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

133 lines
4.3 KiB
Python
Raw Normal View History

import os
from PIL import Image, ImageOps
2022-10-20 07:53:46 +00:00
import math
import platform
import sys
import tqdm
import time
from modules import shared, images
from modules.shared import opts, cmd_opts
if cmd_opts.deepdanbooru:
import modules.deepbooru as deepbooru
def preprocess(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False):
try:
if process_caption:
shared.interrogator.load()
if process_caption_deepbooru:
db_opts = deepbooru.create_deepbooru_opts()
db_opts[deepbooru.OPT_INCLUDE_RANKS] = False
deepbooru.create_deepbooru_process(opts.interrogate_deepbooru_score_threshold, db_opts)
preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru)
finally:
if process_caption:
shared.interrogator.send_blip_to_ram()
if process_caption_deepbooru:
deepbooru.release_process()
def preprocess_work(process_src, process_dst, process_width, process_height, process_flip, process_split, process_caption, process_caption_deepbooru=False):
2022-10-10 13:35:35 +00:00
width = process_width
height = process_height
src = os.path.abspath(process_src)
dst = os.path.abspath(process_dst)
2022-10-20 07:53:46 +00:00
split_threshold = 0.5
overlap_ratio = 0.2
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)
def save_pic_with_caption(image, index):
caption = ""
if process_caption:
caption += shared.interrogator.generate_caption(image)
if process_caption_deepbooru:
if len(caption) > 0:
caption += ", "
caption += deepbooru.get_tags_from_process(image)
filename_part = filename
filename_part = os.path.splitext(filename_part)[0]
filename_part = os.path.basename(filename_part)
basename = f"{index:05}-{subindex[0]}-{filename_part}"
image.save(os.path.join(dst, f"{basename}.png"))
if len(caption) > 0:
with open(os.path.join(dst, f"{basename}.txt"), "w", encoding="utf8") as file:
file.write(caption)
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)
2022-10-20 07:53:46 +00:00
def split_pic(image, inverse_xy):
if inverse_xy:
from_w, from_h = image.height, image.width
to_w, to_h = height, width
else:
from_w, from_h = image.width, image.height
to_w, to_h = width, height
h = from_h * to_w // from_w
if inverse_xy:
image = image.resize((h, to_w))
else:
image = image.resize((to_w, h))
split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio)))
y_step = (h - to_h) / (split_count - 1)
for i in range(split_count):
y = int(y_step * i)
if inverse_xy:
splitted = image.crop((y, 0, y + to_h, to_w))
else:
splitted = image.crop((0, y, to_w, y + to_h))
yield splitted
for index, imagefile in enumerate(tqdm.tqdm(files)):
subindex = [0]
filename = os.path.join(src, imagefile)
2022-10-11 08:32:46 +00:00
try:
img = Image.open(filename).convert("RGB")
except Exception:
continue
if shared.state.interrupted:
break
2022-10-20 07:53:46 +00:00
if img.height > img.width:
ratio = (img.width * height) / (img.height * width)
inverse_xy = False
else:
ratio = (img.height * width) / (img.width * height)
inverse_xy = True
2022-10-20 07:53:46 +00:00
if process_split and ratio < 1.0 and ratio <= split_threshold:
for splitted in split_pic(img, inverse_xy):
save_pic(splitted, 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()