ai个性化 国庆 头像 合成_头像合成 csdn

源码地址 https://github.com/tencentmusic/cube-studio/tree/master/aihub/deep-learning/face-paint/web

实现过程 将个人头像人体人脸识别，裁剪出肩膀以上部分，并将图片进行卡通化处理，最后与背景图片和文字合成，效果如下

实现代码：

import argparse
import base64
import datetime
import os
import sys

import cv2
import numpy as np
from tqdm import tqdm
import pysnooper
from PIL import ImageFont
from PIL import Image
from PIL import ImageDraw


from paddleseg.utils import get_sys_env, logger, get_image_list

from infer import Predictor

import os
import dlib
import collections
from typing import Union, List
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import torch


def get_bg_img(bg_img_path, img_shape):
    if bg_img_path is None:
        bg = 255 * np.ones(img_shape)
    elif not os.path.exists(bg_img_path):
        raise Exception('The --bg_img_path is not existed: {}'.format(
            bg_img_path))
    else:
        bg = cv2.imread(bg_img_path)
    return bg


def makedirs(save_dir):
    dirname = save_dir if os.path.isdir(save_dir) else \
        os.path.dirname(save_dir)
    if not os.path.exists(dirname):
        os.makedirs(dirname)


@pysnooper.snoop()
def seg_image(args):
    assert os.path.exists(args['img_path']), \
        "The --img_path is not existed: {}.".format(args['img_path'])

    logger.info("Input: image")
    logger.info("Create predictor...")
    predictor = Predictor(args)

    logger.info("Start predicting...")
    img = cv2.imread(args['re_save_path'])
    bg_img = get_bg_img(args['bg_img_path'], img.shape)
    out_img = predictor.run(img, bg_img)
    # print(type(out_img))
    cv2.imwrite(args['save_path'], out_img)
    img_draw_text = Image.open(args['save_path'])
    draw = ImageDraw.Draw(img_draw_text)
    x,y = img_draw_text.size
    ft = ImageFont.truetype("/home/ubuntu/PaddleSeg-release-2.6/contrib/PP-HumanSeg/src/1.ttf", args['text_height'])
    draw.text(args['text_position'], args['text'], font=ft, fill=args['text_color'])
    file = open(args['save_path'], 'rb')
    base64_str = base64.b64encode(file.read()).decode('utf-8')
    print(len(base64_str))
    return base64_str
    # img_ = Image.open(out_img)
    # print(img_)



def get_dlib_face_detector(predictor_path: str = "shape_predictor_68_face_landmarks.dat"):
    if not os.path.isfile(predictor_path):
        model_file = "shape_predictor_68_face_landmarks.dat.bz2"
        os.system(f"wget http://dlib.net/files/{model_file}")
        os.system(f"bzip2 -dk {model_file}")

    detector = dlib.get_frontal_face_detector()
    shape_predictor = dlib.shape_predictor('shape_predictor_68_face_landmarks.dat')

    def detect_face_landmarks(img: Union[Image.Image, np.ndarray]):
        if isinstance(img, Image.Image):
            img = np.array(img)
        faces = []
        dets = detector(img)
        for d in dets:
            shape = shape_predictor(img, d)
            faces.append(np.array([[v.x, v.y] for v in shape.parts()]))
        return faces

    return detect_face_landmarks


def display_facial_landmarks(
        img: Image,
        landmarks: List[np.ndarray],
        fig_size=[15, 15]
):
    plot_style = dict(
        marker='o',
        markersize=4,
        linestyle='-',
        lw=2
    )
    pred_type = collections.namedtuple('prediction_type', ['slice', 'color'])
    pred_types = {
        'face': pred_type(slice(0, 17), (0.682, 0.780, 0.909, 0.5)),
        'eyebrow1': pred_type(slice(17, 22), (1.0, 0.498, 0.055, 0.4)),
        'eyebrow2': pred_type(slice(22, 27), (1.0, 0.498, 0.055, 0.4)),
        'nose': pred_type(slice(27, 31), (0.345, 0.239, 0.443, 0.4)),
        'nostril': pred_type(slice(31, 36), (0.345, 0.239, 0.443, 0.4)),
        'eye1': pred_type(slice(36, 42), (0.596, 0.875, 0.541, 0.3)),
        'eye2': pred_type(slice(42, 48), (0.596, 0.875, 0.541, 0.3)),
        'lips': pred_type(slice(48, 60), (0.596, 0.875, 0.541, 0.3)),
        'teeth': pred_type(slice(60, 68), (0.596, 0.875, 0.541, 0.4))
    }

    fig = plt.figure(figsize=fig_size)
    ax = fig.add_subplot(1, 1, 1)
    ax.imshow(img)
    ax.axis('off')

    for face in landmarks:
        for pred_type in pred_types.values():
            ax.plot(
                face[pred_type.slice, 0],
                face[pred_type.slice, 1],
                color=pred_type.color, **plot_style
            )
    plt.show()


import PIL.Image
import PIL.ImageFile
import numpy as np
import scipy.ndimage

def align_and_crop_face(
        img: Image.Image,
        landmarks: np.ndarray,
        expand: float = 1.0,
        output_size: int = 1024,
        transform_size: int = 4096,
        enable_padding: bool = True,
):
    # Parse landmarks.
    # pylint: disable=unused-variable
    lm = landmarks
    lm_chin = lm[0: 17]  # left-right
    lm_eyebrow_left = lm[17: 22]  # left-right
    lm_eyebrow_right = lm[22: 27]  # left-right
    lm_nose = lm[27: 31]  # top-down
    lm_nostrils = lm[31: 36]  # top-down
    lm_eye_left = lm[36: 42]  # left-clockwise
    lm_eye_right = lm[42: 48]  # left-clockwise
    lm_mouth_outer = lm[48: 60]  # left-clockwise
    lm_mouth_inner = lm[60: 68]  # left-clockwise

    # Calculate auxiliary vectors.
    eye_left = np.mean(lm_eye_left, axis=0)
    eye_right = np.mean(lm_eye_right, axis=0)
    eye_avg = (eye_left + eye_right) * 0.5
    eye_to_eye = eye_right - eye_left
    mouth_left = lm_mouth_outer[0]
    mouth_right = lm_mouth_outer[6]
    mouth_avg = (mouth_left + mouth_right) * 0.5
    eye_to_mouth = mouth_avg - eye_avg

    # Choose oriented crop rectangle.
    x = eye_to_eye - np.flipud(eye_to_mouth) * [-1, 1]
    x /= np.hypot(*x)
    x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
    x *= expand
    y = np.flipud(x) * [-1, 1]
    c = eye_avg + eye_to_mouth * 0.1
    quad = np.stack([c - x - y, c - x + y, c + x + y, c + x - y])
    qsize = np.hypot(*x) * 2

    # Shrink.
    shrink = int(np.floor(qsize / output_size * 0.5))
    if shrink > 1:
        rsize = (int(np.rint(float(img.size[0]) / shrink)), int(np.rint(float(img.size[1]) / shrink)))
        img = img.resize(rsize, PIL.Image.ANTIALIAS)
        quad /= shrink
        qsize /= shrink

    # Crop.
    border = max(int(np.rint(qsize * 0.1)), 3)
    crop = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))), int(np.ceil(max(quad[:, 0]))),
            int(np.ceil(max(quad[:, 1]))))
    crop = (max(crop[0] - border, 0), max(crop[1] - border, 0), min(crop[2] + border, img.size[0]),
            min(crop[3] + border, img.size[1]))
    if crop[2] - crop[0] < img.size[0] or crop[3] - crop[1] < img.size[1]:
        img = img.crop(crop)
        quad -= crop[0:2]

    # Pad.
    pad = (int(np.floor(min(quad[:, 0]))), int(np.floor(min(quad[:, 1]))), int(np.ceil(max(quad[:, 0]))),
           int(np.ceil(max(quad[:, 1]))))
    pad = (max(-pad[0] + border, 0), max(-pad[1] + border, 0), max(pad[2] - img.size[0] + border, 0),
           max(pad[3] - img.size[1] + border, 0))
    if enable_padding and max(pad) > border - 4:
        pad = np.maximum(pad, int(np.rint(qsize * 0.3)))
        img = np.pad(np.float32(img), ((pad[1], pad[3]), (pad[0], pad[2]), (0, 0)), 'reflect')
        h, w, _ = img.shape
        y, x, _ = np.ogrid[:h, :w, :1]
        mask = np.maximum(1.0 - np.minimum(np.float32(x) / pad[0], np.float32(w - 1 - x) / pad[2]),
                          1.0 - np.minimum(np.float32(y) / pad[1], np.float32(h - 1 - y) / pad[3]))
        blur = qsize * 0.02
        img += (scipy.ndimage.gaussian_filter(img, [blur, blur, 0]) - img) * np.clip(mask * 3.0 + 1.0, 0.0, 1.0)
        img += (np.median(img, axis=(0, 1)) - img) * np.clip(mask, 0.0, 1.0)
        img = PIL.Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
        quad += pad[:2]

    # Transform.
    img = img.transform((transform_size, transform_size), PIL.Image.QUAD, (quad + 0.5).flatten(), PIL.Image.BILINEAR)
    if output_size < transform_size:
        img = img.resize((output_size, output_size), PIL.Image.ANTIALIAS)

    return img

import pysnooper
@pysnooper.snoop()
def start(
        config=r'/home/ubuntu/PaddleSeg-release-2.6/contrib/PP-HumanSeg/src/inference_models/portrait_pp_humansegv2_lite_256x144_inference_model_with_softmax/deploy.yaml',
        img_path=r'/home/ubuntu/PaddleSeg-release-2.6/contrib/PP-HumanSeg/src/data/images/1.jpg',
        re_save_path=r'temp/1_.jpg',
        save_path=r'temp/1.jpg',
        text='陈',
        use_gpu=False,
        test_speed=False, use_optic_flow=False, use_post_process=False):
    args = {
        'config': config,
        'img_path': img_path,
        're_save_path': re_save_path,
        'save_path': save_path,
        'use_gpu': use_gpu,
        'test_speed': test_speed,
        "text":text,
        'use_optic_flow': use_optic_flow,
        'use_post_process': use_post_process
    }
    print(type(args))

    # 先动漫化后增加背景效果更佳

    # 加载网络或本地文件
    save_ = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
    os.mkdir(save_)
    device = "cuda" if torch.cuda.is_available() else "cpu"
    model = torch.hub.load("bryandlee/animegan2-pytorch:main", "generator", device=device).eval()
    face2paint = torch.hub.load("bryandlee/animegan2-pytorch:main", "face2paint", device=device, side_by_side=True)
    img = Image.open(args['img_path']).convert("RGB")
    # img = Image.open("/content/sample.jpg").convert("RGB")

    face_detector = get_dlib_face_detector()
    landmarks = face_detector(img)
    out = ''
    for landmark in landmarks:
        face = align_and_crop_face(img, landmark, expand=1.3)
        p_face = face2paint(model=model, img=face, size=512)
        # display(p_face)
        p_face.save('temp/input_cartoon.jpg') # 此输出为对比图片
        # 裁剪为需要的部分输出
        x_, y_ = p_face.size
        out = p_face.crop((int(x_/2), 0, x_, y_))  # 后面一半是卡通效果图
    img_ = out
    x, y = img_.size
    print(x, y)
    all_list = []
    all_backgroud=[
        {
            "path":"icon/1.jpg",
            "position":[410,260],
            "height":340,
            "text_position":(260,200),
            "text_height":200,
            "color":(149,6,2),
            "text_color": "white"
        },
        {
            "path": "icon/2.jpg",
            "position": [70, 200],
            "height": 380,
            "text_position": (450, 300),
            "text_height": 180,
            "color": (182,28,30),
            "text_color": "white"
        },
        {
            "path": "icon/3.jpg",
            "position": [330, 150],
            "height": 370,
            "text_position": (150, 350),
            "text_height": 150,
            "color": (114,10,11),
            "text_color": "white"
        },
        {
            "path": "icon/4.jpg",
            "position": [350, 270],
            "height": 340,
            "text_position": (140, 400),
            "text_height": 150,
            "color": (152, 16, 0),
            "text_color": "white"
        },
        {
            "path": "icon/5.jpg",
            "position": [260, 230],
            "height": 570,
            "text_position": (80, 430),
            "text_height": 180,
            "color": (240, 105, 116),
            "text_color": "white"
        },
        {
            "path": "icon/6.jpg",
            "position": [100, 230],
            "height": 320,
            "text_position": (460, 310),
            "text_height": 170,
            "color": (194, 0, 8),
            "text_color": "white"
        },
        {
            "path": "icon/7.jpg",
            "position": [240, 210],
            "height": 400,
            "text_position": (130, 290),
            "text_height": 140,
            "color": (244, 214, 190),
            "text_color": "white"
        },
        {
            "path": "icon/8.jpg",
            "position": [120, 190],
            "height": 330,
            "text_position": (460, 325),
            "text_height": 150,
            "color": (216, 18, 19),
            "text_color": "white"
        },
        {
            "path": "icon/9.jpg",
            "position": [380, 260],
            "height": 400,
            "text_position": (90, 330),
            "text_height": 185,
            "color": (250, 250, 250),
            "text_color": "red"
        },
        {
            "path": "icon/10.jpg",
            "position": [100, 200],
            "height": 320,
            "text_position": (410, 290),
            "text_height": 180,
            "color": (250, 250, 250),
            "text_color": "red"
        }
    ]

    for pic in all_backgroud:
        img_=img_.resize((int((pic['height']/y)*x),pic['height']),Image.ANTIALIAS)
        newIm = Image.new('RGB', (800, 800), pic['color'])

        newIm.paste(img_, pic['position'])  # 把人体复制进去
        newIm.save(args['re_save_path'])
        args['bg_img_path']=pic['path']
        args['position']=pic['position']
        args['height']=pic['height']
        args['text_position']=pic['text_position']
        args['text_height']=pic['text_height']
        args['text_color'] = pic['text_color']
        base64_ = seg_image(args)
        all_list.append(base64_)

    return all_list


if __name__ == "__main__":
    image_path = r'/home/ubuntu/PaddleSeg-release-2.6/contrib/PP-HumanSeg/src/data/images/human.jpg'
    file_after = open(image_path, 'rb')
    base64_after_str = base64.b64encode(file_after.read()).decode('utf-8')
    print(len(base64_after_str))
    imgdata = base64.b64decode(base64_after_str)
    # 将图片保存为文件
    if os.path.exists('temp'):
        pass
    else:
        os.mkdir('temp')
    name_ = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
    new_image_path = f'temp/{name_}.jpg'
    with open(new_image_path, 'wb') as f:
        f.write(imgdata)

    start(
        # config=r'E:\PaddleSeg-release-2.6\contrib\PP-HumanSeg\src\inference_models\portrait_pp_humansegv2_lite_256x144_inference_model_with_softmax\deploy.yaml',
        img_path=new_image_path,
        # bg_img_path=r'E:\PaddleSeg-release-2.6\contrib\PP-HumanSeg\src\data\images\bg_1.jpg',
        # re_save_path=r'E:\PaddleSeg-release-2.6\contrib\PP-HumanSeg\src\data\images\_1.jpg',
        # save_path=r'E:\PaddleSeg-release-2.6\contrib\PP-HumanSeg\src\data\images_result\1.jpg',
        # use_gpu=True,
        # test_speed=False, use_optic_flow=False, use_post_process=False)
        )
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
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411

详情参考github中aihub功能：https://github.com/tencentmusic/cube-studio/tree/master/aihub/deep-learning/face-paint