int(0.8*number_size))] = letscopaint[:, :num_channels, :, :]
# add instagram logo at the bottom left of the cell
_, _, h_insta, w_insta = logo_insta_image_resized.shape
start_insta_h = h1-logo_offset # Fix
start_insta_w = w0 + unique_identifier_size_h // 6 # Fix
back_image[:, :, start_insta_h-(number_size//8):start_insta_h-(number_size//8)+h_insta, start_insta_w:start_insta_w+w_insta] = logo_insta_image_resized[:, :num_channels, :, :]
if debug:
logger.debug(f"Adding content to cells took {time.time() - cell_content_time:.4f} seconds")
logger.debug(f"Created back image of shape {back_image.shape}")
logger.debug(f"Total back image creation took {time.time() - start_time:.4f} seconds")
return back_image
def image_to_pdf_core(input_image, file_name, logo_image, outputfolder, h_cells, w_cells, unique_identifier="Mauricette", cell_size_in_cm=None, a4=False, high_res=False, list_of_cell_idx=None, scale=None, debug=False):
overall_start_time = time.time()
os.makedirs(outputfolder, exist_ok=True)
scale_1, scale_2, scale_3, scale_4 = None, None, None, None
if scale is not None:
scale_1, scale_2, scale_3, scale_4 = scale
# Load image
t1 = time.time()
if not isinstance(input_image, torch.Tensor):
if input_image in pre_loaded_images:
image = pre_loaded_images[input_image]
logger.info(f"Loaded image from cache: {input_image}")
else:
image = load_image(input_image, debug=debug)
pre_loaded_images[input_image] = image
else:
image = input_image
if debug:
logger.debug(f"Image loading took {time.time() - t1:.4f} seconds")
_, c, h, w = image.shape
logger.info(f"Image shape: {image.shape}")
t1_2 = time.time()
if logo_image in pre_loaded_images:
logo_image = pre_loaded_images[logo_image]
logger.info(f"Loaded logo copaint image from cache: {logo_image}")
else:
logo_image = load_image(logo_image, debug=debug)
pre_loaded_images[logo_image] = logo_image
if debug:
logger.debug(f"Logo copaint Image loading took {time.time() - t1_2:.4f} seconds")
t1_3 = time.time()
logo_insta_path = "./copaint/static/logo_instagram.png"
if logo_insta_path in pre_loaded_images:
logo_insta_image = pre_loaded_images[logo_insta_path]
logger.info(f"Loaded logo instagram image from cache: {logo_insta_path}")
else:
logo_insta_image = load_image(logo_insta_path, debug=debug)
pre_loaded_images[logo_insta_path] = logo_insta_image
if debug:
logger.debug(f"Logo instagram Image loading took {time.time() - t1_3:.4f} seconds")
# # Quick check that the greatest dimension corresponds to the greatest number of cells
# if h > w and h_cells < w_cells:
# print("Swapping h_cells and w_cells")
# h_cells, w_cells = w_cells, h_cells
# elif w > h and w_cells < h_cells:
# print("Swapping h_cells and w_cells")
# h_cells, w_cells = w_cells, h_cells
# Create back image
t2 = time.time()
multiplier_w = max(1, 10000 // w)
multiplier_h = max(1, 10000 // h)
if scale_3 is None:
scale_3 = max(multiplier_w, multiplier_h)
logger.info(f"Creating back image with {h*scale_3} x {w*scale_3} pixels for {h_cells} x {w_cells} cells")
back_image = create_back_image(h*scale_3, w*scale_3, h_cells, w_cells, logo_image, logo_insta_image,
unique_identifier=unique_identifier, list_of_cell_idx=list_of_cell_idx, debug=debug)
if debug:
save_image(back_image, os.path.join(outputfolder, "back_image.png"), debug=debug)
logger.debug(f"Back image creation and saving took {time.time() - t2:.4f} seconds")
# Save to PDF
t3 = time.time()
os.makedirs(outputfolder, exist_ok=True)
output_path_front = os.path.join(outputfolder, "output_front.pdf")
output_path_back = os.path.join(outputfolder, "output_back.pdf")
img_small_side_in_cm = None
if cell_size_in_cm is not None:
# Why Min? Cells are not neccearily square, depending on the aspect ratio of the image, and the number of H and W cells, so we assume cell_size_in_cm is the smallest side of the cell.
logger.info(f"cell_size_in_cm: {cell_size_in_cm}")
min_cells = min(h_cells, w_cells)
img_small_side_in_cm = cell_size_in_cm * min_cells # smallest side in cm.
# print image and back image shapes
if debug:
logger.debug(f"Image shape: {image.shape}")
logger.debug(f"Back image shape: {back_image.shape}")
# Only resize back image if not high-res
if not high_res:
back_image_h, back_image_w = back_image.shape[2:]
scale_h = 4096 / back_image_h
if scale_4 is None:
scale_4 = scale_h
back_image = torch.nn.functional.interpolate(back_image, scale_factor=scale_4, mode='bilinear')
_, scale_1 = save_tensor_to_pdf(image, output_path_front, is_front=True, img_small_side_in_cm=img_small_side_in_cm, a4=a4, high_res=high_res, scale=scale_1, debug=debug)
_, scale_2 = save_tensor_to_pdf(back_image, output_path_back, is_front=False, img_small_side_in_cm=img_small_side_in_cm, a4=a4, high_res=high_res, scale=scale_2, debug=debug)
scale = (scale_1 , scale_2, scale_3, scale_4)
if debug:
logger.debug(f"PDF creation took {time.time() - t3:.4f} seconds")
# concatenate pdfs
t4 = time.time()
logger.info("Concatenating PDFs")
output_path = os.path.join(outputfolder, f"{file_name}_{h_cells}x{w_cells}_copaint.pdf")
merge_pdf_list([output_path_front, output_path_back], output_path, debug=debug)
# clean unnecessary files
os.remove(output_path_front)
os.remove(output_path_back)
if debug:
logger.debug(f"PDF concatenation and cleanup took {time.time() - t4:.4f} seconds")
logger.info(f"Total processing time: {time.time() - overall_start_time:.4f} seconds")
logger.info(f"Done! Output saved to {output_path}")
return output_path, scale
def image_to_pdf(input_image, logo_image, outputfolder, h_cells, w_cells, unique_identifier="Mauricette", cell_size_in_cm=None, a4=False, high_res=False, min_cell_size_in_cm=2, list_of_cell_idx=None, debug=False):
"""
Create a copaint PDF from an image and a logo.
"""
logger.info(f"h_cells: {h_cells}, w_cells: {w_cells}, a4: {a4}")
image = load_image(input_image, debug=debug)
_, c, h, w = image.shape
file_name = os.path.basename(input_image)
# Check if the image needs to be split to fit in the page.
if cell_size_in_cm is not None:
min_cell_size_in_cm = cell_size_in_cm
# The US Letter format is US Letter size: 8.5 by 11 inches
W, H = 8.5, 11 # the unit is inch
if a4:
logger.info("Using A4 format")
W, H = 8.27, 11.69 # the unit is inch
margin = 0.25 # hardcoded margin
page_width_in_pt = (W - 2 * margin) * inch
page_height_in_pt = (H - 2 * margin) * inch
max_cell_per_page_h = h_cells
max_cell_per_page_w = w_cells
established_cell_size = False
while not established_cell_size:
img_small_side_in_pt = min(max_cell_per_page_h, max_cell_per_page_w) * min_cell_size_in_cm * inch * 0.393701 # 1 cm = 0.393701 inches
minimum_is_width = min(w, h) == w
img_large_side_in_pt = img_small_side_in_pt * max(w, h) / min(w, h)
logger.info(f"img_small_side_in_pt: {img_small_side_in_pt}, img_large_side_in_pt: {img_large_side_in_pt}")
logger.info(f"page_width_in_pt: {page_width_in_pt}, page_height_in_pt: {page_height_in_pt}")
if img_large_side_in_pt < page_height_in_pt and img_small_side_in_pt < page_width_in_pt:
established_cell_size = True
else:
max_cell_per_page_h = max_cell_per_page_h // 2
max_cell_per_page_w = max_cell_per_page_w // 2
logger.info(f"Decreasing max_cell_per_page to {max_cell_per_page_h}x{max_cell_per_page_w}")
divide_factor_h = int(np.ceil(h_cells / max_cell_per_page_h))
divide_factor_w = int(np.ceil(w_cells / max_cell_per_page_w))
logger.info(f"divide_factor_h: {divide_factor_h}, divide_factor_w: {divide_factor_w}")
copaint_pdfs = []
scale = None
for i in range(divide_factor_h):
for j in range(divide_factor_w):
cell_h_start = i * max_cell_per_page_h
cell_h_end = min((i + 1) * max_cell_per_page_h, h_cells)
cell_w_start = j * max_cell_per_page_w
cell_w_end = min((j + 1) * max_cell_per_page_w, w_cells)
list_of_cell_idx = [cell_h_idx * w_cells + (w_cells-cell_w_idx) for cell_h_idx in range(cell_h_start, cell_h_end) for cell_w_idx in range(cell_w_start, cell_w_end)]
logger.info(f"cell_h_start: {cell_h_start}, cell_h_end: {cell_h_end}, cell_w_start: {cell_w_start}, cell_w_end: {cell_w_end}")
h_cells_new = cell_h_end - cell_h_start
w_cells_new = cell_w_end - cell_w_start
file_name_new = f"{file_name}_{i}x{j}"
px_h_start = int(cell_h_start * h / h_cells)
px_h_end = int(cell_h_end * h / h_cells)
px_w_start = int(cell_w_start * w / w_cells)
px_w_end = int(cell_w_end * w / w_cells)
image_new = image[:, :, px_h_start:px_h_end, px_w_start:px_w_end]
pdf_path, new_scale = image_to_pdf_core(image_new, file_name_new, logo_image, outputfolder, h_cells_new, w_cells_new, unique_identifier, cell_size_in_cm, a4, high_res, list_of_cell_idx=list_of_cell_idx, scale=scale, debug=debug)
if scale is None:
scale = new_scale
copaint_pdfs.append(pdf_path)
# Merge the copaint PDFs
output_path = os.path.join(outputfolder, "copaint-design.pdf")
merge_pdf_list(copaint_pdfs, output_path, debug=debug)
# clean unnecessary files
for pdf in copaint_pdfs:
os.remove(pdf)
logger.info(f"Done! Final output saved to {output_path}")
return output_path
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='CoPaint')
parser.add_argument('--input_image', type=str, default='./data/bear.png', help='input image')
parser.add_argument('--copaint_logo', type=str, default='./data/logo_copaint.png', help='copaint logo')
parser.add_argument('--outputfolder', type=str, default='output/', help='output image')
parser.add_argument('--h_cells', type=int, help='number of cells in height', default=9)
parser.add_argument('--w_cells', type=int, help='number of cells in width', default=6)
parser.add_argument('--debug', action='store_true', help='show timing information')
# done adding arguments
args = parser.parse_args()
image_to_pdf(args.input_image, args.copaint_logo, args.outputfolder, args.h_cells, args.w_cells, cell_size_in_cm=None, debug=args.debug)
|