File size: 5,542 Bytes
1b58573
 
 
 
 
 
 
b1ae84d
1b58573
 
 
 
b1ae84d
 
1b58573
 
b1ae84d
 
 
1b58573
b1ae84d
 
 
 
 
 
 
 
7f20010
 
b1ae84d
1b58573
b1ae84d
 
f56e0f7
b1ae84d
1b58573
 
 
 
b1ae84d
 
 
1b58573
 
 
b1ae84d
 
 
 
 
1b58573
 
 
 
b1ae84d
 
 
 
 
 
1b58573
 
b1ae84d
 
 
1b58573
 
b1ae84d
 
 
 
 
 
 
1b58573
b1ae84d
 
 
 
 
 
 
1b58573
b1ae84d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1b58573
b1ae84d
 
1b58573
 
b1ae84d
1b58573
 
 
b1ae84d
 
 
1b58573
b1ae84d
 
 
 
 
 
 
 
 
 
 
 
 
1b58573
b1ae84d
 
 
1b58573
 
 
 
b1ae84d
 
1b58573
 
 
 
b1ae84d
 
 
 
1b58573
 
 
b1ae84d
 
1b58573
 
 
 
 
 
 
 
 
 
b1ae84d
 
 
 
 
 
 
 
 
 
1b58573
b1ae84d
 
 
 
 
 
1b58573
b1ae84d
1b58573
b1ae84d
 
1b58573
b1ae84d
1b58573
 
 
 
b1ae84d
1b58573
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
#!/usr/bin/env python

from __future__ import annotations

import argparse
import functools
import html
import os

import gradio as gr
import huggingface_hub
import numpy as np
import onnxruntime as rt
import pandas as pd
import piexif
import piexif.helper
import PIL.Image

from Utils import dbimutils

TITLE = "WaifuDiffusion v1.4 Tags"
DESCRIPTION = """
Demo for [SmilingWolf/wd-v1-4-vit-tagger](https://huggingface.co/SmilingWolf/wd-v1-4-vit-tagger) with "ready to copy" prompt and a prompt analyzer.

Modified from [NoCrypt/DeepDanbooru_string](https://huggingface.co/spaces/NoCrypt/DeepDanbooru_string)  
Modified from [hysts/DeepDanbooru](https://huggingface.co/spaces/hysts/DeepDanbooru)

PNG Info code forked from [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui)

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

HF_TOKEN = os.environ["HF_TOKEN"]
MODEL_REPO = "SmilingWolf/wd-v1-4-vit-tagger"
MODEL_FILENAME = "model.onnx"
LABEL_FILENAME = "selected_tags.csv"


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


def load_model() -> rt.InferenceSession:
    path = huggingface_hub.hf_hub_download(
        MODEL_REPO, MODEL_FILENAME, use_auth_token=HF_TOKEN
    )
    model = rt.InferenceSession(path)
    return model


def load_labels() -> list[str]:
    path = huggingface_hub.hf_hub_download(
        MODEL_REPO, LABEL_FILENAME, use_auth_token=HF_TOKEN
    )
    df = pd.read_csv(path)["name"].tolist()
    return df


def plaintext_to_html(text):
    text = (
        "<p>" + "<br>\n".join([f"{html.escape(x)}" for x in text.split("\n")]) + "</p>"
    )
    return text


def predict(
    image: PIL.Image.Image,
    score_threshold: float,
    model: rt.InferenceSession,
    labels: list[str],
):
    rawimage = image
    _, height, width, _ = model.get_inputs()[0].shape

    # Alpha to white
    image = image.convert("RGBA")
    new_image = PIL.Image.new("RGBA", image.size, "WHITE")
    new_image.paste(image, mask=image)
    image = new_image.convert("RGB")
    image = np.asarray(image)

    # PIL RGB to OpenCV BGR
    image = image[:, :, ::-1]

    image = dbimutils.make_square(image, height)
    image = dbimutils.smart_resize(image, height)
    image = image.astype(np.float32)
    image = np.expand_dims(image, 0)

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

    labels = list(zip(labels, probs[0].astype(float)))

    # First 4 labels are actually ratings: pick one with argmax
    ratings_names = labels[:4]
    rating = dict(ratings_names)

    # Everything else is tags: pick any where prediction confidence > threshold
    tags_names = labels[4:]
    res = [x for x in tags_names if x[1] > score_threshold]
    res = dict(res)

    b = dict(sorted(res.items(), key=lambda item: item[1], reverse=True))
    a = (
        ", ".join(list(b.keys()))
        .replace("_", " ")
        .replace("(", "\(")
        .replace(")", "\)")
    )
    c = ", ".join(list(b.keys()))

    items = rawimage.info
    geninfo = ""

    if "exif" in rawimage.info:
        exif = piexif.load(rawimage.info["exif"])
        exif_comment = (exif or {}).get("Exif", {}).get(piexif.ExifIFD.UserComment, b"")
        try:
            exif_comment = piexif.helper.UserComment.load(exif_comment)
        except ValueError:
            exif_comment = exif_comment.decode("utf8", errors="ignore")

        items["exif comment"] = exif_comment
        geninfo = exif_comment

        for field in [
            "jfif",
            "jfif_version",
            "jfif_unit",
            "jfif_density",
            "dpi",
            "exif",
            "loop",
            "background",
            "timestamp",
            "duration",
        ]:
            items.pop(field, None)

    geninfo = items.get("parameters", geninfo)

    info = f"""
<p><h4>PNG Info</h4></p>    
"""
    for key, text in items.items():
        info += (
            f"""
<div>
<p><b>{plaintext_to_html(str(key))}</b></p>
<p>{plaintext_to_html(str(text))}</p>
</div>
""".strip()
            + "\n"
        )

    if len(info) == 0:
        message = "Nothing found in the image."
        info = f"<div><p>{message}<p></div>"

    return (a, c, rating, res, info)


def main():
    args = parse_args()
    model = load_model()
    labels = load_labels()

    func = functools.partial(predict, model=model, labels=labels)

    gr.Interface(
        fn=func,
        inputs=[
            gr.Image(type="pil", label="Input"),
            gr.Slider(
                0,
                1,
                step=args.score_slider_step,
                value=args.score_threshold,
                label="Score Threshold",
            ),
        ],
        outputs=[
            gr.Textbox(label="Output (string)"),
            gr.Textbox(label="Output (raw string)"),
            gr.Label(label="Rating"),
            gr.Label(label="Output (label)"),
            gr.HTML(),
        ],
        examples=[["power.jpg", 0.5]],
        title=TITLE,
        description=DESCRIPTION,
        allow_flagging="never",
    ).launch(
        enable_queue=True,
        share=args.share,
    )


if __name__ == "__main__":
    main()