stable-diffusion-webui/modules/textual_inversion/preprocess.py

106 lines
3.5 KiB
Python
Raw Normal View History

import os
from PIL import Image, ImageOps
import platform
import sys
import tqdm
from modules import shared, images
2022-10-10 13:35:35 +00:00
def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption):
width = process_width
height = process_height
src = os.path.abspath(process_src)
dst = os.path.abspath(process_dst)
2022-10-05 21:11:32 +00:00
assert src != dst, 'same directory specified as source and destination'
os.makedirs(dst, exist_ok=True)
files = os.listdir(src)
shared.state.textinfo = "Preprocessing..."
shared.state.job_count = len(files)
if process_caption:
shared.interrogator.load()
def save_pic_with_caption(image, index):
if process_caption:
caption = "-" + shared.interrogator.generate_caption(image)
caption = sanitize_caption(os.path.join(dst, f"{index:05}-{subindex[0]}"), caption, ".png")
else:
caption = filename
caption = os.path.splitext(caption)[0]
caption = os.path.basename(caption)
image.save(os.path.join(dst, f"{index:05}-{subindex[0]}{caption}.png"))
subindex[0] += 1
def save_pic(image, index):
save_pic_with_caption(image, index)
if process_flip:
save_pic_with_caption(ImageOps.mirror(image), index)
for index, imagefile in enumerate(tqdm.tqdm(files)):
subindex = [0]
filename = os.path.join(src, imagefile)
img = Image.open(filename).convert("RGB")
if shared.state.interrupted:
break
ratio = img.height / img.width
is_tall = ratio > 1.35
is_wide = ratio < 1 / 1.35
if process_split and is_tall:
2022-10-10 13:35:35 +00:00
img = img.resize((width, height * img.height // img.width))
2022-10-10 13:35:35 +00:00
top = img.crop((0, 0, width, height))
save_pic(top, index)
2022-10-10 13:35:35 +00:00
bot = img.crop((0, img.height - height, width, img.height))
save_pic(bot, index)
elif process_split and is_wide:
2022-10-10 13:35:35 +00:00
img = img.resize((width * img.width // img.height, height))
2022-10-10 13:35:35 +00:00
left = img.crop((0, 0, width, height))
save_pic(left, index)
2022-10-10 13:35:35 +00:00
right = img.crop((img.width - width, 0, img.width, height))
save_pic(right, index)
else:
2022-10-10 13:35:35 +00:00
img = images.resize_image(1, img, width, height)
save_pic(img, index)
shared.state.nextjob()
if process_caption:
shared.interrogator.send_blip_to_ram()
def sanitize_caption(base_path, original_caption, suffix):
operating_system = platform.system().lower()
if (operating_system == "windows"):
invalid_path_characters = "\\/:*?\"<>|"
max_path_length = 259
else:
invalid_path_characters = "/" #linux/macos
max_path_length = 1023
caption = original_caption
for invalid_character in invalid_path_characters:
caption = caption.replace(invalid_character, "")
fixed_path_length = len(base_path) + len(suffix)
if fixed_path_length + len(caption) <= max_path_length:
return caption
caption_tokens = caption.split()
new_caption = ""
for token in caption_tokens:
last_caption = new_caption
new_caption = new_caption + token + " "
if (len(new_caption) + fixed_path_length - 1 > max_path_length):
break
print(f"\nPath will be too long. Truncated caption: {original_caption}\nto: {last_caption}", file=sys.stderr)
return last_caption.strip()