File size: 11,862 Bytes
c3fca62
 
 
 
 
 
 
 
5bf67a7
c3fca62
412032a
1154448
5bf67a7
c3fca62
 
c6e87b3
 
 
 
5bf67a7
c3fca62
 
 
 
5bf67a7
 
 
 
 
3861450
 
5bf67a7
 
 
 
 
 
 
 
 
c3fca62
 
 
5bf67a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c3fca62
 
 
 
 
 
 
 
 
 
5bf67a7
 
 
 
 
 
 
 
 
 
c3fca62
 
 
5bf67a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c3fca62
5bf67a7
c3fca62
5bf67a7
 
 
c3fca62
5bf67a7
c3fca62
5bf67a7
 
c3fca62
5bf67a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c3fca62
5bf67a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5f83a76
 
 
5bf67a7
 
 
 
 
c3fca62
 
5bf67a7
 
 
 
 
 
3861450
 
5bf67a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0e0c620
5bf67a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c3fca62
 
 
 
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
import argparse
import os

import gradio as gr
import huggingface_hub
import numpy as np
import onnxruntime as rt
import pandas as pd
from PIL import Image



TITLE = "WaifuDiffusion Tagger"

DESCRIPTION = """
This is an edited version of SmilingWolf's wd-1.4 taggs, which I have modified so that you don't have to remove the commas when you label an image for a booru website

https://huggingface.co/spaces/SmilingWolf/wd-v1-4-tags

Demo for the WaifuDiffusion tagger models

Example image by [ほし☆☆☆](https://www.pixiv.net/en/users/43565085)
"""


# Dataset v3 series of models:
SWINV2_MODEL_DSV3_REPO = "SmilingWolf/wd-swinv2-tagger-v3"
CONV_MODEL_DSV3_REPO = "SmilingWolf/wd-convnext-tagger-v3"
VIT_MODEL_DSV3_REPO = "SmilingWolf/wd-vit-tagger-v3"
VIT_LARGE_MODEL_DSV3_REPO = "SmilingWolf/wd-vit-large-tagger-v3"
EVA02_LARGE_MODEL_DSV3_REPO = "SmilingWolf/wd-eva02-large-tagger-v3"

# Dataset v2 series of models:
MOAT_MODEL_DSV2_REPO = "SmilingWolf/wd-v1-4-moat-tagger-v2"
SWIN_MODEL_DSV2_REPO = "SmilingWolf/wd-v1-4-swinv2-tagger-v2"
CONV_MODEL_DSV2_REPO = "SmilingWolf/wd-v1-4-convnext-tagger-v2"
CONV2_MODEL_DSV2_REPO = "SmilingWolf/wd-v1-4-convnextv2-tagger-v2"
VIT_MODEL_DSV2_REPO = "SmilingWolf/wd-v1-4-vit-tagger-v2"

# Files to download from the repos
MODEL_FILENAME = "model.onnx"
LABEL_FILENAME = "selected_tags.csv"

# https://github.com/toriato/stable-diffusion-webui-wd14-tagger/blob/a9eacb1eff904552d3012babfa28b57e1d3e295c/tagger/ui.py#L368
kaomojis = [
    "0_0",
    "(o)_(o)",
    "+_+",
    "+_-",
    "._.",
    "<o>_<o>",
    "<|>_<|>",
    "=_=",
    ">_<",
    "3_3",
    "6_9",
    ">_o",
    "@_@",
    "^_^",
    "o_o",
    "u_u",
    "x_x",
    "|_|",
    "||_||",
]


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser()
    parser.add_argument("--score-slider-step", type=float, default=0.05)
    parser.add_argument("--score-general-threshold", type=float, default=0.35)
    parser.add_argument("--score-character-threshold", type=float, default=0.85)
    parser.add_argument("--share", action="store_true")
    return parser.parse_args()


def load_labels(dataframe) -> list[str]:
    name_series = dataframe["name"]
    # name_series = name_series.map(
    #     lambda x: x.replace("_", " ") if x not in kaomojis else x
    # )
    tag_names = name_series.tolist()

    rating_indexes = list(np.where(dataframe["category"] == 9)[0])
    general_indexes = list(np.where(dataframe["category"] == 0)[0])
    character_indexes = list(np.where(dataframe["category"] == 4)[0])
    return tag_names, rating_indexes, general_indexes, character_indexes


def mcut_threshold(probs):
    """
    Maximum Cut Thresholding (MCut)
    Largeron, C., Moulin, C., & Gery, M. (2012). MCut: A Thresholding Strategy
     for Multi-label Classification. In 11th International Symposium, IDA 2012
     (pp. 172-183).
    """
    sorted_probs = probs[probs.argsort()[::-1]]
    difs = sorted_probs[:-1] - sorted_probs[1:]
    t = difs.argmax()
    thresh = (sorted_probs[t] + sorted_probs[t + 1]) / 2
    return thresh


class Predictor:
    def __init__(self):
        self.model_target_size = None
        self.last_loaded_repo = None

    def download_model(self, model_repo):
        csv_path = huggingface_hub.hf_hub_download(
            model_repo,
            LABEL_FILENAME,
        )
        model_path = huggingface_hub.hf_hub_download(
            model_repo,
            MODEL_FILENAME,
        )
        return csv_path, model_path

    def load_model(self, model_repo):
        if model_repo == self.last_loaded_repo:
            return

        csv_path, model_path = self.download_model(model_repo)

        tags_df = pd.read_csv(csv_path)
        sep_tags = load_labels(tags_df)

        self.tag_names = sep_tags[0]
        self.rating_indexes = sep_tags[1]
        self.general_indexes = sep_tags[2]
        self.character_indexes = sep_tags[3]

        model = rt.InferenceSession(model_path)
        _, height, width, _ = model.get_inputs()[0].shape
        self.model_target_size = height

        self.last_loaded_repo = model_repo
        self.model = model

    def prepare_image(self, image):
        target_size = self.model_target_size

        canvas = Image.new("RGBA", image.size, (255, 255, 255))
        canvas.alpha_composite(image)
        image = canvas.convert("RGB")

        # Pad image to square
        image_shape = image.size
        max_dim = max(image_shape)
        pad_left = (max_dim - image_shape[0]) // 2
        pad_top = (max_dim - image_shape[1]) // 2

        padded_image = Image.new("RGB", (max_dim, max_dim), (255, 255, 255))
        padded_image.paste(image, (pad_left, pad_top))

        # Resize
        if max_dim != target_size:
            padded_image = padded_image.resize(
                (target_size, target_size),
                Image.BICUBIC,
            )

        # Convert to numpy array
        image_array = np.asarray(padded_image, dtype=np.float32)

        # Convert PIL-native RGB to BGR
        image_array = image_array[:, :, ::-1]

        return np.expand_dims(image_array, axis=0)

    def predict(
        self,
        image,
        model_repo,
        general_thresh,
        general_mcut_enabled,
        character_thresh,
        character_mcut_enabled,
    ):
        self.load_model(model_repo)

        image = self.prepare_image(image)

        input_name = self.model.get_inputs()[0].name
        label_name = self.model.get_outputs()[0].name
        preds = self.model.run([label_name], {input_name: image})[0]

        labels = list(zip(self.tag_names, preds[0].astype(float)))

        # First 4 labels are actually ratings: pick one with argmax
        ratings_names = [labels[i] for i in self.rating_indexes]
        rating = dict(ratings_names)

        # Then we have general tags: pick any where prediction confidence > threshold
        general_names = [labels[i] for i in self.general_indexes]

        if general_mcut_enabled:
            general_probs = np.array([x[1] for x in general_names])
            general_thresh = mcut_threshold(general_probs)

        general_res = [x for x in general_names if x[1] > general_thresh]
        general_res = dict(general_res)

        # Everything else is characters: pick any where prediction confidence > threshold
        character_names = [labels[i] for i in self.character_indexes]

        if character_mcut_enabled:
            character_probs = np.array([x[1] for x in character_names])
            character_thresh = mcut_threshold(character_probs)
            character_thresh = max(0.15, character_thresh)

        character_res = [x for x in character_names if x[1] > character_thresh]
        character_res = dict(character_res)

        sorted_general_strings = sorted(
            general_res.items(),
            key=lambda x: x[1],
            reverse=True,
        )
        sorted_general_strings = [x[0] for x in sorted_general_strings]
        sorted_booru_strings = (
            " ".join(sorted_general_strings)
        )
        sorted_general_strings = (
            ", ".join(sorted_general_strings).replace("(", "\(").replace(")", "\)")
        )
        # sorted_general_strings = sorted_general_strings.map(
        # lambda x: x.replace("_", " ") if x not in kaomojis else x
        # )

        return sorted_general_strings, sorted_booru_strings, rating, character_res, general_res


def main():
    args = parse_args()

    predictor = Predictor()

    dropdown_list = [
        SWINV2_MODEL_DSV3_REPO,
        CONV_MODEL_DSV3_REPO,
        VIT_MODEL_DSV3_REPO,
        VIT_LARGE_MODEL_DSV3_REPO,
        EVA02_LARGE_MODEL_DSV3_REPO,
        MOAT_MODEL_DSV2_REPO,
        SWIN_MODEL_DSV2_REPO,
        CONV_MODEL_DSV2_REPO,
        CONV2_MODEL_DSV2_REPO,
        VIT_MODEL_DSV2_REPO,
    ]

    with gr.Blocks(title=TITLE) as demo:
        with gr.Column():
            gr.Markdown(
                value=f"<h1 style='text-align: center; margin-bottom: 1rem'>{TITLE}</h1>"
            )
            gr.Markdown(value=DESCRIPTION)
            with gr.Row():
                with gr.Column(variant="panel"):
                    image = gr.Image(type="pil", image_mode="RGBA", label="Input")
                    model_repo = gr.Dropdown(
                        dropdown_list,
                        value=SWINV2_MODEL_DSV3_REPO,
                        label="Model",
                    )
                    with gr.Row():
                        general_thresh = gr.Slider(
                            0,
                            1,
                            step=args.score_slider_step,
                            value=args.score_general_threshold,
                            label="General Tags Threshold",
                            scale=3,
                        )
                        general_mcut_enabled = gr.Checkbox(
                            value=False,
                            label="Use MCut threshold",
                            scale=1,
                        )
                    with gr.Row():
                        character_thresh = gr.Slider(
                            0,
                            1,
                            step=args.score_slider_step,
                            value=args.score_character_threshold,
                            label="Character Tags Threshold",
                            scale=3,
                        )
                        character_mcut_enabled = gr.Checkbox(
                            value=False,
                            label="Use MCut threshold",
                            scale=1,
                        )
                    with gr.Row():
                        clear = gr.ClearButton(
                            components=[
                                image,
                                model_repo,
                                general_thresh,
                                general_mcut_enabled,
                                character_thresh,
                                character_mcut_enabled,
                            ],
                            variant="secondary",
                            size="lg",
                        )
                        submit = gr.Button(value="Submit", variant="primary", size="lg")
                with gr.Column(variant="panel"):
                    sorted_general_strings = gr.Textbox(label="Output (string)")
                    sorted_booru_strings = gr.Textbox(label="Output (Booru)")
                    rating = gr.Label(label="Rating")
                    character_res = gr.Label(label="Output (characters)")
                    general_res = gr.Label(label="Output (tags)")
                    clear.add(
                        [
                            sorted_general_strings,
                            sorted_booru_strings,
                            rating,
                            character_res,
                            general_res,
                        ]
                    )

        submit.click(
            predictor.predict,
            inputs=[
                image,
                model_repo,
                general_thresh,
                general_mcut_enabled,
                character_thresh,
                character_mcut_enabled,
            ],
            outputs=[sorted_general_strings,sorted_booru_strings, rating, character_res, general_res],
        )

        gr.Examples(
            [["power.jpg", SWINV2_MODEL_DSV3_REPO, 0.35, False, 0.85, False]],
            inputs=[
                image,
                model_repo,
                general_thresh,
                general_mcut_enabled,
                character_thresh,
                character_mcut_enabled,
            ],
        )

    demo.queue(max_size=10)
    demo.launch()


if __name__ == "__main__":
    main()