File size: 16,408 Bytes
87b62f4
 
b1cc251
87b62f4
 
 
 
771ff1c
aaa6de6
87b62f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30257f2
 
 
 
 
 
 
 
 
 
 
 
87b62f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1cc251
 
 
 
 
 
 
 
 
 
 
87b62f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30257f2
 
 
 
 
 
 
 
 
 
 
 
87b62f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1cc251
 
 
 
 
 
 
 
 
 
 
 
87b62f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
import gradio as gr
import cv2
import numpy as np

from annotator.util import resize_image, HWC3

DESCRIPTION = '# ControlNet v1.1 Annotators (that runs on cpu only)'
DESCRIPTION += '\n<p>This app generates Control Image for Core ML Stable Diffusion apps such as Mochi Diffusion.</p>'
DESCRIPTION += '\n<p>HEIC image is not converted. Please use PNG or JPG image.</p>'


model_canny = None


def canny(img, res, l, h):
    img = resize_image(HWC3(img), res)
    global model_canny
    if model_canny is None:
        from annotator.canny import CannyDetector
        model_canny = CannyDetector()
    result = model_canny(img, l, h)
    return [result]


model_hed = None


def hed(img, res):
    img = resize_image(HWC3(img), res)
    global model_hed
    if model_hed is None:
        from annotator.hed import HEDdetector
        model_hed = HEDdetector()
    result = model_hed(img)
    return [result]


model_pidi = None


def pidi(img, res):
    img = resize_image(HWC3(img), res)
    global model_pidi
    if model_pidi is None:
        from annotator.pidinet import PidiNetDetector
        model_pidi = PidiNetDetector()
    result = model_pidi(img)
    return [result]


model_mlsd = None


def mlsd(img, res, thr_v, thr_d):
    img = resize_image(HWC3(img), res)
    global model_mlsd
    if model_mlsd is None:
        from annotator.mlsd import MLSDdetector
        model_mlsd = MLSDdetector()
    result = model_mlsd(img, thr_v, thr_d)
    return [result]


model_midas = None


def midas(img, res):
    img = resize_image(HWC3(img), res)
    global model_midas
    if model_midas is None:
        from annotator.midas import MidasDetector
        model_midas = MidasDetector()
    result = model_midas(img)
    return [result]


model_zoe = None


def zoe(img, res):
    img = resize_image(HWC3(img), res)
    global model_zoe
    if model_zoe is None:
        from annotator.zoe import ZoeDetector
        model_zoe = ZoeDetector()
    result = model_zoe(img)
    return [result]


model_normalbae = None


def normalbae(img, res):
    img = resize_image(HWC3(img), res)
    global model_normalbae
    if model_normalbae is None:
        from annotator.normalbae import NormalBaeDetector
        model_normalbae = NormalBaeDetector()
    result = model_normalbae(img)
    return [result]


model_dwpose = None

def dwpose(img, res):
    img = resize_image(HWC3(img), res)
    global model_dwpose
    if model_dwpose is None:
        from annotator.dwpose import DWposeDetector
        model_dwpose = DWposeDetector()
    result = model_dwpose(img)
    return [result]


model_openpose = None


def openpose(img, res, hand_and_face):
    img = resize_image(HWC3(img), res)
    global model_openpose
    if model_openpose is None:
        from annotator.openpose import OpenposeDetector
        model_openpose = OpenposeDetector()
    result = model_openpose(img, hand_and_face)
    return [result]


model_uniformer = None


#def uniformer(img, res):
#    img = resize_image(HWC3(img), res)
#    global model_uniformer
#    if model_uniformer is None:
#        from annotator.uniformer import UniformerDetector
#        model_uniformer = UniformerDetector()
#    result = model_uniformer(img)
#    return [result]


model_lineart_anime = None


def lineart_anime(img, res, invert=True):
    img = resize_image(HWC3(img), res)
    global model_lineart_anime
    if model_lineart_anime is None:
        from annotator.lineart_anime import LineartAnimeDetector
        model_lineart_anime = LineartAnimeDetector()
#    result = model_lineart_anime(img)
    if (invert):
        result = cv2.bitwise_not(model_lineart_anime(img))
    else:
        result = model_lineart_anime(img)
    return [result]


model_lineart = None


def lineart(img, res, coarse=False, invert=True):
    img = resize_image(HWC3(img), res)
    global model_lineart
    if model_lineart is None:
        from annotator.lineart import LineartDetector
        model_lineart = LineartDetector()
#    result = model_lineart(img, coarse)
    if (invert):
        result = cv2.bitwise_not(model_lineart(img, coarse))
    else:
        result = model_lineart(img, coarse)    
    return [result]


model_oneformer_coco = None


def oneformer_coco(img, res):
    img = resize_image(HWC3(img), res)
    global model_oneformer_coco
    if model_oneformer_coco is None:
        from annotator.oneformer import OneformerCOCODetector
        model_oneformer_coco = OneformerCOCODetector()
    result = model_oneformer_coco(img)
    return [result]


model_oneformer_ade20k = None


def oneformer_ade20k(img, res):
    img = resize_image(HWC3(img), res)
    global model_oneformer_ade20k
    if model_oneformer_ade20k is None:
        from annotator.oneformer import OneformerADE20kDetector
        model_oneformer_ade20k = OneformerADE20kDetector()
    result = model_oneformer_ade20k(img)
    return [result]


model_content_shuffler = None


def content_shuffler(img, res):
    img = resize_image(HWC3(img), res)
    global model_content_shuffler
    if model_content_shuffler is None:
        from annotator.shuffle import ContentShuffleDetector
        model_content_shuffler = ContentShuffleDetector()
    result = model_content_shuffler(img)
    return [result]


model_color_shuffler = None


def color_shuffler(img, res):
    img = resize_image(HWC3(img), res)
    global model_color_shuffler
    if model_color_shuffler is None:
        from annotator.shuffle import ColorShuffleDetector
        model_color_shuffler = ColorShuffleDetector()
    result = model_color_shuffler(img)
    return [result]

model_inpaint = None


def inpaint(image, invert):
    color = HWC3(image["image"])
    if(invert):
        alpha = image["mask"][:, :, 0:1]
    else:
        alpha = 255 - image["mask"][:, :, 0:1]
    result = np.concatenate([color, alpha], axis=2)
    return [result]

block = gr.Blocks().queue()
with block:
    gr.Markdown(DESCRIPTION)
    with gr.Row():
        gr.Markdown("## Canny Edge")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            low_threshold = gr.Slider(label="low_threshold", minimum=1, maximum=255, value=100, step=1)
            high_threshold = gr.Slider(label="high_threshold", minimum=1, maximum=255, value=200, step=1)
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=canny, inputs=[input_image, resolution, low_threshold, high_threshold], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## HED Edge&nbsp;&quot;SoftEdge&quot;")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=hed, inputs=[input_image, resolution], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Pidi Edge&nbsp;&quot;SoftEdge&quot;")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=pidi, inputs=[input_image, resolution], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## MLSD Edge")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            value_threshold = gr.Slider(label="value_threshold", minimum=0.01, maximum=2.0, value=0.1, step=0.01)
            distance_threshold = gr.Slider(label="distance_threshold", minimum=0.01, maximum=20.0, value=0.1, step=0.01)
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=384, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=mlsd, inputs=[input_image, resolution, value_threshold, distance_threshold], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## MIDAS Depth")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=384, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=midas, inputs=[input_image, resolution], outputs=[gallery])


    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Zoe Depth")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=zoe, inputs=[input_image, resolution], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Normal Bae")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=normalbae, inputs=[input_image, resolution], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## DWPose")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=dwpose, inputs=[input_image, resolution], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Openpose")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            hand_and_face = gr.Checkbox(label='Hand and Face', value=False)
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=openpose, inputs=[input_image, resolution, hand_and_face], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Lineart Anime \n<p>Check Invert to use with Mochi Diffusion.")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            invert = gr.Checkbox(label='Invert', value=True)
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=lineart_anime, inputs=[input_image, resolution, invert], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Lineart \n<p>Check Invert to use with Mochi Diffusion.  Inverted image can also be created here for use with ControlNet Scribble.")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            coarse = gr.Checkbox(label='Using coarse model', value=False)
            invert = gr.Checkbox(label='Invert', value=True)
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=lineart, inputs=[input_image, resolution, coarse, invert], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## InPaint")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy", tool="sketch", height=512)
            invert = gr.Checkbox(label='Invert Mask', value=False)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=inpaint, inputs=[input_image, invert], outputs=[gallery])

#    with gr.Row():
#        gr.Markdown("## Uniformer Segmentation")
#    with gr.Row():
#        with gr.Column():
#            input_image = gr.Image(source='upload', type="numpy")
#            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
#            run_button = gr.Button(label="Run")
#        with gr.Column():
#            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
#    run_button.click(fn=uniformer, inputs=[input_image, resolution], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Oneformer COCO Segmentation")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=oneformer_coco, inputs=[input_image, resolution], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Oneformer ADE20K Segmentation")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=640, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=oneformer_ade20k, inputs=[input_image, resolution], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Content Shuffle")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=content_shuffler, inputs=[input_image, resolution], outputs=[gallery])

    gr.Markdown("<hr>")
    with gr.Row():
        gr.Markdown("## Color Shuffle")
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(source='upload', type="numpy")
            resolution = gr.Slider(label="resolution", minimum=256, maximum=1024, value=512, step=64)
            run_button = gr.Button(label="Run")
        with gr.Column():
            gallery = gr.Gallery(label="Generated images", show_label=False).style(height="auto")
    run_button.click(fn=color_shuffler, inputs=[input_image, resolution], outputs=[gallery])


block.launch(server_name='0.0.0.0')