File size: 81,786 Bytes
483de47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
# coding: utf-8
import os
import gradio as gr
import random
import torch
import cv2
import re
import uuid
from PIL import Image, ImageDraw, ImageOps
import math
import numpy as np
import argparse
import inspect

import shutil
import torchvision
import whisper
import matplotlib.pyplot as plt
from automatic_label_demo import load_model, load_image, get_grounding_output, show_box, show_mask, generate_tags, check_caption
from grounding_dino_demo import plot_boxes_to_image
from segment_anything import build_sam, SamAutomaticMaskGenerator, SamPredictor
from segment_anything.utils.amg import remove_small_regions 

from transformers import CLIPSegProcessor, CLIPSegForImageSegmentation
from transformers import pipeline, BlipProcessor, BlipForConditionalGeneration, BlipForQuestionAnswering
from transformers import AutoImageProcessor, UperNetForSemanticSegmentation

from diffusers import StableDiffusionPipeline, StableDiffusionInpaintPipeline, StableDiffusionInstructPix2PixPipeline
from diffusers import EulerAncestralDiscreteScheduler
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
from controlnet_aux import OpenposeDetector, MLSDdetector, HEDdetector

from langchain.agents.initialize import initialize_agent
from langchain.agents.tools import Tool
from langchain.chains.conversation.memory import ConversationBufferMemory
from langchain.llms.openai import OpenAI

VISUAL_CHATGPT_PREFIX = """Visual ChatGPT is designed to be able to assist with a wide range of text and visual related tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. Visual ChatGPT is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.

Visual ChatGPT is able to process and understand large amounts of text and images. As a language model, Visual ChatGPT can not directly read images, but it has a list of tools to finish different visual tasks. Each image will have a file name formed as "image/xxx.png", and Visual ChatGPT can invoke different tools to indirectly understand pictures. When talking about images, Visual ChatGPT is very strict to the file name and will never fabricate nonexistent files. When using tools to generate new image files, Visual ChatGPT is also known that the image may not be the same as the user's demand, and will use other visual question answering tools or description tools to observe the real image. Visual ChatGPT is able to use tools in a sequence, and is loyal to the tool observation outputs rather than faking the image content and image file name. It will remember to provide the file name from the last tool observation, if a new image is generated.

Human may provide new figures to Visual ChatGPT with a description. The description helps Visual ChatGPT to understand this image, but Visual ChatGPT should use tools to finish following tasks, rather than directly imagine from the description.

Overall, Visual ChatGPT is a powerful visual dialogue assistant tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. 


TOOLS:
------

Visual ChatGPT  has access to the following tools:"""

VISUAL_CHATGPT_FORMAT_INSTRUCTIONS = """To use a tool, please use the following format:

```
Thought: Do I need to use a tool? Yes
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
```

When you have a response to say to the Human, or if you do not need to use a tool, you MUST use the format:

```
Thought: Do I need to use a tool? No
{ai_prefix}: [your response here]
```
"""

VISUAL_CHATGPT_SUFFIX = """You are very strict to the filename correctness and will never fake a file name if it does not exist.
You will remember to provide the image file name loyally if it's provided in the last tool observation.

Begin!

Previous conversation history:
{chat_history}

New input: {input}
Since Visual ChatGPT is a text language model, Visual ChatGPT must use tools to observe images rather than imagination.
The thoughts and observations are only visible for Visual ChatGPT, Visual ChatGPT should remember to repeat important information in the final response for Human. 
Thought: Do I need to use a tool? {agent_scratchpad} Let's think step by step.
"""

VISUAL_CHATGPT_PREFIX_CN = """Visual ChatGPT 旨在能够协助完成范围广泛的文本和视觉相关任务,从回答简单的问题到提供对广泛主题的深入解释和讨论。 Visual ChatGPT 能够根据收到的输入生成类似人类的文本,使其能够进行听起来自然的对话,并提供连贯且与手头主题相关的响应。

Visual ChatGPT 能够处理和理解大量文本和图像。作为一种语言模型,Visual ChatGPT 不能直接读取图像,但它有一系列工具来完成不同的视觉任务。每张图片都会有一个文件名,格式为“image/xxx.png”,Visual ChatGPT可以调用不同的工具来间接理解图片。在谈论图片时,Visual ChatGPT 对文件名的要求非常严格,绝不会伪造不存在的文件。在使用工具生成新的图像文件时,Visual ChatGPT也知道图像可能与用户需求不一样,会使用其他视觉问答工具或描述工具来观察真实图像。 Visual ChatGPT 能够按顺序使用工具,并且忠于工具观察输出,而不是伪造图像内容和图像文件名。如果生成新图像,它将记得提供上次工具观察的文件名。

Human 可能会向 Visual ChatGPT 提供带有描述的新图形。描述帮助 Visual ChatGPT 理解这个图像,但 Visual ChatGPT 应该使用工具来完成以下任务,而不是直接从描述中想象。有些工具将会返回英文描述,但你对用户的聊天应当采用中文。

总的来说,Visual ChatGPT 是一个强大的可视化对话辅助工具,可以帮助处理范围广泛的任务,并提供关于范围广泛的主题的有价值的见解和信息。

工具列表:
------

Visual ChatGPT 可以使用这些工具:"""

VISUAL_CHATGPT_FORMAT_INSTRUCTIONS_CN = """用户使用中文和你进行聊天,但是工具的参数应当使用英文。如果要调用工具,你必须遵循如下格式:

```
Thought: Do I need to use a tool? Yes
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
```

当你不再需要继续调用工具,而是对观察结果进行总结回复时,你必须使用如下格式:


```
Thought: Do I need to use a tool? No
{ai_prefix}: [your response here]
```
"""

VISUAL_CHATGPT_SUFFIX_CN = """你对文件名的正确性非常严格,而且永远不会伪造不存在的文件。

开始!

因为Visual ChatGPT是一个文本语言模型,必须使用工具去观察图片而不是依靠想象。
推理想法和观察结果只对Visual ChatGPT可见,需要记得在最终回复时把重要的信息重复给用户,你只能给用户返回中文句子。我们一步一步思考。在你使用工具时,工具的参数只能是英文。

聊天历史:
{chat_history}

新输入: {input}
Thought: Do I need to use a tool? {agent_scratchpad}
"""

os.makedirs('image', exist_ok=True)


def seed_everything(seed):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    return seed


def prompts(name, description):
    def decorator(func):
        func.name = name
        func.description = description
        return func

    return decorator


def blend_gt2pt(old_image, new_image, sigma=0.15, steps=100):
    new_size = new_image.size
    old_size = old_image.size
    easy_img = np.array(new_image)
    gt_img_array = np.array(old_image)
    pos_w = (new_size[0] - old_size[0]) // 2
    pos_h = (new_size[1] - old_size[1]) // 2

    kernel_h = cv2.getGaussianKernel(old_size[1], old_size[1] * sigma)
    kernel_w = cv2.getGaussianKernel(old_size[0], old_size[0] * sigma)
    kernel = np.multiply(kernel_h, np.transpose(kernel_w))

    kernel[steps:-steps, steps:-steps] = 1
    kernel[:steps, :steps] = kernel[:steps, :steps] / kernel[steps - 1, steps - 1]
    kernel[:steps, -steps:] = kernel[:steps, -steps:] / kernel[steps - 1, -(steps)]
    kernel[-steps:, :steps] = kernel[-steps:, :steps] / kernel[-steps, steps - 1]
    kernel[-steps:, -steps:] = kernel[-steps:, -steps:] / kernel[-steps, -steps]
    kernel = np.expand_dims(kernel, 2)
    kernel = np.repeat(kernel, 3, 2)

    weight = np.linspace(0, 1, steps)
    top = np.expand_dims(weight, 1)
    top = np.repeat(top, old_size[0] - 2 * steps, 1)
    top = np.expand_dims(top, 2)
    top = np.repeat(top, 3, 2)

    weight = np.linspace(1, 0, steps)
    down = np.expand_dims(weight, 1)
    down = np.repeat(down, old_size[0] - 2 * steps, 1)
    down = np.expand_dims(down, 2)
    down = np.repeat(down, 3, 2)

    weight = np.linspace(0, 1, steps)
    left = np.expand_dims(weight, 0)
    left = np.repeat(left, old_size[1] - 2 * steps, 0)
    left = np.expand_dims(left, 2)
    left = np.repeat(left, 3, 2)

    weight = np.linspace(1, 0, steps)
    right = np.expand_dims(weight, 0)
    right = np.repeat(right, old_size[1] - 2 * steps, 0)
    right = np.expand_dims(right, 2)
    right = np.repeat(right, 3, 2)

    kernel[:steps, steps:-steps] = top
    kernel[-steps:, steps:-steps] = down
    kernel[steps:-steps, :steps] = left
    kernel[steps:-steps, -steps:] = right

    pt_gt_img = easy_img[pos_h:pos_h + old_size[1], pos_w:pos_w + old_size[0]]
    gaussian_gt_img = kernel * gt_img_array + (1 - kernel) * pt_gt_img  # gt img with blur img
    gaussian_gt_img = gaussian_gt_img.astype(np.int64)
    easy_img[pos_h:pos_h + old_size[1], pos_w:pos_w + old_size[0]] = gaussian_gt_img
    gaussian_img = Image.fromarray(easy_img)
    return gaussian_img


def cut_dialogue_history(history_memory, keep_last_n_words=500):
    if history_memory is None or len(history_memory) == 0:
        return history_memory
    tokens = history_memory.split()
    n_tokens = len(tokens)
    print(f"history_memory:{history_memory}, n_tokens: {n_tokens}")
    if n_tokens < keep_last_n_words:
        return history_memory
    paragraphs = history_memory.split('\n')
    last_n_tokens = n_tokens
    while last_n_tokens >= keep_last_n_words:
        last_n_tokens -= len(paragraphs[0].split(' '))
        paragraphs = paragraphs[1:]
    return '\n' + '\n'.join(paragraphs)


def get_new_image_name(org_img_name, func_name="update"):
    head_tail = os.path.split(org_img_name)
    head = head_tail[0]
    tail = head_tail[1]
    name_split = tail.split('.')[0].split('_')
    this_new_uuid = str(uuid.uuid4())[:4]
    if len(name_split) == 1:
        most_org_file_name = name_split[0]
    else:
        assert len(name_split) == 4
        most_org_file_name = name_split[3]
    recent_prev_file_name = name_split[0]
    new_file_name = f'{this_new_uuid}_{func_name}_{recent_prev_file_name}_{most_org_file_name}.png'
    return os.path.join(head, new_file_name)



class MaskFormer:
    def __init__(self, device):
        print(f"Initializing MaskFormer to {device}")
        self.device = device
        self.processor = CLIPSegProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
        self.model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined").to(device)

    def inference(self, image_path, text):
        threshold = 0.5
        min_area = 0.02
        padding = 20
        original_image = Image.open(image_path)
        image = original_image.resize((512, 512))
        inputs = self.processor(text=text, images=image, padding="max_length", return_tensors="pt").to(self.device)
        with torch.no_grad():
            outputs = self.model(**inputs)
        mask = torch.sigmoid(outputs[0]).squeeze().cpu().numpy() > threshold
        area_ratio = len(np.argwhere(mask)) / (mask.shape[0] * mask.shape[1])
        if area_ratio < min_area:
            return None
        true_indices = np.argwhere(mask)
        mask_array = np.zeros_like(mask, dtype=bool)
        for idx in true_indices:
            padded_slice = tuple(slice(max(0, i - padding), i + padding + 1) for i in idx)
            mask_array[padded_slice] = True
        visual_mask = (mask_array * 255).astype(np.uint8)
        image_mask = Image.fromarray(visual_mask)
        return image_mask.resize(original_image.size)


class ImageEditing:
    def __init__(self, device):
        print(f"Initializing ImageEditing to {device}")
        self.device = device
        self.mask_former = MaskFormer(device=self.device)
        self.revision = 'fp16' if 'cuda' in device else None
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.inpaint = StableDiffusionInpaintPipeline.from_pretrained(
            "runwayml/stable-diffusion-inpainting", revision=self.revision, torch_dtype=self.torch_dtype).to(device)

    @prompts(name="Replace Something From The Photo",
             description="useful when you want to replace an object from the object description or "
                         "location with another object from its description. "
                         "The input to this tool should be a comma separated string of three, "
                         "representing the image_path, the object to be replaced, the object to be replaced with ")
    def inference_replace(self, inputs):
        image_path, to_be_replaced_txt, replace_with_txt = inputs.split(",")
        original_image = Image.open(image_path)
        original_size = original_image.size
        mask_image = self.mask_former.inference(image_path, to_be_replaced_txt)
        updated_image = self.inpaint(prompt=replace_with_txt, image=original_image.resize((512, 512)),
                                     mask_image=mask_image.resize((512, 512))).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="replace-something")
        updated_image = updated_image.resize(original_size)
        updated_image.save(updated_image_path)
        print(
            f"\nProcessed ImageEditing, Input Image: {image_path}, Replace {to_be_replaced_txt} to {replace_with_txt}, "
            f"Output Image: {updated_image_path}")
        return updated_image_path


class InstructPix2Pix:
    def __init__(self, device):
        print(f"Initializing InstructPix2Pix to {device}")
        self.device = device
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained("timbrooks/instruct-pix2pix",
                                                                           safety_checker=None,
                                                                           torch_dtype=self.torch_dtype).to(device)
        self.pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(self.pipe.scheduler.config)

    @prompts(name="Instruct Image Using Text",
             description="useful when you want to the style of the image to be like the text. "
                         "like: make it look like a painting. or make it like a robot. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the text. ")
    def inference(self, inputs):
        """Change style of image."""
        print("===>Starting InstructPix2Pix Inference")
        image_path, text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        original_image = Image.open(image_path)
        image = self.pipe(text, image=original_image, num_inference_steps=40, image_guidance_scale=1.2).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="pix2pix")
        image.save(updated_image_path)
        print(f"\nProcessed InstructPix2Pix, Input Image: {image_path}, Instruct Text: {text}, "
              f"Output Image: {updated_image_path}")
        return updated_image_path


class Text2Image:
    def __init__(self, device):
        print(f"Initializing Text2Image to {device}")
        self.device = device
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5",
                                                            torch_dtype=self.torch_dtype)
        self.pipe.to(device)
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
                        'fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image From User Input Text",
             description="useful when you want to generate an image from a user input text and save it to a file. "
                         "like: generate an image of an object or something, or generate an image that includes some objects. "
                         "The input to this tool should be a string, representing the text used to generate image. ")
    def inference(self, text):
        image_filename = os.path.join('image', f"{str(uuid.uuid4())[:8]}.png")
        prompt = text + ', ' + self.a_prompt
        image = self.pipe(prompt, negative_prompt=self.n_prompt).images[0]
        image.save(image_filename)
        print(
            f"\nProcessed Text2Image, Input Text: {text}, Output Image: {image_filename}")
        return image_filename


class ImageCaptioning:
    def __init__(self, device):
        print(f"Initializing ImageCaptioning to {device}")
        self.device = device
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
        self.model = BlipForConditionalGeneration.from_pretrained(
            "Salesforce/blip-image-captioning-base", torch_dtype=self.torch_dtype).to(self.device)

    @prompts(name="Get Photo Description",
             description="useful when you want to know what is inside the photo. receives image_path as input. "
                         "The input to this tool should be a string, representing the image_path. ")
    def inference(self, image_path):
        inputs = self.processor(Image.open(image_path), return_tensors="pt").to(self.device, self.torch_dtype)
        out = self.model.generate(**inputs)
        captions = self.processor.decode(out[0], skip_special_tokens=True)
        print(f"\nProcessed ImageCaptioning, Input Image: {image_path}, Output Text: {captions}")
        return captions


class Image2Canny:
    def __init__(self, device):
        print("Initializing Image2Canny")
        self.low_threshold = 100
        self.high_threshold = 200

    @prompts(name="Edge Detection On Image",
             description="useful when you want to detect the edge of the image. "
                         "like: detect the edges of this image, or canny detection on image, "
                         "or perform edge detection on this image, or detect the canny image of this image. "
                         "The input to this tool should be a string, representing the image_path")
    def inference(self, inputs):
        image = Image.open(inputs)
        image = np.array(image)
        canny = cv2.Canny(image, self.low_threshold, self.high_threshold)
        canny = canny[:, :, None]
        canny = np.concatenate([canny, canny, canny], axis=2)
        canny = Image.fromarray(canny)
        updated_image_path = get_new_image_name(inputs, func_name="edge")
        canny.save(updated_image_path)
        print(f"\nProcessed Image2Canny, Input Image: {inputs}, Output Text: {updated_image_path}")
        return updated_image_path


class CannyText2Image:
    def __init__(self, device):
        print(f"Initializing CannyText2Image to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-canny",
                                                          torch_dtype=self.torch_dtype)
        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
            torch_dtype=self.torch_dtype)
        self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
        self.pipe.to(device)
        self.seed = -1
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
                            'fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image Condition On Canny Image",
             description="useful when you want to generate a new real image from both the user description and a canny image."
                         " like: generate a real image of a object or something from this canny image,"
                         " or generate a new real image of a object or something from this edge image. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the user description. ")
    def inference(self, inputs):
        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        image = Image.open(image_path)
        self.seed = random.randint(0, 65535)
        seed_everything(self.seed)
        prompt = f'{instruct_text}, {self.a_prompt}'
        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
                          guidance_scale=9.0).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="canny2image")
        image.save(updated_image_path)
        print(f"\nProcessed CannyText2Image, Input Canny: {image_path}, Input Text: {instruct_text}, "
              f"Output Text: {updated_image_path}")
        return updated_image_path


class Image2Line:
    def __init__(self, device):
        print("Initializing Image2Line")
        self.detector = MLSDdetector.from_pretrained('lllyasviel/ControlNet')

    @prompts(name="Line Detection On Image",
             description="useful when you want to detect the straight line of the image. "
                         "like: detect the straight lines of this image, or straight line detection on image, "
                         "or perform straight line detection on this image, or detect the straight line image of this image. "
                         "The input to this tool should be a string, representing the image_path")
    def inference(self, inputs):
        image = Image.open(inputs)
        mlsd = self.detector(image)
        updated_image_path = get_new_image_name(inputs, func_name="line-of")
        mlsd.save(updated_image_path)
        print(f"\nProcessed Image2Line, Input Image: {inputs}, Output Line: {updated_image_path}")
        return updated_image_path


class LineText2Image:
    def __init__(self, device):
        print(f"Initializing LineText2Image to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-mlsd",
                                                          torch_dtype=self.torch_dtype)
        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
            torch_dtype=self.torch_dtype
        )
        self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
        self.pipe.to(device)
        self.seed = -1
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
                            'fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image Condition On Line Image",
             description="useful when you want to generate a new real image from both the user description "
                         "and a straight line image. "
                         "like: generate a real image of a object or something from this straight line image, "
                         "or generate a new real image of a object or something from this straight lines. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the user description. ")
    def inference(self, inputs):
        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        image = Image.open(image_path)
        self.seed = random.randint(0, 65535)
        seed_everything(self.seed)
        prompt = f'{instruct_text}, {self.a_prompt}'
        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
                          guidance_scale=9.0).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="line2image")
        image.save(updated_image_path)
        print(f"\nProcessed LineText2Image, Input Line: {image_path}, Input Text: {instruct_text}, "
              f"Output Text: {updated_image_path}")
        return updated_image_path


class Image2Hed:
    def __init__(self, device):
        print("Initializing Image2Hed")
        self.detector = HEDdetector.from_pretrained('lllyasviel/ControlNet')

    @prompts(name="Hed Detection On Image",
             description="useful when you want to detect the soft hed boundary of the image. "
                         "like: detect the soft hed boundary of this image, or hed boundary detection on image, "
                         "or perform hed boundary detection on this image, or detect soft hed boundary image of this image. "
                         "The input to this tool should be a string, representing the image_path")
    def inference(self, inputs):
        image = Image.open(inputs)
        hed = self.detector(image)
        updated_image_path = get_new_image_name(inputs, func_name="hed-boundary")
        hed.save(updated_image_path)
        print(f"\nProcessed Image2Hed, Input Image: {inputs}, Output Hed: {updated_image_path}")
        return updated_image_path


class HedText2Image:
    def __init__(self, device):
        print(f"Initializing HedText2Image to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-hed",
                                                          torch_dtype=self.torch_dtype)
        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
            torch_dtype=self.torch_dtype
        )
        self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
        self.pipe.to(device)
        self.seed = -1
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
                            'fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image Condition On Soft Hed Boundary Image",
             description="useful when you want to generate a new real image from both the user description "
                         "and a soft hed boundary image. "
                         "like: generate a real image of a object or something from this soft hed boundary image, "
                         "or generate a new real image of a object or something from this hed boundary. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the user description")
    def inference(self, inputs):
        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        image = Image.open(image_path)
        self.seed = random.randint(0, 65535)
        seed_everything(self.seed)
        prompt = f'{instruct_text}, {self.a_prompt}'
        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
                          guidance_scale=9.0).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="hed2image")
        image.save(updated_image_path)
        print(f"\nProcessed HedText2Image, Input Hed: {image_path}, Input Text: {instruct_text}, "
              f"Output Image: {updated_image_path}")
        return updated_image_path


class Image2Scribble:
    def __init__(self, device):
        print("Initializing Image2Scribble")
        self.detector = HEDdetector.from_pretrained('lllyasviel/ControlNet')

    @prompts(name="Sketch Detection On Image",
             description="useful when you want to generate a scribble of the image. "
                         "like: generate a scribble of this image, or generate a sketch from this image, "
                         "detect the sketch from this image. "
                         "The input to this tool should be a string, representing the image_path")
    def inference(self, inputs):
        image = Image.open(inputs)
        scribble = self.detector(image, scribble=True)
        updated_image_path = get_new_image_name(inputs, func_name="scribble")
        scribble.save(updated_image_path)
        print(f"\nProcessed Image2Scribble, Input Image: {inputs}, Output Scribble: {updated_image_path}")
        return updated_image_path


class ScribbleText2Image:
    def __init__(self, device):
        print(f"Initializing ScribbleText2Image to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-scribble",
                                                          torch_dtype=self.torch_dtype)
        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
            torch_dtype=self.torch_dtype
        )
        self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
        self.pipe.to(device)
        self.seed = -1
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
                            'fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image Condition On Sketch Image",
             description="useful when you want to generate a new real image from both the user description and "
                         "a scribble image or a sketch image. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the user description")
    def inference(self, inputs):
        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        image = Image.open(image_path)
        self.seed = random.randint(0, 65535)
        seed_everything(self.seed)
        prompt = f'{instruct_text}, {self.a_prompt}'
        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
                          guidance_scale=9.0).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="scribble2image")
        image.save(updated_image_path)
        print(f"\nProcessed ScribbleText2Image, Input Scribble: {image_path}, Input Text: {instruct_text}, "
              f"Output Image: {updated_image_path}")
        return updated_image_path


class Image2Pose:
    def __init__(self, device):
        print("Initializing Image2Pose")
        self.detector = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')

    @prompts(name="Pose Detection On Image",
             description="useful when you want to detect the human pose of the image. "
                         "like: generate human poses of this image, or generate a pose image from this image. "
                         "The input to this tool should be a string, representing the image_path")
    def inference(self, inputs):
        image = Image.open(inputs)
        pose = self.detector(image)
        updated_image_path = get_new_image_name(inputs, func_name="human-pose")
        pose.save(updated_image_path)
        print(f"\nProcessed Image2Pose, Input Image: {inputs}, Output Pose: {updated_image_path}")
        return updated_image_path


class PoseText2Image:
    def __init__(self, device):
        print(f"Initializing PoseText2Image to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-openpose",
                                                          torch_dtype=self.torch_dtype)
        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
            torch_dtype=self.torch_dtype)
        self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
        self.pipe.to(device)
        self.num_inference_steps = 20
        self.seed = -1
        self.unconditional_guidance_scale = 9.0
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit,' \
                            ' fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image Condition On Pose Image",
             description="useful when you want to generate a new real image from both the user description "
                         "and a human pose image. "
                         "like: generate a real image of a human from this human pose image, "
                         "or generate a new real image of a human from this pose. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the user description")
    def inference(self, inputs):
        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        image = Image.open(image_path)
        self.seed = random.randint(0, 65535)
        seed_everything(self.seed)
        prompt = f'{instruct_text}, {self.a_prompt}'
        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
                          guidance_scale=9.0).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="pose2image")
        image.save(updated_image_path)
        print(f"\nProcessed PoseText2Image, Input Pose: {image_path}, Input Text: {instruct_text}, "
              f"Output Image: {updated_image_path}")
        return updated_image_path


class Image2Seg:
    def __init__(self, device):
        print("Initializing Image2Seg")
        self.image_processor = AutoImageProcessor.from_pretrained("openmmlab/upernet-convnext-small")
        self.image_segmentor = UperNetForSemanticSegmentation.from_pretrained("openmmlab/upernet-convnext-small")
        self.ade_palette = [[120, 120, 120], [180, 120, 120], [6, 230, 230], [80, 50, 50],
                            [4, 200, 3], [120, 120, 80], [140, 140, 140], [204, 5, 255],
                            [230, 230, 230], [4, 250, 7], [224, 5, 255], [235, 255, 7],
                            [150, 5, 61], [120, 120, 70], [8, 255, 51], [255, 6, 82],
                            [143, 255, 140], [204, 255, 4], [255, 51, 7], [204, 70, 3],
                            [0, 102, 200], [61, 230, 250], [255, 6, 51], [11, 102, 255],
                            [255, 7, 71], [255, 9, 224], [9, 7, 230], [220, 220, 220],
                            [255, 9, 92], [112, 9, 255], [8, 255, 214], [7, 255, 224],
                            [255, 184, 6], [10, 255, 71], [255, 41, 10], [7, 255, 255],
                            [224, 255, 8], [102, 8, 255], [255, 61, 6], [255, 194, 7],
                            [255, 122, 8], [0, 255, 20], [255, 8, 41], [255, 5, 153],
                            [6, 51, 255], [235, 12, 255], [160, 150, 20], [0, 163, 255],
                            [140, 140, 140], [250, 10, 15], [20, 255, 0], [31, 255, 0],
                            [255, 31, 0], [255, 224, 0], [153, 255, 0], [0, 0, 255],
                            [255, 71, 0], [0, 235, 255], [0, 173, 255], [31, 0, 255],
                            [11, 200, 200], [255, 82, 0], [0, 255, 245], [0, 61, 255],
                            [0, 255, 112], [0, 255, 133], [255, 0, 0], [255, 163, 0],
                            [255, 102, 0], [194, 255, 0], [0, 143, 255], [51, 255, 0],
                            [0, 82, 255], [0, 255, 41], [0, 255, 173], [10, 0, 255],
                            [173, 255, 0], [0, 255, 153], [255, 92, 0], [255, 0, 255],
                            [255, 0, 245], [255, 0, 102], [255, 173, 0], [255, 0, 20],
                            [255, 184, 184], [0, 31, 255], [0, 255, 61], [0, 71, 255],
                            [255, 0, 204], [0, 255, 194], [0, 255, 82], [0, 10, 255],
                            [0, 112, 255], [51, 0, 255], [0, 194, 255], [0, 122, 255],
                            [0, 255, 163], [255, 153, 0], [0, 255, 10], [255, 112, 0],
                            [143, 255, 0], [82, 0, 255], [163, 255, 0], [255, 235, 0],
                            [8, 184, 170], [133, 0, 255], [0, 255, 92], [184, 0, 255],
                            [255, 0, 31], [0, 184, 255], [0, 214, 255], [255, 0, 112],
                            [92, 255, 0], [0, 224, 255], [112, 224, 255], [70, 184, 160],
                            [163, 0, 255], [153, 0, 255], [71, 255, 0], [255, 0, 163],
                            [255, 204, 0], [255, 0, 143], [0, 255, 235], [133, 255, 0],
                            [255, 0, 235], [245, 0, 255], [255, 0, 122], [255, 245, 0],
                            [10, 190, 212], [214, 255, 0], [0, 204, 255], [20, 0, 255],
                            [255, 255, 0], [0, 153, 255], [0, 41, 255], [0, 255, 204],
                            [41, 0, 255], [41, 255, 0], [173, 0, 255], [0, 245, 255],
                            [71, 0, 255], [122, 0, 255], [0, 255, 184], [0, 92, 255],
                            [184, 255, 0], [0, 133, 255], [255, 214, 0], [25, 194, 194],
                            [102, 255, 0], [92, 0, 255]]

    @prompts(name="Segmentation On Image",
             description="useful when you want to detect segmentations of the image. "
                         "like: segment this image, or generate segmentations on this image, "
                         "or perform segmentation on this image. "
                         "The input to this tool should be a string, representing the image_path")
    def inference(self, inputs):
        image = Image.open(inputs)
        pixel_values = self.image_processor(image, return_tensors="pt").pixel_values
        with torch.no_grad():
            outputs = self.image_segmentor(pixel_values)
        seg = self.image_processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
        color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8)  # height, width, 3
        palette = np.array(self.ade_palette)
        for label, color in enumerate(palette):
            color_seg[seg == label, :] = color
        color_seg = color_seg.astype(np.uint8)
        segmentation = Image.fromarray(color_seg)
        updated_image_path = get_new_image_name(inputs, func_name="segmentation")
        segmentation.save(updated_image_path)
        print(f"\nProcessed Image2Seg, Input Image: {inputs}, Output Pose: {updated_image_path}")
        return updated_image_path


class SegText2Image:
    def __init__(self, device):
        print(f"Initializing SegText2Image to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-seg",
                                                          torch_dtype=self.torch_dtype)
        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
            torch_dtype=self.torch_dtype)
        self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
        self.pipe.to(device)
        self.seed = -1
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit,' \
                            ' fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image Condition On Segmentations",
             description="useful when you want to generate a new real image from both the user description and segmentations. "
                         "like: generate a real image of a object or something from this segmentation image, "
                         "or generate a new real image of a object or something from these segmentations. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the user description")
    def inference(self, inputs):
        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        image = Image.open(image_path)
        self.seed = random.randint(0, 65535)
        seed_everything(self.seed)
        prompt = f'{instruct_text}, {self.a_prompt}'
        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
                          guidance_scale=9.0).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="segment2image")
        image.save(updated_image_path)
        print(f"\nProcessed SegText2Image, Input Seg: {image_path}, Input Text: {instruct_text}, "
              f"Output Image: {updated_image_path}")
        return updated_image_path


class Image2Depth:
    def __init__(self, device):
        print("Initializing Image2Depth")
        self.depth_estimator = pipeline('depth-estimation')

    @prompts(name="Predict Depth On Image",
             description="useful when you want to detect depth of the image. like: generate the depth from this image, "
                         "or detect the depth map on this image, or predict the depth for this image. "
                         "The input to this tool should be a string, representing the image_path")
    def inference(self, inputs):
        image = Image.open(inputs)
        depth = self.depth_estimator(image)['depth']
        depth = np.array(depth)
        depth = depth[:, :, None]
        depth = np.concatenate([depth, depth, depth], axis=2)
        depth = Image.fromarray(depth)
        updated_image_path = get_new_image_name(inputs, func_name="depth")
        depth.save(updated_image_path)
        print(f"\nProcessed Image2Depth, Input Image: {inputs}, Output Depth: {updated_image_path}")
        return updated_image_path


class DepthText2Image:
    def __init__(self, device):
        print(f"Initializing DepthText2Image to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.controlnet = ControlNetModel.from_pretrained(
            "fusing/stable-diffusion-v1-5-controlnet-depth", torch_dtype=self.torch_dtype)
        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
            torch_dtype=self.torch_dtype)
        self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
        self.pipe.to(device)
        self.seed = -1
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit,' \
                            ' fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image Condition On Depth",
             description="useful when you want to generate a new real image from both the user description and depth image. "
                         "like: generate a real image of a object or something from this depth image, "
                         "or generate a new real image of a object or something from the depth map. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the user description")
    def inference(self, inputs):
        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        image = Image.open(image_path)
        self.seed = random.randint(0, 65535)
        seed_everything(self.seed)
        prompt = f'{instruct_text}, {self.a_prompt}'
        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
                          guidance_scale=9.0).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="depth2image")
        image.save(updated_image_path)
        print(f"\nProcessed DepthText2Image, Input Depth: {image_path}, Input Text: {instruct_text}, "
              f"Output Image: {updated_image_path}")
        return updated_image_path


class Image2Normal:
    def __init__(self, device):
        print("Initializing Image2Normal")
        self.depth_estimator = pipeline("depth-estimation", model="Intel/dpt-hybrid-midas")
        self.bg_threhold = 0.4

    @prompts(name="Predict Normal Map On Image",
             description="useful when you want to detect norm map of the image. "
                         "like: generate normal map from this image, or predict normal map of this image. "
                         "The input to this tool should be a string, representing the image_path")
    def inference(self, inputs):
        image = Image.open(inputs)
        original_size = image.size
        image = self.depth_estimator(image)['predicted_depth'][0]
        image = image.numpy()
        image_depth = image.copy()
        image_depth -= np.min(image_depth)
        image_depth /= np.max(image_depth)
        x = cv2.Sobel(image, cv2.CV_32F, 1, 0, ksize=3)
        x[image_depth < self.bg_threhold] = 0
        y = cv2.Sobel(image, cv2.CV_32F, 0, 1, ksize=3)
        y[image_depth < self.bg_threhold] = 0
        z = np.ones_like(x) * np.pi * 2.0
        image = np.stack([x, y, z], axis=2)
        image /= np.sum(image ** 2.0, axis=2, keepdims=True) ** 0.5
        image = (image * 127.5 + 127.5).clip(0, 255).astype(np.uint8)
        image = Image.fromarray(image)
        image = image.resize(original_size)
        updated_image_path = get_new_image_name(inputs, func_name="normal-map")
        image.save(updated_image_path)
        print(f"\nProcessed Image2Normal, Input Image: {inputs}, Output Depth: {updated_image_path}")
        return updated_image_path


class NormalText2Image:
    def __init__(self, device):
        print(f"Initializing NormalText2Image to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.controlnet = ControlNetModel.from_pretrained(
            "fusing/stable-diffusion-v1-5-controlnet-normal", torch_dtype=self.torch_dtype)
        self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
            torch_dtype=self.torch_dtype)
        self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
        self.pipe.to(device)
        self.seed = -1
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit,' \
                            ' fewer digits, cropped, worst quality, low quality'

    @prompts(name="Generate Image Condition On Normal Map",
             description="useful when you want to generate a new real image from both the user description and normal map. "
                         "like: generate a real image of a object or something from this normal map, "
                         "or generate a new real image of a object or something from the normal map. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the user description")
    def inference(self, inputs):
        image_path, instruct_text = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        image = Image.open(image_path)
        self.seed = random.randint(0, 65535)
        seed_everything(self.seed)
        prompt = f'{instruct_text}, {self.a_prompt}'
        image = self.pipe(prompt, image, num_inference_steps=20, eta=0.0, negative_prompt=self.n_prompt,
                          guidance_scale=9.0).images[0]
        updated_image_path = get_new_image_name(image_path, func_name="normal2image")
        image.save(updated_image_path)
        print(f"\nProcessed NormalText2Image, Input Normal: {image_path}, Input Text: {instruct_text}, "
              f"Output Image: {updated_image_path}")
        return updated_image_path


class VisualQuestionAnswering:
    def __init__(self, device):
        print(f"Initializing VisualQuestionAnswering to {device}")
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.device = device
        self.processor = BlipProcessor.from_pretrained("Salesforce/blip-vqa-base")
        self.model = BlipForQuestionAnswering.from_pretrained(
            "Salesforce/blip-vqa-base", torch_dtype=self.torch_dtype).to(self.device)

    @prompts(name="Answer Question About The Image",
             description="useful when you need an answer for a question based on an image. "
                         "like: what is the background color of the last image, how many cats in this figure, what is in this figure. "
                         "The input to this tool should be a comma separated string of two, representing the image_path and the question")
    def inference(self, inputs):
        image_path, question = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        raw_image = Image.open(image_path).convert('RGB')
        inputs = self.processor(raw_image, question, return_tensors="pt").to(self.device, self.torch_dtype)
        out = self.model.generate(**inputs)
        answer = self.processor.decode(out[0], skip_special_tokens=True)
        print(f"\nProcessed VisualQuestionAnswering, Input Image: {image_path}, Input Question: {question}, "
              f"Output Answer: {answer}")
        return answer


class InfinityOutPainting:
    template_model = True # Add this line to show this is a template model.
    def __init__(self, ImageCaptioning, ImageEditing, VisualQuestionAnswering):
        self.llm = OpenAI(temperature=0)
        self.ImageCaption = ImageCaptioning
        self.ImageEditing = ImageEditing
        self.ImageVQA = VisualQuestionAnswering
        self.a_prompt = 'best quality, extremely detailed'
        self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
                        'fewer digits, cropped, worst quality, low quality'

    def get_BLIP_vqa(self, image, question):
        inputs = self.ImageVQA.processor(image, question, return_tensors="pt").to(self.ImageVQA.device,
                                                                                  self.ImageVQA.torch_dtype)
        out = self.ImageVQA.model.generate(**inputs)
        answer = self.ImageVQA.processor.decode(out[0], skip_special_tokens=True)
        print(f"\nProcessed VisualQuestionAnswering, Input Question: {question}, Output Answer: {answer}")
        return answer

    def get_BLIP_caption(self, image):
        inputs = self.ImageCaption.processor(image, return_tensors="pt").to(self.ImageCaption.device,
                                                                                self.ImageCaption.torch_dtype)
        out = self.ImageCaption.model.generate(**inputs)
        BLIP_caption = self.ImageCaption.processor.decode(out[0], skip_special_tokens=True)
        return BLIP_caption

    def check_prompt(self, prompt):
        check = f"Here is a paragraph with adjectives. " \
                f"{prompt} " \
                f"Please change all plural forms in the adjectives to singular forms. "
        return self.llm(check)

    def get_imagine_caption(self, image, imagine):
        BLIP_caption = self.get_BLIP_caption(image)
        background_color = self.get_BLIP_vqa(image, 'what is the background color of this image')
        style = self.get_BLIP_vqa(image, 'what is the style of this image')
        imagine_prompt = f"let's pretend you are an excellent painter and now " \
                         f"there is an incomplete painting with {BLIP_caption} in the center, " \
                         f"please imagine the complete painting and describe it" \
                         f"you should consider the background color is {background_color}, the style is {style}" \
                         f"You should make the painting as vivid and realistic as possible" \
                         f"You can not use words like painting or picture" \
                         f"and you should use no more than 50 words to describe it"
        caption = self.llm(imagine_prompt) if imagine else BLIP_caption
        caption = self.check_prompt(caption)
        print(f'BLIP observation: {BLIP_caption}, ChatGPT imagine to {caption}') if imagine else print(
            f'Prompt: {caption}')
        return caption

    def resize_image(self, image, max_size=1000000, multiple=8):
        aspect_ratio = image.size[0] / image.size[1]
        new_width = int(math.sqrt(max_size * aspect_ratio))
        new_height = int(new_width / aspect_ratio)
        new_width, new_height = new_width - (new_width % multiple), new_height - (new_height % multiple)
        return image.resize((new_width, new_height))

    def dowhile(self, original_img, tosize, expand_ratio, imagine, usr_prompt):
        old_img = original_img
        while (old_img.size != tosize):
            prompt = self.check_prompt(usr_prompt) if usr_prompt else self.get_imagine_caption(old_img, imagine)
            crop_w = 15 if old_img.size[0] != tosize[0] else 0
            crop_h = 15 if old_img.size[1] != tosize[1] else 0
            old_img = ImageOps.crop(old_img, (crop_w, crop_h, crop_w, crop_h))
            temp_canvas_size = (expand_ratio * old_img.width if expand_ratio * old_img.width < tosize[0] else tosize[0],
                                expand_ratio * old_img.height if expand_ratio * old_img.height < tosize[1] else tosize[
                                    1])
            temp_canvas, temp_mask = Image.new("RGB", temp_canvas_size, color="white"), Image.new("L", temp_canvas_size,
                                                                                                  color="white")
            x, y = (temp_canvas.width - old_img.width) // 2, (temp_canvas.height - old_img.height) // 2
            temp_canvas.paste(old_img, (x, y))
            temp_mask.paste(0, (x, y, x + old_img.width, y + old_img.height))
            resized_temp_canvas, resized_temp_mask = self.resize_image(temp_canvas), self.resize_image(temp_mask)
            image = self.ImageEditing.inpaint(prompt=prompt, image=resized_temp_canvas, mask_image=resized_temp_mask,
                                              height=resized_temp_canvas.height, width=resized_temp_canvas.width,
                                              num_inference_steps=50).images[0].resize(
                (temp_canvas.width, temp_canvas.height), Image.ANTIALIAS)
            image = blend_gt2pt(old_img, image)
            old_img = image
        return old_img

    @prompts(name="Extend An Image",
             description="useful when you need to extend an image into a larger image."
                         "like: extend the image into a resolution of 2048x1024, extend the image into 2048x1024. "
                         "The input to this tool should be a comma separated string of two, representing the image_path and the resolution of widthxheight")
    def inference(self, inputs):
        image_path, resolution = inputs.split(',')
        width, height = resolution.split('x')
        tosize = (int(width), int(height))
        image = Image.open(image_path)
        image = ImageOps.crop(image, (10, 10, 10, 10))
        out_painted_image = self.dowhile(image, tosize, 4, True, False)
        updated_image_path = get_new_image_name(image_path, func_name="outpainting")
        out_painted_image.save(updated_image_path)
        print(f"\nProcessed InfinityOutPainting, Input Image: {image_path}, Input Resolution: {resolution}, "
              f"Output Image: {updated_image_path}")
        return updated_image_path

#############################################New Tool#############################################
class Grounded_dino_sam_inpainting:
    def __init__(self, device):
        print(f"Initializing BLIP")
        self.device = device
        self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
        self.blip_processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
        self.blip_model = BlipForConditionalGeneration.from_pretrained(
            "Salesforce/blip-image-captioning-large", torch_dtype=self.torch_dtype
        ).to(self.device)
        print(f"Initializing GroundingDINO")
        self.dino_model = load_model(
            model_config_path="GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py", 
            model_checkpoint_path="groundingdino_swint_ogc.pth", 
            device=self.device
        )
        print(f"Initializing Segment Anthing")
        self.sam_model = build_sam(checkpoint="sam_vit_h_4b8939.pth").to(self.device)
        print(f"Initializing Stable Diffusion")
        self.sd_pipe = StableDiffusionInpaintPipeline.from_pretrained(
            "runwayml/stable-diffusion-inpainting", torch_dtype=self.torch_dtype
        ).to(self.device)

    @prompts(name="Get Photo Description",
             description="useful when you want to know what is inside the photo. receives image_path as input. "
                         "The input to this tool should be a string, representing the image_path. ")
    def inference_caption(self, image_path):
        inputs = self.blip_processor(Image.open(image_path), return_tensors="pt").to(self.device, self.torch_dtype)
        out = self.blip_model.generate(**inputs)
        captions = self.blip_processor.decode(out[0], skip_special_tokens=True)
        print(f"\nProcessed ImageCaptioning, Input Image: {image_path}, Output Text: {captions}")
        return captions
    
    def _detect_object(self, image_path, text_prompt, func_name):
        image_pil, image = load_image(image_path)
        boxes_filt, scores, pred_phrases = get_grounding_output(
            self.dino_model, image, text_prompt, 0.3, 0.25, device=self.device
        )
        # use NMS to handle overlapped boxes
        print(f"Before NMS: {boxes_filt.shape[0]} boxes")
        nms_idx = torchvision.ops.nms(boxes_filt, scores, 0.5).numpy().tolist()
        boxes_filt = boxes_filt[nms_idx]
        pred_phrases = [pred_phrases[idx] for idx in nms_idx]
        print(f"After NMS: {boxes_filt.shape[0]} boxes")
        size = image_pil.size
        pred_dict = {
            "boxes": boxes_filt,
            "size": [size[1], size[0]],  # H,W
            "labels": pred_phrases,
        }
        image_with_box = plot_boxes_to_image(image_pil, pred_dict)[0]
        updated_image_path = get_new_image_name(image_path, func_name)
        image_with_box.save(updated_image_path)
        return updated_image_path

    @prompts(name="Detect One Object In Image",
             description="useful when you want to detect the specific object in the image. "
                         "like: detect the black dog in the image. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the description of specific object.")
    def inference_detect_one_object(self, inputs):
        image_path, text_prompt = inputs.split(',')
        print(f"\nInput Text Prompt: {text_prompt}")
        updated_image_path = self._detect_object(image_path, text_prompt, func_name="det-object")
        print(f"Processed DetectOneObject, Input Image: {image_path}, Output Image: {updated_image_path}")
        return updated_image_path

    @prompts(name="Detect Multiple Objects In Image",
             description="useful when you want to detect two or more specific objects in the image. "
                         "like: detect the black dog and white cat in the image. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the description of multiple specific objects. "
                         "Different description should be separated by symbol '&', "
                         "like 'black dog & white cat'. ")
    def inference_detect_multi_object(self, inputs):
        image_path, text_prompt = inputs.split(',')
        processed_text_prompt = text_prompt.replace(' &', ',')
        print(f"\nOriginal Text Prompt: {text_prompt}, Input Text Prompt: {processed_text_prompt}")
        updated_image_path = self._detect_object(image_path, text_prompt, func_name="det-objects")
        print(f"Processed DetectMultiObject, Input Image: {image_path}, Output Image: {updated_image_path}")
        return updated_image_path

    # modified from https://github.com/Cheems-Seminar/segment-anything-and-name-it/blob/58408f1e4e340f565c5ef6b0c71920cdcd30b213/chatbot.py#L1046
    @prompts(name="Segment Anything in Image",
             description="useful when you want to segment anything in the image. "
                         "like: segment anything in the image. "
                         "The input to this tool should be a string, representing the image_path. ")
    def inference_segment_anything(self, image_path):
        image = cv2.imread(image_path)
        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
        mask_generator = SamAutomaticMaskGenerator(self.sam_model)
        anns = mask_generator.generate(image)
        plt.figure(figsize=(10, 10))
        plt.imshow(image)
        sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True)
        ax = plt.gca()
        ax.set_autoscale_on(False)
        for ann in sorted_anns:
            m = ann['segmentation']
            img = np.ones((m.shape[0], m.shape[1], 3))
            color_mask = np.random.random((1, 3)).tolist()[0]
            for i in range(3):
                img[:,:,i] = color_mask[i]
            ax.imshow(np.dstack((img, m*0.35)))
        plt.axis('off')
        updated_image_path = get_new_image_name(image_path, func_name="seg-any")
        plt.savefig(updated_image_path, bbox_inches='tight', dpi=300, pad_inches=0.0)
        print(f"\nProcessed SegmentAnything, Input Image: {image_path}, Output Image: {updated_image_path}")
        return updated_image_path

    def _segment_object(self, image_path, text_prompt, func_name):
        image_pil, image = load_image(image_path)
        # run grounding dino model
        boxes_filt, scores, pred_phrases = get_grounding_output(
            self.dino_model, image, text_prompt, 0.25, 0.2, device=self.device
        )
        # initialize SAM
        predictor = SamPredictor(self.sam_model)
        image = cv2.imread(image_path)
        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
        predictor.set_image(image)
        size = image_pil.size
        H, W = size[1], size[0]
        for i in range(boxes_filt.size(0)):
            boxes_filt[i] = boxes_filt[i] * torch.Tensor([W, H, W, H])
            boxes_filt[i][:2] -= boxes_filt[i][2:] / 2
            boxes_filt[i][2:] += boxes_filt[i][:2]
        boxes_filt = boxes_filt.cpu()
        # use NMS to handle overlapped boxes
        print(f"Before NMS: {boxes_filt.shape[0]} boxes")
        nms_idx = torchvision.ops.nms(boxes_filt, scores, 0.5).numpy().tolist()
        boxes_filt = boxes_filt[nms_idx]
        pred_phrases = [pred_phrases[idx] for idx in nms_idx]
        print(f"After NMS: {boxes_filt.shape[0]} boxes")
        # generate mask
        transformed_boxes = predictor.transform.apply_boxes_torch(boxes_filt, image.shape[:2])
        masks, _, _ = predictor.predict_torch(
            point_coords = None,
            point_labels = None,
            boxes = transformed_boxes.to(self.device),
            multimask_output = False,
        )
        # remove the mask when area < area_thresh (in pixels)
        new_masks = []
        for mask in masks:
            # reshape to be used in remove_small_regions()
            mask = mask.cpu().numpy().squeeze()
            mask, _ = remove_small_regions(mask, 100, mode="holes")
            mask, _ = remove_small_regions(mask, 100, mode="islands")
            new_masks.append(torch.as_tensor(mask).unsqueeze(0))
        masks = torch.stack(new_masks, dim=0)
        # add box and mask in the image
        plt.figure(figsize=(10, 10))
        plt.imshow(image)
        for mask in masks:
            show_mask(mask.cpu().numpy(), plt.gca(), random_color=True)
        for box, label in zip(boxes_filt, pred_phrases):
            show_box(box.numpy(), plt.gca(), label)
        plt.axis('off')
        updated_image_path = get_new_image_name(image_path, func_name)
        plt.savefig(updated_image_path, bbox_inches='tight', dpi=300, pad_inches=0.0)
        return updated_image_path, pred_phrases

    @prompts(name="Segment One Object In Image",
             description="useful when you want to segment the specific object in the image. "
                         "like: segment the black dog in the image, or mask the black dog in the image. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the description of specific object.")
    def inference_segment_one_object(self, inputs):
        image_path, text_prompt = inputs.split(',')
        print(f"\nInput Text Prompt: {text_prompt}")
        updated_image_path, _ = self._segment_object(image_path, text_prompt, func_name="seg-object")
        print(f"Processed SegmentOneObject, Input Image: {image_path}, Output Image: {updated_image_path}")
        return updated_image_path

    @prompts(name="Segment Multiple Object In Image",
             description="useful when you want to segment two or more specific objects in the image. "
                         "like: segment the black dog and white cat in the image. "
                         "The input to this tool should be a comma separated string of two, "
                         "representing the image_path and the description of multiple specific objects. "
                         "Different description should be separated by symbol '&', "
                         "like 'black dog & white cat'. ")
    def inference_segment_multi_object(self, inputs):
        image_path, text_prompt = inputs.split(',')
        processed_text_prompt = text_prompt.replace(' &', ',')
        print("\nOriginal Text Prompt: {text_prompt}, Input Text Prompt: {processed_text_prompt}, ")
        updated_image_path, _ = self._segment_object(image_path, text_prompt, func_name="seg-objects")
        print(f"Processed SegmentMultiObject, Input Image: {image_path}, Output Image: {updated_image_path}")
        return updated_image_path

    @prompts(name="Auto Label the Image",
             description="useful when you want to label the image automatically. "
                         "like: help me label the image. "
                         "The input to this tool should be a string, representing the image_path. ")
    def inference_auto_segment_object(self, image_path):
        inputs = self.blip_processor(Image.open(image_path), return_tensors="pt").to(self.device, self.torch_dtype)
        out = self.blip_model.generate(**inputs)
        caption = self.blip_processor.decode(out[0], skip_special_tokens=True)
        text_prompt = generate_tags(caption, split=",")
        print(f"\nCaption: {caption}")
        print(f"Tags: {text_prompt}")
        updated_image_path, pred_phrases = self._segment_object(image_path, text_prompt, func_name="auto-label")
        caption = check_caption(caption, pred_phrases)
        print(f"Revise caption with number: {caption}")
        print(f"Processed SegmentMultiObject, Input Image: {image_path}, Caption: {caption}, "
              f"Text Prompt: {text_prompt}, Output Image: {updated_image_path}")
        return updated_image_path

    def _inpainting(self, image_path, to_be_replaced_txt, replace_with_txt, func_name):
        image_pil, image = load_image(image_path)
        # run grounding dino model
        boxes_filt, scores, pred_phrases = get_grounding_output(
            self.dino_model, image, to_be_replaced_txt, 0.3, 0.25, device=self.device
        )
        # initialize SAM
        predictor = SamPredictor(self.sam_model)
        image = cv2.imread(image_path)
        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
        predictor.set_image(image)
        size = image_pil.size
        H, W = size[1], size[0]
        for i in range(boxes_filt.size(0)):
            boxes_filt[i] = boxes_filt[i] * torch.Tensor([W, H, W, H])
            boxes_filt[i][:2] -= boxes_filt[i][2:] / 2
            boxes_filt[i][2:] += boxes_filt[i][:2]
        boxes_filt = boxes_filt.cpu()
        # generate mask
        transformed_boxes = predictor.transform.apply_boxes_torch(boxes_filt, image.shape[:2])
        masks, _, _ = predictor.predict_torch(
            point_coords = None,
            point_labels = None,
            boxes = transformed_boxes.to(self.device),
            multimask_output = False,
        )
        # inpainting pipeline
        mask = masks[0][0].cpu().numpy() # simply choose the first mask, which will be refine in the future release
        mask_pil = Image.fromarray(mask).resize((512, 512))
        image_pil = Image.fromarray(image).resize((512, 512))
        image = self.sd_pipe(prompt=replace_with_txt, image=image_pil, mask_image=mask_pil).images[0]
        updated_image_path = get_new_image_name(image_path, func_name)
        image.save(updated_image_path)
        return updated_image_path

    @prompts(name="Replace Something From The Photo",
             description="useful when you want to replace an object from the object description or "
                         "location with another object from its description. "
                         "The input to this tool should be a comma separated string of three, "
                         "representing the image_path, the object to be replaced, the object to be replaced with ")
    def inference_replace(self, inputs):
        image_path, to_be_replaced_txt, replace_with_txt = inputs.split(",")
        print(f"\nReplace {to_be_replaced_txt} to {replace_with_txt}")
        updated_image_path = self._inpainting(image_path, to_be_replaced_txt, replace_with_txt, 'replace-something')
        print(f"Processed ImageEditing, Input Image: {image_path}, Output Image: {updated_image_path}")
        return updated_image_path

#############################################New Tool#############################################


class ConversationBot:
    def __init__(self, load_dict):
        # load_dict = {'VisualQuestionAnswering':'cuda:0', 'ImageCaptioning':'cuda:1',...}
        print(f"Initializing VisualChatGPT, load_dict={load_dict}")
        if 'ImageCaptioning' not in load_dict and 'Grounded_dino_sam_inpainting' not in load_dict:
            raise ValueError("You have to load ImageCaptioning or Grounded_dino_sam_inpainting as a basic function for VisualChatGPT")

        self.models = {}
        # Load Basic Foundation Models
        for class_name, device in load_dict.items():
            self.models[class_name] = globals()[class_name](device=device)

        # Load Template Foundation Models
        for class_name, module in globals().items():
            if getattr(module, 'template_model', False):
                template_required_names = {k for k in inspect.signature(module.__init__).parameters.keys() if k!='self'}
                loaded_names = set([type(e).__name__ for e in self.models.values()])
                if template_required_names.issubset(loaded_names):
                    self.models[class_name] = globals()[class_name](
                        **{name: self.models[name] for name in template_required_names})
        self.tools = []
        for instance in self.models.values():
            for e in dir(instance):
                if e.startswith('inference'):
                    func = getattr(instance, e)
                    self.tools.append(Tool(name=func.name, description=func.description, func=func))
        self.llm = OpenAI(temperature=0)
        self.memory = ConversationBufferMemory(memory_key="chat_history", output_key='output')

    def run_text(self, text, state):
        self.agent.memory.buffer = cut_dialogue_history(self.agent.memory.buffer, keep_last_n_words=500)
        res = self.agent({"input": text.strip()})
        res['output'] = res['output'].replace("\\", "/")
        response = re.sub('(image/[-\w]*.png)', lambda m: f'![](/file={m.group(0)})*{m.group(0)}*', res['output'])
        state = state + [(text, response)]
        print(f"\nProcessed run_text, Input text: {text}\nCurrent state: {state}\n"
              f"Current Memory: {self.agent.memory.buffer}")
        return state, state

    def run_image(self, image, state, txt, lang):
        # image_filename = os.path.join('image', f"{str(uuid.uuid4())[:8]}.png")
        # print("======>Auto Resize Image...")
        # img = Image.open(image.name)
        # width, height = img.size
        # ratio = min(512 / width, 512 / height)
        # width_new, height_new = (round(width * ratio), round(height * ratio))
        # width_new = int(np.round(width_new / 64.0)) * 64
        # height_new = int(np.round(height_new / 64.0)) * 64
        # img = img.resize((width_new, height_new))
        # img = img.convert('RGB')
        # img.save(image_filename)
        # img.save(image_filename, "PNG")
        # print(f"Resize image form {width}x{height} to {width_new}x{height_new}")
        ## Directly use original image for better results
        suffix = image.name.split('.')[-1] 
        image_filename = os.path.join('image', f"{str(uuid.uuid4())[:8]}.{suffix}")
        shutil.copy(image.name, image_filename)
        if 'Grounded_dino_sam_inpainting' in self.models:
            description = self.models['Grounded_dino_sam_inpainting'].inference_caption(image_filename)
        else:
            description = self.models['ImageCaptioning'].inference(image_filename)
        if lang == 'Chinese':
            Human_prompt = f'\nHuman: 提供一张名为 {image_filename}的图片。它的描述是: {description}。 这些信息帮助你理解这个图像,但是你应该使用工具来完成下面的任务,而不是直接从我的描述中想象。 如果你明白了, 说 \"收到\". \n'
            AI_prompt = "收到。  "
        else:
            Human_prompt = f'\nHuman: provide a figure named {image_filename}. The description is: {description}. This information helps you to understand this image, but you should use tools to finish following tasks, rather than directly imagine from my description. If you understand, say \"Received\". \n'
            AI_prompt = "Received.  "
        self.agent.memory.buffer = self.agent.memory.buffer + Human_prompt + 'AI: ' + AI_prompt
        state = state + [(f"![](/file={image_filename})*{image_filename}*", AI_prompt)]
        print(f"\nProcessed run_image, Input image: {image_filename}\nCurrent state: {state}\n"
              f"Current Memory: {self.agent.memory.buffer}")
        return state, state, f'{txt} {image_filename} '

    def init_agent(self, openai_api_key, lang):
        self.memory.clear() #clear previous history
        if lang=='English':
            PREFIX, FORMAT_INSTRUCTIONS, SUFFIX = VISUAL_CHATGPT_PREFIX, VISUAL_CHATGPT_FORMAT_INSTRUCTIONS, VISUAL_CHATGPT_SUFFIX
            place = "Enter text and press enter, or upload an image"
            label_clear = "Clear"
        else:
            PREFIX, FORMAT_INSTRUCTIONS, SUFFIX = VISUAL_CHATGPT_PREFIX_CN, VISUAL_CHATGPT_FORMAT_INSTRUCTIONS_CN, VISUAL_CHATGPT_SUFFIX_CN
            place = "输入文字并回车,或者上传图片"
            label_clear = "清除"
        self.llm = OpenAI(temperature=0, openai_api_key=openai_api_key)
        self.agent = initialize_agent(
            self.tools,
            self.llm,
            agent="conversational-react-description",
            verbose=True,
            memory=self.memory,
            return_intermediate_steps=True,
            agent_kwargs={'prefix': PREFIX, 'format_instructions': FORMAT_INSTRUCTIONS, 'suffix': SUFFIX}, )
        return gr.update(visible = True), gr.update(visible = True)


whisper_model = whisper.load_model("base").to('cuda:0')
def speech_recognition(speech_file):
    # whisper
    # load audio and pad/trim it to fit 30 seconds
    audio = whisper.load_audio(speech_file)
    audio = whisper.pad_or_trim(audio)

    # make log-Mel spectrogram and move to the same device as the model
    mel = whisper.log_mel_spectrogram(audio).to(whisper_model.device)

    # detect the spoken language
    _, probs = whisper_model.detect_language(mel)
    speech_language = max(probs, key=probs.get)
    print(f'\nDetect Language: {speech_language}')

    # decode the audio
    options = whisper.DecodingOptions(fp16 = False)
    result = whisper.decode(whisper_model, mel, options)
    print(result.text)

    return result.text


if __name__ == '__main__':
    load_dict = {'Grounded_dino_sam_inpainting': 'cuda:0'}
    # load_dict = {'ImageCaptioning': 'cuda:0'}
    
    bot = ConversationBot(load_dict)

    with gr.Blocks(css="#chatbot {overflow:auto; height:500px;}") as demo:
        gr.Markdown("<h3><center>ChatBot</center></h3>")
        gr.Markdown(
            """This is a demo to the work [Grounded-Segment-Anything](https://github.com/IDEA-Research/Grounded-Segment-Anything).<br>
            """
        )

        with gr.Row():
            lang = gr.Radio(choices=['Chinese', 'English'], value='English', label='Language')
            openai_api_key_textbox = gr.Textbox(
                placeholder="Paste your OpenAI API key here to start ChatBot(sk-...) and press Enter ↵️",
                show_label=False,
                lines=1,
                type="password",
            )

        chatbot = gr.Chatbot(elem_id="chatbot", label="ChatBot")
        state = gr.State([])

        with gr.Row(visible=False) as input_raws:
            with gr.Column(scale=0.7):
                txt = gr.Textbox(show_label=False, placeholder="Enter text and press enter, or upload an image").style(container=False)
            with gr.Column(scale=0.10, min_width=0):
                run = gr.Button("🏃‍♂️Run")
            with gr.Column(scale=0.10, min_width=0):
                clear = gr.Button("🔄Clear️")
            with gr.Column(scale=0.10, min_width=0):
                btn = gr.UploadButton("🖼️Upload", file_types=["image"])
        with gr.Row(visible=False, equal_height=True) as audio_raw:
            with gr.Column(scale=0.85):
                audio = gr.Audio(source="microphone", type="filepath", label="Just say it!")
            with gr.Column(scale=0.15):
                transcribe = gr.Button("Transcribe")

        gr.Examples(
            examples=[
                    "Describe this image",
                    "Detect the dog",
                    "Detect the dog and the cat",
                    "Segment anything",
                    "Segment the dog",
                    "Help me label the image",
                    "Replace the dog with a cat",
                    ],
            inputs=txt
        )

        openai_api_key_textbox.submit(bot.init_agent, [openai_api_key_textbox, lang], [input_raws, audio_raw])
        transcribe.click(speech_recognition, inputs=[audio], outputs=[txt])
        txt.submit(bot.run_text, [txt, state], [chatbot, state])
        txt.submit(lambda: "", None, txt)
        run.click(bot.run_text, [txt, state], [chatbot, state])
        run.click(lambda: "", None, txt)
        btn.upload(bot.run_image, [btn, state, txt, lang], [chatbot, state, txt])
        clear.click(bot.memory.clear)
        clear.click(lambda: [], None, chatbot)
        clear.click(lambda: [], None, state)

    demo.launch(server_name="0.0.0.0", server_port=10010)