File size: 9,888 Bytes
6cf4883
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
from PIL import Image, ImageOps
import math
import platform
import sys
import tqdm
import time

from modules import paths, shared, images, deepbooru
from modules.shared import opts, cmd_opts
from modules.textual_inversion import autocrop


def preprocess(id_task, process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
    try:
        if process_caption:
            shared.interrogator.load()

        if process_caption_deepbooru:
            deepbooru.model.start()

        preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug, process_multicrop, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold)

    finally:

        if process_caption:
            shared.interrogator.send_blip_to_ram()

        if process_caption_deepbooru:
            deepbooru.model.stop()


def listfiles(dirname):
    return os.listdir(dirname)


class PreprocessParams:
    src = None
    dstdir = None
    subindex = 0
    flip = False
    process_caption = False
    process_caption_deepbooru = False
    preprocess_txt_action = None


def save_pic_with_caption(image, index, params: PreprocessParams, existing_caption=None):
    caption = ""

    if params.process_caption:
        caption += shared.interrogator.generate_caption(image)

    if params.process_caption_deepbooru:
        if len(caption) > 0:
            caption += ", "
        caption += deepbooru.model.tag_multi(image)

    filename_part = params.src
    filename_part = os.path.splitext(filename_part)[0]
    filename_part = os.path.basename(filename_part)

    basename = f"{index:05}-{params.subindex}-{filename_part}"
    image.save(os.path.join(params.dstdir, f"{basename}.png"))

    if params.preprocess_txt_action == 'prepend' and existing_caption:
        caption = existing_caption + ' ' + caption
    elif params.preprocess_txt_action == 'append' and existing_caption:
        caption = caption + ' ' + existing_caption
    elif params.preprocess_txt_action == 'copy' and existing_caption:
        caption = existing_caption

    caption = caption.strip()

    if len(caption) > 0:
        with open(os.path.join(params.dstdir, f"{basename}.txt"), "w", encoding="utf8") as file:
            file.write(caption)

    params.subindex += 1


def save_pic(image, index, params, existing_caption=None):
    save_pic_with_caption(image, index, params, existing_caption=existing_caption)

    if params.flip:
        save_pic_with_caption(ImageOps.mirror(image), index, params, existing_caption=existing_caption)


def split_pic(image, inverse_xy, width, height, overlap_ratio):
    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

# not using torchvision.transforms.CenterCrop because it doesn't allow float regions
def center_crop(image: Image, w: int, h: int):
    iw, ih = image.size
    if ih / h < iw / w:
        sw = w * ih / h
        box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih
    else:
        sh = h * iw / w
        box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2
    return image.resize((w, h), Image.Resampling.LANCZOS, box)


def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold):
    iw, ih = image.size
    err = lambda w, h: 1-(lambda x: x if x < 1 else 1/x)(iw/ih/(w/h))
    wh = max(((w, h) for w in range(mindim, maxdim+1, 64) for h in range(mindim, maxdim+1, 64)
        if minarea <= w * h <= maxarea and err(w, h) <= threshold),
        key= lambda wh: (wh[0]*wh[1], -err(*wh))[::1 if objective=='Maximize area' else -1],
        default=None
    )
    return wh and center_crop(image, *wh)
    

def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
    width = process_width
    height = process_height
    src = os.path.abspath(process_src)
    dst = os.path.abspath(process_dst)
    split_threshold = max(0.0, min(1.0, split_threshold))
    overlap_ratio = max(0.0, min(0.9, overlap_ratio))

    assert src != dst, 'same directory specified as source and destination'

    os.makedirs(dst, exist_ok=True)

    files = listfiles(src)

    shared.state.job = "preprocess"
    shared.state.textinfo = "Preprocessing..."
    shared.state.job_count = len(files)

    params = PreprocessParams()
    params.dstdir = dst
    params.flip = process_flip
    params.process_caption = process_caption
    params.process_caption_deepbooru = process_caption_deepbooru
    params.preprocess_txt_action = preprocess_txt_action

    pbar = tqdm.tqdm(files)
    for index, imagefile in enumerate(pbar):
        params.subindex = 0
        filename = os.path.join(src, imagefile)
        try:
            img = Image.open(filename).convert("RGB")
        except Exception:
            continue

        description = f"Preprocessing [Image {index}/{len(files)}]"
        pbar.set_description(description)
        shared.state.textinfo = description

        params.src = filename

        existing_caption = None
        existing_caption_filename = os.path.splitext(filename)[0] + '.txt'
        if os.path.exists(existing_caption_filename):
            with open(existing_caption_filename, 'r', encoding="utf8") as file:
                existing_caption = file.read()

        if shared.state.interrupted:
            break

        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

        process_default_resize = True

        if process_split and ratio < 1.0 and ratio <= split_threshold:
            for splitted in split_pic(img, inverse_xy, width, height, overlap_ratio):
                save_pic(splitted, index, params, existing_caption=existing_caption)
            process_default_resize = False

        if process_focal_crop and img.height != img.width:

            dnn_model_path = None
            try:
                dnn_model_path = autocrop.download_and_cache_models(os.path.join(paths.models_path, "opencv"))
            except Exception as e:
                print("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", e)

            autocrop_settings = autocrop.Settings(
                crop_width = width,
                crop_height = height,
                face_points_weight = process_focal_crop_face_weight,
                entropy_points_weight = process_focal_crop_entropy_weight,
                corner_points_weight = process_focal_crop_edges_weight,
                annotate_image = process_focal_crop_debug,
                dnn_model_path = dnn_model_path,
            )
            for focal in autocrop.crop_image(img, autocrop_settings):
                save_pic(focal, index, params, existing_caption=existing_caption)
            process_default_resize = False

        if process_multicrop:
            cropped = multicrop_pic(img, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold)
            if cropped is not None:
                save_pic(cropped, index, params, existing_caption=existing_caption)
            else:
                print(f"skipped {img.width}x{img.height} image {filename} (can't find suitable size within error threshold)")
            process_default_resize = False

        if process_default_resize:
            img = images.resize_image(1, img, width, height)
            save_pic(img, index, params, existing_caption=existing_caption)

        shared.state.nextjob()