File size: 105,555 Bytes
d8f8d4e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
# Copyright 2023 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.


import inspect
import os
from typing import Any, Callable, Dict, List, Optional, Tuple, Union
import matplotlib.pyplot as plt

import numpy as np
import PIL.Image
import torch
import torch.nn.functional as F
import random
import warnings
from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer

from diffusers.utils.import_utils import is_invisible_watermark_available

from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
from diffusers.loaders import (
    FromSingleFileMixin,
    LoraLoaderMixin,
    TextualInversionLoaderMixin,
)
from diffusers.models import AutoencoderKL, ControlNetModel, UNet2DConditionModel
from diffusers.models.attention_processor import (
    AttnProcessor2_0,
    LoRAAttnProcessor2_0,
    LoRAXFormersAttnProcessor,
    XFormersAttnProcessor,
)
from diffusers.models.lora import adjust_lora_scale_text_encoder
from diffusers.schedulers import KarrasDiffusionSchedulers
from diffusers.utils import (
    is_accelerate_available,
    is_accelerate_version,
    logging,
    replace_example_docstring,
)
from diffusers.utils.torch_utils import is_compiled_module, randn_tensor
from diffusers.pipelines.pipeline_utils import DiffusionPipeline
from diffusers.pipelines.stable_diffusion_xl import StableDiffusionXLPipelineOutput


if is_invisible_watermark_available():
    from diffusers.pipelines.stable_diffusion_xl.watermark import (
        StableDiffusionXLWatermarker,
    )

from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel


logger = logging.get_logger(__name__)  # pylint: disable=invalid-name


EXAMPLE_DOC_STRING = """
    Examples:
"""


def gaussian_kernel(kernel_size=3, sigma=1.0, channels=3):
    x_coord = torch.arange(kernel_size)
    gaussian_1d = torch.exp(
        -((x_coord - (kernel_size - 1) / 2) ** 2) / (2 * sigma**2)
    )
    gaussian_1d = gaussian_1d / gaussian_1d.sum()
    gaussian_2d = gaussian_1d[:, None] * gaussian_1d[None, :]
    kernel = gaussian_2d[None, None, :, :].repeat(channels, 1, 1, 1)

    return kernel


def gaussian_filter(latents, kernel_size=3, sigma=1.0):
    channels = latents.shape[1]
    kernel = gaussian_kernel(kernel_size, sigma, channels).to(
        latents.device, latents.dtype
    )
    blurred_latents = F.conv2d(
        latents, kernel, padding=kernel_size // 2, groups=channels
    )

    return blurred_latents


class DemoFusionSDXLControlNetPipeline(
    DiffusionPipeline, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
):
    r"""
    Pipeline for text-to-image generation using Stable Diffusion XL with ControlNet guidance.

    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
    implemented for all pipelines (downloading, saving, running on a particular device, etc.).

    The pipeline also inherits the following loading methods:
        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
        - [`loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
        - [`loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files

    Args:
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
        text_encoder ([`~transformers.CLIPTextModel`]):
            Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)).
        text_encoder_2 ([`~transformers.CLIPTextModelWithProjection`]):
            Second frozen text-encoder
            ([laion/CLIP-ViT-bigG-14-laion2B-39B-b160k](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k)).
        tokenizer ([`~transformers.CLIPTokenizer`]):
            A `CLIPTokenizer` to tokenize text.
        tokenizer_2 ([`~transformers.CLIPTokenizer`]):
            A `CLIPTokenizer` to tokenize text.
        unet ([`UNet2DConditionModel`]):
            A `UNet2DConditionModel` to denoise the encoded image latents.
        controlnet ([`ControlNetModel`] or `List[ControlNetModel]`):
            Provides additional conditioning to the `unet` during the denoising process. If you set multiple
            ControlNets as a list, the outputs from each ControlNet are added together to create one combined
            additional conditioning.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
        force_zeros_for_empty_prompt (`bool`, *optional*, defaults to `"True"`):
            Whether the negative prompt embeddings should always be set to 0. Also see the config of
            `stabilityai/stable-diffusion-xl-base-1-0`.
        add_watermarker (`bool`, *optional*):
            Whether to use the [invisible_watermark](https://github.com/ShieldMnt/invisible-watermark/) library to
            watermark output images. If not defined, it defaults to `True` if the package is installed; otherwise no
            watermarker is used.
    """
    model_cpu_offload_seq = "text_encoder->text_encoder_2->unet->vae"  # leave controlnet out on purpose because it iterates with unet

    def __init__(
        self,
        vae: AutoencoderKL,
        text_encoder: CLIPTextModel,
        text_encoder_2: CLIPTextModelWithProjection,
        tokenizer: CLIPTokenizer,
        tokenizer_2: CLIPTokenizer,
        unet: UNet2DConditionModel,
        controlnet: Union[
            ControlNetModel,
            List[ControlNetModel],
            Tuple[ControlNetModel],
            MultiControlNetModel,
        ],
        scheduler: KarrasDiffusionSchedulers,
        force_zeros_for_empty_prompt: bool = True,
        add_watermarker: Optional[bool] = None,
    ):
        super().__init__()

        if isinstance(controlnet, (list, tuple)):
            controlnet = MultiControlNetModel(controlnet)

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            text_encoder_2=text_encoder_2,
            tokenizer=tokenizer,
            tokenizer_2=tokenizer_2,
            unet=unet,
            controlnet=controlnet,
            scheduler=scheduler,
        )
        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
        self.image_processor = VaeImageProcessor(
            vae_scale_factor=self.vae_scale_factor, do_convert_rgb=True
        )
        self.control_image_processor = VaeImageProcessor(
            vae_scale_factor=self.vae_scale_factor,
            do_convert_rgb=True,
            do_normalize=False,
        )
        add_watermarker = (
            add_watermarker
            if add_watermarker is not None
            else is_invisible_watermark_available()
        )

        if add_watermarker:
            self.watermark = StableDiffusionXLWatermarker()
        else:
            self.watermark = None

        self.register_to_config(
            force_zeros_for_empty_prompt=force_zeros_for_empty_prompt
        )

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_slicing
    def enable_vae_slicing(self):
        r"""
        Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
        compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
        """
        self.vae.enable_slicing()

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_slicing
    def disable_vae_slicing(self):
        r"""
        Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
        computing decoding in one step.
        """
        self.vae.disable_slicing()

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_tiling
    def enable_vae_tiling(self):
        r"""
        Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
        compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
        processing larger images.
        """
        self.vae.enable_tiling()

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_tiling
    def disable_vae_tiling(self):
        r"""
        Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to
        computing decoding in one step.
        """
        self.vae.disable_tiling()

    # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl.StableDiffusionXLPipeline.encode_prompt
    def encode_prompt(
        self,
        prompt: str,
        prompt_2: Optional[str] = None,
        device: Optional[torch.device] = None,
        num_images_per_prompt: int = 1,
        do_classifier_free_guidance: bool = True,
        negative_prompt: Optional[str] = None,
        negative_prompt_2: Optional[str] = None,
        prompt_embeds: Optional[torch.FloatTensor] = None,
        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
        lora_scale: Optional[float] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts to be sent to the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
                used in both text-encoders
            device: (`torch.device`):
                torch device
            num_images_per_prompt (`int`):
                number of images that should be generated per prompt
            do_classifier_free_guidance (`bool`):
                whether to use classifier free guidance or not
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            negative_prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
                `text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
            prompt_embeds (`torch.FloatTensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                argument.
            pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
                If not provided, pooled text embeddings will be generated from `prompt` input argument.
            negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
                input argument.
            lora_scale (`float`, *optional*):
                A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
        """
        device = device or self._execution_device

        # set lora scale so that monkey patched LoRA
        # function of text encoder can correctly access it
        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
            self._lora_scale = lora_scale

            # dynamically adjust the LoRA scale
            adjust_lora_scale_text_encoder(self.text_encoder, lora_scale)
            adjust_lora_scale_text_encoder(self.text_encoder_2, lora_scale)

        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        # Define tokenizers and text encoders
        tokenizers = (
            [self.tokenizer, self.tokenizer_2]
            if self.tokenizer is not None
            else [self.tokenizer_2]
        )
        text_encoders = (
            [self.text_encoder, self.text_encoder_2]
            if self.text_encoder is not None
            else [self.text_encoder_2]
        )

        if prompt_embeds is None:
            prompt_2 = prompt_2 or prompt
            # textual inversion: procecss multi-vector tokens if necessary
            prompt_embeds_list = []
            prompts = [prompt, prompt_2]
            for prompt, tokenizer, text_encoder in zip(
                prompts, tokenizers, text_encoders
            ):
                if isinstance(self, TextualInversionLoaderMixin):
                    prompt = self.maybe_convert_prompt(prompt, tokenizer)

                text_inputs = tokenizer(
                    prompt,
                    padding="max_length",
                    max_length=tokenizer.model_max_length,
                    truncation=True,
                    return_tensors="pt",
                )

                text_input_ids = text_inputs.input_ids
                untruncated_ids = tokenizer(
                    prompt, padding="longest", return_tensors="pt"
                ).input_ids

                if untruncated_ids.shape[-1] >= text_input_ids.shape[
                    -1
                ] and not torch.equal(text_input_ids, untruncated_ids):
                    removed_text = tokenizer.batch_decode(
                        untruncated_ids[:, tokenizer.model_max_length - 1 : -1]
                    )
                    logger.warning(
                        "The following part of your input was truncated because CLIP can only handle sequences up to"
                        f" {tokenizer.model_max_length} tokens: {removed_text}"
                    )

                prompt_embeds = text_encoder(
                    text_input_ids.to(device),
                    output_hidden_states=True,
                )

                # We are only ALWAYS interested in the pooled output of the final text encoder
                pooled_prompt_embeds = prompt_embeds[0]
                prompt_embeds = prompt_embeds.hidden_states[-2]

                prompt_embeds_list.append(prompt_embeds)

            prompt_embeds = torch.concat(prompt_embeds_list, dim=-1)

        # get unconditional embeddings for classifier free guidance
        zero_out_negative_prompt = (
            negative_prompt is None and self.config.force_zeros_for_empty_prompt
        )
        if (
            do_classifier_free_guidance
            and negative_prompt_embeds is None
            and zero_out_negative_prompt
        ):
            negative_prompt_embeds = torch.zeros_like(prompt_embeds)
            negative_pooled_prompt_embeds = torch.zeros_like(pooled_prompt_embeds)
        elif do_classifier_free_guidance and negative_prompt_embeds is None:
            negative_prompt = negative_prompt or ""
            negative_prompt_2 = negative_prompt_2 or negative_prompt

            uncond_tokens: List[str]
            if prompt is not None and type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif isinstance(negative_prompt, str):
                uncond_tokens = [negative_prompt, negative_prompt_2]
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )
            else:
                uncond_tokens = [negative_prompt, negative_prompt_2]

            negative_prompt_embeds_list = []
            for negative_prompt, tokenizer, text_encoder in zip(
                uncond_tokens, tokenizers, text_encoders
            ):
                if isinstance(self, TextualInversionLoaderMixin):
                    negative_prompt = self.maybe_convert_prompt(
                        negative_prompt, tokenizer
                    )

                max_length = prompt_embeds.shape[1]
                uncond_input = tokenizer(
                    negative_prompt,
                    padding="max_length",
                    max_length=max_length,
                    truncation=True,
                    return_tensors="pt",
                )

                negative_prompt_embeds = text_encoder(
                    uncond_input.input_ids.to(device),
                    output_hidden_states=True,
                )
                # We are only ALWAYS interested in the pooled output of the final text encoder
                negative_pooled_prompt_embeds = negative_prompt_embeds[0]
                negative_prompt_embeds = negative_prompt_embeds.hidden_states[-2]

                negative_prompt_embeds_list.append(negative_prompt_embeds)

            negative_prompt_embeds = torch.concat(negative_prompt_embeds_list, dim=-1)

        prompt_embeds = prompt_embeds.to(dtype=self.text_encoder_2.dtype, device=device)
        bs_embed, seq_len, _ = prompt_embeds.shape
        # duplicate text embeddings for each generation per prompt, using mps friendly method
        prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
        prompt_embeds = prompt_embeds.view(
            bs_embed * num_images_per_prompt, seq_len, -1
        )

        if do_classifier_free_guidance:
            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
            seq_len = negative_prompt_embeds.shape[1]
            negative_prompt_embeds = negative_prompt_embeds.to(
                dtype=self.text_encoder_2.dtype, device=device
            )
            negative_prompt_embeds = negative_prompt_embeds.repeat(
                1, num_images_per_prompt, 1
            )
            negative_prompt_embeds = negative_prompt_embeds.view(
                batch_size * num_images_per_prompt, seq_len, -1
            )

        pooled_prompt_embeds = pooled_prompt_embeds.repeat(
            1, num_images_per_prompt
        ).view(bs_embed * num_images_per_prompt, -1)
        if do_classifier_free_guidance:
            negative_pooled_prompt_embeds = negative_pooled_prompt_embeds.repeat(
                1, num_images_per_prompt
            ).view(bs_embed * num_images_per_prompt, -1)

        return (
            prompt_embeds,
            negative_prompt_embeds,
            pooled_prompt_embeds,
            negative_pooled_prompt_embeds,
        )

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
    def prepare_extra_step_kwargs(self, generator, eta):
        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
        # and should be between [0, 1]

        accepts_eta = "eta" in set(
            inspect.signature(self.scheduler.step).parameters.keys()
        )
        extra_step_kwargs = {}
        if accepts_eta:
            extra_step_kwargs["eta"] = eta

        # check if the scheduler accepts generator
        accepts_generator = "generator" in set(
            inspect.signature(self.scheduler.step).parameters.keys()
        )
        if accepts_generator:
            extra_step_kwargs["generator"] = generator
        return extra_step_kwargs

    def check_inputs(
        self,
        prompt,
        prompt_2,
        image,
        callback_steps,
        negative_prompt=None,
        negative_prompt_2=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        pooled_prompt_embeds=None,
        negative_pooled_prompt_embeds=None,
        controlnet_conditioning_scale=1.0,
        control_guidance_start=0.0,
        control_guidance_end=1.0,
    ):
        if (callback_steps is None) or (
            callback_steps is not None
            and (not isinstance(callback_steps, int) or callback_steps <= 0)
        ):
            raise ValueError(
                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
                f" {type(callback_steps)}."
            )

        if prompt is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt_2 is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt_2`: {prompt_2} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt is None and prompt_embeds is None:
            raise ValueError(
                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
            )
        elif prompt is not None and (
            not isinstance(prompt, str) and not isinstance(prompt, list)
        ):
            raise ValueError(
                f"`prompt` has to be of type `str` or `list` but is {type(prompt)}"
            )
        elif prompt_2 is not None and (
            not isinstance(prompt_2, str) and not isinstance(prompt_2, list)
        ):
            raise ValueError(
                f"`prompt_2` has to be of type `str` or `list` but is {type(prompt_2)}"
            )

        if negative_prompt is not None and negative_prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
            )
        elif negative_prompt_2 is not None and negative_prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `negative_prompt_2`: {negative_prompt_2} and `negative_prompt_embeds`:"
                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
            )

        if prompt_embeds is not None and negative_prompt_embeds is not None:
            if prompt_embeds.shape != negative_prompt_embeds.shape:
                raise ValueError(
                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
                    f" {negative_prompt_embeds.shape}."
                )

        if prompt_embeds is not None and pooled_prompt_embeds is None:
            raise ValueError(
                "If `prompt_embeds` are provided, `pooled_prompt_embeds` also have to be passed. Make sure to generate `pooled_prompt_embeds` from the same text encoder that was used to generate `prompt_embeds`."
            )

        if negative_prompt_embeds is not None and negative_pooled_prompt_embeds is None:
            raise ValueError(
                "If `negative_prompt_embeds` are provided, `negative_pooled_prompt_embeds` also have to be passed. Make sure to generate `negative_pooled_prompt_embeds` from the same text encoder that was used to generate `negative_prompt_embeds`."
            )

        # `prompt` needs more sophisticated handling when there are multiple
        # conditionings.
        if isinstance(self.controlnet, MultiControlNetModel):
            if isinstance(prompt, list):
                logger.warning(
                    f"You have {len(self.controlnet.nets)} ControlNets and you have passed {len(prompt)}"
                    " prompts. The conditionings will be fixed across the prompts."
                )

        # Check `image`
        is_compiled = hasattr(F, "scaled_dot_product_attention") and isinstance(
            self.controlnet, torch._dynamo.eval_frame.OptimizedModule
        )
        if (
            isinstance(self.controlnet, ControlNetModel)
            or is_compiled
            and isinstance(self.controlnet._orig_mod, ControlNetModel)
        ):
            self.check_image(image, prompt, prompt_embeds)
        elif (
            isinstance(self.controlnet, MultiControlNetModel)
            or is_compiled
            and isinstance(self.controlnet._orig_mod, MultiControlNetModel)
        ):
            if not isinstance(image, list):
                raise TypeError("For multiple controlnets: `image` must be type `list`")

            # When `image` is a nested list:
            # (e.g. [[canny_image_1, pose_image_1], [canny_image_2, pose_image_2]])
            elif any(isinstance(i, list) for i in image):
                raise ValueError(
                    "A single batch of multiple conditionings are supported at the moment."
                )
            elif len(image) != len(self.controlnet.nets):
                raise ValueError(
                    f"For multiple controlnets: `image` must have the same length as the number of controlnets, but got {len(image)} images and {len(self.controlnet.nets)} ControlNets."
                )

            for image_ in image:
                self.check_image(image_, prompt, prompt_embeds)
        else:
            assert False

        # Check `controlnet_conditioning_scale`
        if (
            isinstance(self.controlnet, ControlNetModel)
            or is_compiled
            and isinstance(self.controlnet._orig_mod, ControlNetModel)
        ):
            if not isinstance(controlnet_conditioning_scale, float):
                raise TypeError(
                    "For single controlnet: `controlnet_conditioning_scale` must be type `float`."
                )
        elif (
            isinstance(self.controlnet, MultiControlNetModel)
            or is_compiled
            and isinstance(self.controlnet._orig_mod, MultiControlNetModel)
        ):
            if isinstance(controlnet_conditioning_scale, list):
                if any(isinstance(i, list) for i in controlnet_conditioning_scale):
                    raise ValueError(
                        "A single batch of multiple conditionings are supported at the moment."
                    )
            elif isinstance(controlnet_conditioning_scale, list) and len(
                controlnet_conditioning_scale
            ) != len(self.controlnet.nets):
                raise ValueError(
                    "For multiple controlnets: When `controlnet_conditioning_scale` is specified as `list`, it must have"
                    " the same length as the number of controlnets"
                )
        else:
            assert False

        if not isinstance(control_guidance_start, (tuple, list)):
            control_guidance_start = [control_guidance_start]

        if not isinstance(control_guidance_end, (tuple, list)):
            control_guidance_end = [control_guidance_end]

        if len(control_guidance_start) != len(control_guidance_end):
            raise ValueError(
                f"`control_guidance_start` has {len(control_guidance_start)} elements, but `control_guidance_end` has {len(control_guidance_end)} elements. Make sure to provide the same number of elements to each list."
            )

        if isinstance(self.controlnet, MultiControlNetModel):
            if len(control_guidance_start) != len(self.controlnet.nets):
                raise ValueError(
                    f"`control_guidance_start`: {control_guidance_start} has {len(control_guidance_start)} elements but there are {len(self.controlnet.nets)} controlnets available. Make sure to provide {len(self.controlnet.nets)}."
                )

        for start, end in zip(control_guidance_start, control_guidance_end):
            if start >= end:
                raise ValueError(
                    f"control guidance start: {start} cannot be larger or equal to control guidance end: {end}."
                )
            if start < 0.0:
                raise ValueError(
                    f"control guidance start: {start} can't be smaller than 0."
                )
            if end > 1.0:
                raise ValueError(
                    f"control guidance end: {end} can't be larger than 1.0."
                )

    # Copied from diffusers.pipelines.controlnet.pipeline_controlnet.StableDiffusionControlNetPipeline.check_image
    def check_image(self, image, prompt, prompt_embeds):
        image_is_pil = isinstance(image, PIL.Image.Image)
        image_is_tensor = isinstance(image, torch.Tensor)
        image_is_np = isinstance(image, np.ndarray)
        image_is_pil_list = isinstance(image, list) and isinstance(
            image[0], PIL.Image.Image
        )
        image_is_tensor_list = isinstance(image, list) and isinstance(
            image[0], torch.Tensor
        )
        image_is_np_list = isinstance(image, list) and isinstance(image[0], np.ndarray)

        if (
            not image_is_pil
            and not image_is_tensor
            and not image_is_np
            and not image_is_pil_list
            and not image_is_tensor_list
            and not image_is_np_list
        ):
            raise TypeError(
                f"image must be passed and be one of PIL image, numpy array, torch tensor, list of PIL images, list of numpy arrays or list of torch tensors, but is {type(image)}"
            )

        if image_is_pil:
            image_batch_size = 1
        else:
            image_batch_size = len(image)

        if prompt is not None and isinstance(prompt, str):
            prompt_batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            prompt_batch_size = len(prompt)
        elif prompt_embeds is not None:
            prompt_batch_size = prompt_embeds.shape[0]

        if image_batch_size != 1 and image_batch_size != prompt_batch_size:
            raise ValueError(
                f"If image batch size is not 1, image batch size must be same as prompt batch size. image batch size: {image_batch_size}, prompt batch size: {prompt_batch_size}"
            )

    # Copied from diffusers.pipelines.controlnet.pipeline_controlnet.StableDiffusionControlNetPipeline.prepare_image
    def prepare_image(
        self,
        image,
        width,
        height,
        batch_size,
        num_images_per_prompt,
        device,
        dtype,
        do_classifier_free_guidance=False,
        guess_mode=False,
    ):
        image = self.control_image_processor.preprocess(
            image, height=height, width=width
        ).to(dtype=torch.float32)
        image_batch_size = image.shape[0]

        if image_batch_size == 1:
            repeat_by = batch_size
        else:
            # image batch size is the same as prompt batch size
            repeat_by = num_images_per_prompt

        image = image.repeat_interleave(repeat_by, dim=0)

        image = image.to(device=device, dtype=dtype)

        if do_classifier_free_guidance and not guess_mode:
            image = torch.cat([image] * 2)

        return image

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
    def prepare_latents(
        self,
        batch_size,
        num_channels_latents,
        height,
        width,
        dtype,
        device,
        generator,
        latents=None,
    ):
        shape = (
            batch_size,
            num_channels_latents,
            height // self.vae_scale_factor,
            width // self.vae_scale_factor,
        )
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        if latents is None:
            latents = randn_tensor(
                shape, generator=generator, device=device, dtype=dtype
            )
        else:
            latents = latents.to(device)

        # scale the initial noise by the standard deviation required by the scheduler
        latents = latents * self.scheduler.init_noise_sigma
        return latents

    # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl.StableDiffusionXLPipeline._get_add_time_ids
    def _get_add_time_ids(
        self, original_size, crops_coords_top_left, target_size, dtype
    ):
        add_time_ids = list(original_size + crops_coords_top_left + target_size)

        passed_add_embed_dim = (
            self.unet.config.addition_time_embed_dim * len(add_time_ids)
            + self.text_encoder_2.config.projection_dim
        )
        expected_add_embed_dim = self.unet.add_embedding.linear_1.in_features

        if expected_add_embed_dim != passed_add_embed_dim:
            raise ValueError(
                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`."
            )

        add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
        return add_time_ids

    def get_views(self, height, width, window_size=128, stride=64, random_jitter=False):
        # Here, we define the mappings F_i (see Eq. 7 in the MultiDiffusion paper https://arxiv.org/abs/2302.08113)
        # if panorama's height/width < window_size, num_blocks of height/width should return 1
        height //= self.vae_scale_factor
        width //= self.vae_scale_factor
        num_blocks_height = (
            int((height - window_size) / stride - 1e-6) + 2
            if height > window_size
            else 1
        )
        num_blocks_width = (
            int((width - window_size) / stride - 1e-6) + 2 if width > window_size else 1
        )
        total_num_blocks = int(num_blocks_height * num_blocks_width)
        views = []
        for i in range(total_num_blocks):
            h_start = int((i // num_blocks_width) * stride)
            h_end = h_start + window_size
            w_start = int((i % num_blocks_width) * stride)
            w_end = w_start + window_size

            if h_end > height:
                h_start = int(h_start + height - h_end)
                h_end = int(height)
            if w_end > width:
                w_start = int(w_start + width - w_end)
                w_end = int(width)
            if h_start < 0:
                h_end = int(h_end - h_start)
                h_start = 0
            if w_start < 0:
                w_end = int(w_end - w_start)
                w_start = 0

            if random_jitter:
                jitter_range = (window_size - stride) // 4
                w_jitter = 0
                h_jitter = 0
                if (w_start != 0) and (w_end != width):
                    w_jitter = random.randint(-jitter_range, jitter_range)
                elif (w_start == 0) and (w_end != width):
                    w_jitter = random.randint(-jitter_range, 0)
                elif (w_start != 0) and (w_end == width):
                    w_jitter = random.randint(0, jitter_range)
                if (h_start != 0) and (h_end != height):
                    h_jitter = random.randint(-jitter_range, jitter_range)
                elif (h_start == 0) and (h_end != height):
                    h_jitter = random.randint(-jitter_range, 0)
                elif (h_start != 0) and (h_end == height):
                    h_jitter = random.randint(0, jitter_range)
                h_start += h_jitter + jitter_range
                h_end += h_jitter + jitter_range
                w_start += w_jitter + jitter_range
                w_end += w_jitter + jitter_range

            views.append((h_start, h_end, w_start, w_end))
        return views

    def tiled_decode(self, latents, current_height, current_width):
        sample_size = self.unet.config.sample_size
        core_size = self.unet.config.sample_size // 4
        core_stride = core_size
        pad_size = self.unet.config.sample_size // 8 * 3
        decoder_view_batch_size = 1

        if self.lowvram:
            core_stride = core_size // 2
            pad_size = core_size

        views = self.get_views(
            current_height, current_width, stride=core_stride, window_size=core_size
        )
        views_batch = [
            views[i : i + decoder_view_batch_size]
            for i in range(0, len(views), decoder_view_batch_size)
        ]
        latents_ = F.pad(
            latents, (pad_size, pad_size, pad_size, pad_size), "constant", 0
        )
        image = torch.zeros(latents.size(0), 3, current_height, current_width).to(
            latents.device
        )
        count = torch.zeros_like(image).to(latents.device)
        # get the latents corresponding to the current view coordinates
        with self.progress_bar(total=len(views_batch)) as progress_bar:
            for j, batch_view in enumerate(views_batch):
                vb_size = len(batch_view)
                latents_for_view = torch.cat(
                    [
                        latents_[
                            :,
                            :,
                            h_start : h_end + pad_size * 2,
                            w_start : w_end + pad_size * 2,
                        ]
                        for h_start, h_end, w_start, w_end in batch_view
                    ]
                ).to(self.vae.device)
                image_patch = self.vae.decode(
                    latents_for_view / self.vae.config.scaling_factor, return_dict=False
                )[0]
                h_start, h_end, w_start, w_end = views[j]
                h_start, h_end, w_start, w_end = (
                    h_start * self.vae_scale_factor,
                    h_end * self.vae_scale_factor,
                    w_start * self.vae_scale_factor,
                    w_end * self.vae_scale_factor,
                )
                p_h_start, p_h_end, p_w_start, p_w_end = (
                    pad_size * self.vae_scale_factor,
                    image_patch.size(2) - pad_size * self.vae_scale_factor,
                    pad_size * self.vae_scale_factor,
                    image_patch.size(3) - pad_size * self.vae_scale_factor,
                )
                image[:, :, h_start:h_end, w_start:w_end] += image_patch[
                    :, :, p_h_start:p_h_end, p_w_start:p_w_end
                ].to(latents.device)
                count[:, :, h_start:h_end, w_start:w_end] += 1
                progress_bar.update()
        image = image / count

        return image

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
    def upcast_vae(self):
        dtype = self.vae.dtype
        self.vae.to(dtype=torch.float32)
        use_torch_2_0_or_xformers = isinstance(
            self.vae.decoder.mid_block.attentions[0].processor,
            (
                AttnProcessor2_0,
                XFormersAttnProcessor,
                LoRAXFormersAttnProcessor,
                LoRAAttnProcessor2_0,
            ),
        )
        # if xformers or torch_2_0 is used attention block does not need
        # to be in float32 which can save lots of memory
        if use_torch_2_0_or_xformers:
            self.vae.post_quant_conv.to(dtype)
            self.vae.decoder.conv_in.to(dtype)
            self.vae.decoder.mid_block.to(dtype)

    @torch.no_grad()
    @replace_example_docstring(EXAMPLE_DOC_STRING)
    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        prompt_2: Optional[Union[str, List[str]]] = None,
        condition_image: PipelineImageInput = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_inference_steps: int = 50,
        guidance_scale: float = 5.0,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        negative_prompt_2: Optional[Union[str, List[str]]] = None,
        num_images_per_prompt: Optional[int] = 1,
        eta: float = 0.0,
        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
        latents: Optional[torch.FloatTensor] = None,
        prompt_embeds: Optional[torch.FloatTensor] = None,
        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = True,
        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
        callback_steps: int = 1,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        controlnet_conditioning_scale: Union[float, List[float]] = 1.0,
        guess_mode: bool = False,
        control_guidance_start: Union[float, List[float]] = 0.0,
        control_guidance_end: Union[float, List[float]] = 1.0,
        original_size: Tuple[int, int] = None,
        crops_coords_top_left: Tuple[int, int] = (0, 0),
        target_size: Tuple[int, int] = None,
        negative_original_size: Optional[Tuple[int, int]] = None,
        negative_crops_coords_top_left: Tuple[int, int] = (0, 0),
        negative_target_size: Optional[Tuple[int, int]] = None,
        ################### DemoFusion specific parameters ####################
        image_lr: Optional[torch.FloatTensor] = None,
        view_batch_size: int = 16,
        multi_decoder: bool = True,
        stride: Optional[int] = 64,
        cosine_scale_1: Optional[float] = 3.0,
        cosine_scale_2: Optional[float] = 1.0,
        cosine_scale_3: Optional[float] = 1.0,
        sigma: Optional[float] = 1.0,
        show_image: bool = False,
        lowvram: bool = False,
    ):
        r"""
        The call function to the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
            prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts to be sent to `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
                used in both text-encoders.
            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
                    `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
                The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
                specified as `torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be
                accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
                and/or width are passed, `image` is resized accordingly. If multiple ControlNets are specified in
                `init`, images must be passed as a list such that each element of the list can be correctly batched for
                input to a single ControlNet.
            height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The height in pixels of the generated image. Anything below 512 pixels won't work well for
                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
                and checkpoints that are not specifically fine-tuned on low resolutions.
            width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                The width in pixels of the generated image. Anything below 512 pixels won't work well for
                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
                and checkpoints that are not specifically fine-tuned on low resolutions.
            num_inference_steps (`int`, *optional*, defaults to 50):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            guidance_scale (`float`, *optional*, defaults to 5.0):
                A higher guidance scale value encourages the model to generate images closely linked to the text
                `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide what to not include in image generation. If not defined, you need to
                pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
            negative_prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide what to not include in image generation. This is sent to `tokenizer_2`
                and `text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders.
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                generation deterministic.
            latents (`torch.FloatTensor`, *optional*):
                Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor is generated by sampling using the supplied random `generator`.
            prompt_embeds (`torch.FloatTensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
                provided, text embeddings are generated from the `prompt` input argument.
            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
            pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                not provided, pooled text embeddings are generated from `prompt` input argument.
            negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs (prompt
                weighting). If not provided, pooled `negative_prompt_embeds` are generated from `negative_prompt` input
                argument.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generated image. Choose between `PIL.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `True`):
                Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
                plain tuple.
            callback (`Callable`, *optional*):
                A function that calls every `callback_steps` steps during inference. The function is called with the
                following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
            callback_steps (`int`, *optional*, defaults to 1):
                The frequency at which the `callback` function is called. If not specified, the callback is called at
                every step.
            cross_attention_kwargs (`dict`, *optional*):
                A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
                [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
            controlnet_conditioning_scale (`float` or `List[float]`, *optional*, defaults to 1.0):
                The outputs of the ControlNet are multiplied by `controlnet_conditioning_scale` before they are added
                to the residual in the original `unet`. If multiple ControlNets are specified in `init`, you can set
                the corresponding scale as a list.
            guess_mode (`bool`, *optional*, defaults to `False`):
                The ControlNet encoder tries to recognize the content of the input image even if you remove all
                prompts. A `guidance_scale` value between 3.0 and 5.0 is recommended.
            control_guidance_start (`float` or `List[float]`, *optional*, defaults to 0.0):
                The percentage of total steps at which the ControlNet starts applying.
            control_guidance_end (`float` or `List[float]`, *optional*, defaults to 1.0):
                The percentage of total steps at which the ControlNet stops applying.
            original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
                `original_size` defaults to `(width, height)` if not specified. Part of SDXL's micro-conditioning as
                explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
            crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
                `crops_coords_top_left` can be used to generate an image that appears to be "cropped" from the position
                `crops_coords_top_left` downwards. Favorable, well-centered images are usually achieved by setting
                `crops_coords_top_left` to (0, 0). Part of SDXL's micro-conditioning as explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
            target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                For most cases, `target_size` should be set to the desired height and width of the generated image. If
                not specified it will default to `(width, height)`. Part of SDXL's micro-conditioning as explained in
                section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
            negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                To negatively condition the generation process based on a specific image resolution. Part of SDXL's
                micro-conditioning as explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
            negative_crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
                To negatively condition the generation process based on a specific crop coordinates. Part of SDXL's
                micro-conditioning as explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
            negative_target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
                To negatively condition the generation process based on a target image resolution. It should be as same
                as the `target_size` for most cases. Part of SDXL's micro-conditioning as explained in section 2.2 of
                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
            ################### DemoFusion specific parameters ####################
            image_lr (`torch.FloatTensor`, *optional*, , defaults to None):
                Low-resolution image input for upscaling. If provided, DemoFusion will encode it as the initial latent representation.
            view_batch_size (`int`, defaults to 16):
                The batch size for multiple denoising paths. Typically, a larger batch size can result in higher
                efficiency but comes with increased GPU memory requirements.
            multi_decoder (`bool`, defaults to True):
                Determine whether to use a tiled decoder. Generally, when the resolution exceeds 3072x3072,
                a tiled decoder becomes necessary.
            stride (`int`, defaults to 64):
                The stride of moving local patches. A smaller stride is better for alleviating seam issues,
                but it also introduces additional computational overhead and inference time.
            cosine_scale_1 (`float`, defaults to 3):
                Control the strength of skip-residual. For specific impacts, please refer to Appendix C
                in the DemoFusion paper.
            cosine_scale_2 (`float`, defaults to 1):
                Control the strength of dilated sampling. For specific impacts, please refer to Appendix C
                in the DemoFusion paper.
            cosine_scale_3 (`float`, defaults to 1):
                Control the strength of the gaussion filter. For specific impacts, please refer to Appendix C
                in the DemoFusion paper.
            sigma (`float`, defaults to 1):
                The standard value of the gaussian filter.
            show_image (`bool`, defaults to False):
                Determine whether to show intermediate results during generation.
            lowvram (`bool`, defaults to False):
                Try to fit in 8 Gb of VRAM, with xformers installed.
        Examples:

        Returns:
            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] is returned,
                otherwise a `tuple` is returned containing the output images.
        """
        controlnet = (
            self.controlnet._orig_mod
            if is_compiled_module(self.controlnet)
            else self.controlnet
        )

        # align format for control guidance
        if not isinstance(control_guidance_start, list) and isinstance(
            control_guidance_end, list
        ):
            control_guidance_start = len(control_guidance_end) * [
                control_guidance_start
            ]
        elif not isinstance(control_guidance_end, list) and isinstance(
            control_guidance_start, list
        ):
            control_guidance_end = len(control_guidance_start) * [control_guidance_end]
        elif not isinstance(control_guidance_start, list) and not isinstance(
            control_guidance_end, list
        ):
            mult = (
                len(controlnet.nets)
                if isinstance(controlnet, MultiControlNetModel)
                else 1
            )
            control_guidance_start, control_guidance_end = mult * [
                control_guidance_start
            ], mult * [control_guidance_end]

        # 0. Default height and width to unet
        height = height or self.unet.config.sample_size * self.vae_scale_factor
        width = width or self.unet.config.sample_size * self.vae_scale_factor

        x1_size = self.unet.config.sample_size * self.vae_scale_factor

        height_scale = height / x1_size
        width_scale = width / x1_size
        scale_num = int(max(height_scale, width_scale))
        aspect_ratio = min(height_scale, width_scale) / max(height_scale, width_scale)

        original_size = original_size or (height, width)
        target_size = target_size or (height, width)

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt,
            prompt_2,
            condition_image,
            callback_steps,
            negative_prompt,
            negative_prompt_2,
            prompt_embeds,
            negative_prompt_embeds,
            pooled_prompt_embeds,
            negative_pooled_prompt_embeds,
            controlnet_conditioning_scale,
            control_guidance_start,
            control_guidance_end,
        )

        # 2. Define call parameters
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        device = self._execution_device
        self.lowvram = lowvram
        if self.lowvram:
            self.vae.cpu()
            self.unet.cpu()
            self.text_encoder.to(device)
            self.text_encoder_2.to(device)
            image_lr.cpu()
        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
        # corresponds to doing no classifier free guidance.
        do_classifier_free_guidance = guidance_scale > 1.0

        if isinstance(controlnet, MultiControlNetModel) and isinstance(
            controlnet_conditioning_scale, float
        ):
            controlnet_conditioning_scale = [controlnet_conditioning_scale] * len(
                controlnet.nets
            )

        global_pool_conditions = (
            controlnet.config.global_pool_conditions
            if isinstance(controlnet, ControlNetModel)
            else controlnet.nets[0].config.global_pool_conditions
        )
        guess_mode = guess_mode or global_pool_conditions

        # 3. Encode input prompt
        text_encoder_lora_scale = (
            cross_attention_kwargs.get("scale", None)
            if cross_attention_kwargs is not None
            else None
        )
        (
            prompt_embeds,
            negative_prompt_embeds,
            pooled_prompt_embeds,
            negative_pooled_prompt_embeds,
        ) = self.encode_prompt(
            prompt,
            prompt_2,
            device,
            num_images_per_prompt,
            do_classifier_free_guidance,
            negative_prompt,
            negative_prompt_2,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            pooled_prompt_embeds=pooled_prompt_embeds,
            negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
            lora_scale=text_encoder_lora_scale,
        )

        # 4. Prepare image
        if isinstance(controlnet, ControlNetModel):
            condition_image = self.prepare_image(
                image=condition_image,
                width=width // scale_num,
                height=height // scale_num,
                batch_size=batch_size * num_images_per_prompt,
                num_images_per_prompt=num_images_per_prompt,
                device=device,
                dtype=controlnet.dtype,
                do_classifier_free_guidance=do_classifier_free_guidance,
                guess_mode=guess_mode,
            )
            # height, width = condition_image.shape[-2:]
            # condition_image.shape ([2, 3, 1024, 1024])
        elif isinstance(controlnet, MultiControlNetModel):
            condition_images = []

            for image_ in condition_image:
                image_ = self.prepare_image(
                    image=image_,
                    width=width // scale_num,
                    height=height // scale_num,
                    batch_size=batch_size * num_images_per_prompt,
                    num_images_per_prompt=num_images_per_prompt,
                    device=device,
                    dtype=controlnet.dtype,
                    do_classifier_free_guidance=do_classifier_free_guidance,
                    guess_mode=guess_mode,
                )

                condition_images.append(image_)

            condition_image = condition_images
            # height, width = condition_image[0].shape[-2:]
        else:
            assert False

        # 5. Prepare timesteps
        self.scheduler.set_timesteps(num_inference_steps, device=device)
        timesteps = self.scheduler.timesteps

        # 6. Prepare latent variables
        num_channels_latents = self.unet.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_images_per_prompt,
            num_channels_latents,
            height // scale_num,
            width // scale_num,
            prompt_embeds.dtype,
            device,
            generator,
            latents,
        )

        # 7. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

        # 7.1 Create tensor stating which controlnets to keep
        controlnet_keep = []
        for i in range(len(timesteps)):
            keeps = [
                1.0 - float(i / len(timesteps) < s or (i + 1) / len(timesteps) > e)
                for s, e in zip(control_guidance_start, control_guidance_end)
            ]
            controlnet_keep.append(
                keeps[0] if isinstance(controlnet, ControlNetModel) else keeps
            )

        # 7.2 Prepare added time ids & embeddings
        if isinstance(condition_image, list):
            original_size = original_size or condition_image[0].shape[-2:]
        else:
            original_size = original_size or condition_image.shape[-2:]
        target_size = target_size or (height, width)

        add_text_embeds = pooled_prompt_embeds
        add_time_ids = self._get_add_time_ids(
            original_size, crops_coords_top_left, target_size, dtype=prompt_embeds.dtype
        )

        if negative_original_size is not None and negative_target_size is not None:
            negative_add_time_ids = self._get_add_time_ids(
                negative_original_size,
                negative_crops_coords_top_left,
                negative_target_size,
                dtype=prompt_embeds.dtype,
            )
        else:
            negative_add_time_ids = add_time_ids

        if do_classifier_free_guidance:
            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
            add_text_embeds = torch.cat(
                [negative_pooled_prompt_embeds, add_text_embeds], dim=0
            )
            add_time_ids = torch.cat([negative_add_time_ids, add_time_ids], dim=0)

        prompt_embeds = prompt_embeds.to(device)
        add_text_embeds = add_text_embeds.to(device)
        add_time_ids = add_time_ids.to(device).repeat(
            batch_size * num_images_per_prompt, 1
        )

        # 8. Denoising loop
        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order

        output_images = []

        ###################################################### Phase Initialization ########################################################

        if self.lowvram:
            self.text_encoder.cpu()
            self.text_encoder_2.cpu()

        if image_lr == None:
            print("### Phase 1 Denoising ###")
            with self.progress_bar(total=num_inference_steps) as progress_bar:
                for i, t in enumerate(timesteps):
                    if self.lowvram:
                        self.vae.cpu()
                        self.unet.to(device)

                    latents_for_view = latents

                    # expand the latents if we are doing classifier free guidance
                    latent_model_input = (
                        latents.repeat_interleave(2, dim=0)
                        if do_classifier_free_guidance
                        else latents
                    )
                    latent_model_input = self.scheduler.scale_model_input(
                        latent_model_input, t
                    )

                    added_cond_kwargs = {
                        "text_embeds": add_text_embeds,
                        "time_ids": add_time_ids,
                    }

                    # controlnet(s) inference
                    if guess_mode and do_classifier_free_guidance:
                        # Infer ControlNet only for the conditional batch.
                        control_model_input = latents
                        control_model_input = self.scheduler.scale_model_input(
                            control_model_input, t
                        )
                        controlnet_prompt_embeds = prompt_embeds.chunk(2)[1]
                        controlnet_added_cond_kwargs = {
                            "text_embeds": add_text_embeds.chunk(2)[1],
                            "time_ids": add_time_ids.chunk(2)[1],
                        }
                    else:
                        control_model_input = latent_model_input
                        controlnet_prompt_embeds = prompt_embeds
                        controlnet_added_cond_kwargs = added_cond_kwargs

                    if isinstance(controlnet_keep[i], list):
                        cond_scale = [
                            c * s
                            for c, s in zip(
                                controlnet_conditioning_scale, controlnet_keep[i]
                            )
                        ]
                    else:
                        controlnet_cond_scale = controlnet_conditioning_scale
                        if isinstance(controlnet_cond_scale, list):
                            controlnet_cond_scale = controlnet_cond_scale[0]
                        cond_scale = controlnet_cond_scale * controlnet_keep[i]

                    # print(condition_image.shape, control_model_input.shape, controlnet_prompt_embeds.shape, t, cond_scale, guess_mode)
                    # print(controlnet_added_cond_kwargs["text_embeds"].shape, controlnet_added_cond_kwargs["time_ids"].shape)
                    down_block_res_samples, mid_block_res_sample = self.controlnet(
                        control_model_input,
                        t,
                        encoder_hidden_states=controlnet_prompt_embeds,
                        controlnet_cond=condition_image,
                        conditioning_scale=cond_scale,
                        guess_mode=guess_mode,
                        added_cond_kwargs=controlnet_added_cond_kwargs,
                        return_dict=False,
                    )

                    if guess_mode and do_classifier_free_guidance:
                        # Infered ControlNet only for the conditional batch.
                        # To apply the output of ControlNet to both the unconditional and conditional batches,
                        # add 0 to the unconditional batch to keep it unchanged.
                        down_block_res_samples = [
                            torch.cat([torch.zeros_like(d), d])
                            for d in down_block_res_samples
                        ]
                        mid_block_res_sample = torch.cat(
                            [
                                torch.zeros_like(mid_block_res_sample),
                                mid_block_res_sample,
                            ]
                        )

                    # predict the noise residual
                    noise_pred = self.unet(
                        latent_model_input,
                        t,
                        encoder_hidden_states=prompt_embeds,
                        cross_attention_kwargs=cross_attention_kwargs,
                        down_block_additional_residuals=down_block_res_samples,
                        mid_block_additional_residual=mid_block_res_sample,
                        added_cond_kwargs=added_cond_kwargs,
                        return_dict=False,
                    )[0]

                    # perform guidance
                    if do_classifier_free_guidance:
                        noise_pred_uncond, noise_pred_text = (
                            noise_pred[::2],
                            noise_pred[1::2],
                        )
                        noise_pred = noise_pred_uncond + guidance_scale * (
                            noise_pred_text - noise_pred_uncond
                        )

                    # compute the previous noisy sample x_t -> x_t-1
                    latents = self.scheduler.step(
                        noise_pred, t, latents, **extra_step_kwargs, return_dict=False
                    )[0]

                    # call the callback, if provided
                    if i == len(timesteps) - 1 or (
                        (i + 1) > num_warmup_steps
                        and (i + 1) % self.scheduler.order == 0
                    ):
                        progress_bar.update()
                        if callback is not None and i % callback_steps == 0:
                            step_idx = i // getattr(self.scheduler, "order", 1)
                            callback(step_idx, t, latents)
        else:
            print("### Encoding Real Image ###")
            latents = self.vae.encode(image_lr)
            latents = latents.latent_dist.sample() * self.vae.config.scaling_factor

        anchor_mean = latents.mean()
        anchor_std = latents.std()
        if self.lowvram:
            latents = latents.cpu()
            torch.cuda.empty_cache()
        if not output_type == "latent":
            # make sure the VAE is in float32 mode, as it overflows in float16
            needs_upcasting = (
                self.vae.dtype == torch.float16 and self.vae.config.force_upcast
            )

            if self.lowvram:
                needs_upcasting = (
                    False  # use madebyollin/sdxl-vae-fp16-fix in lowvram mode!
                )
                self.unet.cpu()
                self.vae.to(device)

            if needs_upcasting:
                self.upcast_vae()
                latents = latents.to(
                    next(iter(self.vae.post_quant_conv.parameters())).dtype
                )
            if self.lowvram and multi_decoder:
                current_width_height = (
                    self.unet.config.sample_size * self.vae_scale_factor
                )
                image = self.tiled_decode(
                    latents, current_width_height, current_width_height
                )
            else:
                image = self.vae.decode(
                    latents / self.vae.config.scaling_factor, return_dict=False
                )[0]
            # cast back to fp16 if needed
            if needs_upcasting:
                self.vae.to(dtype=torch.float16)

        image = self.image_processor.postprocess(image, output_type=output_type)
        if show_image:
            plt.figure(figsize=(10, 10))
            plt.imshow(image[0])
            plt.axis("off")  # Turn off axis numbers and ticks
            plt.show()
        output_images.append(image[0])

        ####################################################### Phase Upscaling #####################################################
        if image_lr == None:
            starting_scale = 2
        else:
            starting_scale = 1
        for current_scale_num in range(starting_scale, scale_num + 1):
            if self.lowvram:
                latents = latents.to(device)
                self.unet.to(device)
                torch.cuda.empty_cache()
            print("### Phase {} Denoising ###".format(current_scale_num))
            current_height = (
                self.unet.config.sample_size * self.vae_scale_factor * current_scale_num
            )
            current_width = (
                self.unet.config.sample_size * self.vae_scale_factor * current_scale_num
            )
            if height > width:
                current_width = int(current_width * aspect_ratio)
            else:
                current_height = int(current_height * aspect_ratio)

            latents = F.interpolate(
                latents,
                size=(
                    int(current_height / self.vae_scale_factor),
                    int(current_width / self.vae_scale_factor),
                ),
                mode="bicubic",
            )
            condition_image = F.interpolate(
                condition_image, size=(current_height, current_width), mode="bicubic"
            )

            noise_latents = []
            noise = torch.randn_like(latents)
            for timestep in timesteps:
                noise_latent = self.scheduler.add_noise(
                    latents, noise, timestep.unsqueeze(0)
                )
                noise_latents.append(noise_latent)
            latents = noise_latents[0]

            with self.progress_bar(total=num_inference_steps) as progress_bar:
                for i, t in enumerate(timesteps):
                    count = torch.zeros_like(latents)
                    value = torch.zeros_like(latents)
                    cosine_factor = (
                        0.5
                        * (
                            1
                            + torch.cos(
                                torch.pi
                                * (self.scheduler.config.num_train_timesteps - t)
                                / self.scheduler.config.num_train_timesteps
                            )
                        ).cpu()
                    )

                    c1 = cosine_factor**cosine_scale_1
                    latents = latents * (1 - c1) + noise_latents[i] * c1

                    ############################################# MultiDiffusion #############################################

                    views = self.get_views(
                        current_height,
                        current_width,
                        stride=stride,
                        window_size=self.unet.config.sample_size,
                        random_jitter=True,
                    )
                    views_batch = [
                        views[i : i + view_batch_size]
                        for i in range(0, len(views), view_batch_size)
                    ]

                    jitter_range = (self.unet.config.sample_size - stride) // 4
                    latents_ = F.pad(
                        latents,
                        (jitter_range, jitter_range, jitter_range, jitter_range),
                        "constant",
                        0,
                    )
                    condition_image_ = F.pad(
                        condition_image,
                        (
                            jitter_range * self.vae_scale_factor,
                            jitter_range * self.vae_scale_factor,
                            jitter_range * self.vae_scale_factor,
                            jitter_range * self.vae_scale_factor,
                        ),
                        "constant",
                        0,
                    )

                    count_local = torch.zeros_like(latents_)
                    value_local = torch.zeros_like(latents_)

                    for j, batch_view in enumerate(views_batch):
                        vb_size = len(batch_view)

                        # get the latents corresponding to the current view coordinates
                        latents_for_view = torch.cat(
                            [
                                latents_[:, :, h_start:h_end, w_start:w_end]
                                for h_start, h_end, w_start, w_end in batch_view
                            ]
                        )
                        condition_image_for_view = torch.cat(
                            [
                                condition_image_[
                                    0:1,
                                    :,
                                    h_start
                                    * self.vae_scale_factor : h_end
                                    * self.vae_scale_factor,
                                    w_start
                                    * self.vae_scale_factor : w_end
                                    * self.vae_scale_factor,
                                ]
                                for h_start, h_end, w_start, w_end in batch_view
                            ]
                        )

                        # expand the latents if we are doing classifier free guidance
                        latent_model_input = latents_for_view
                        latent_model_input = (
                            latent_model_input.repeat_interleave(2, dim=0)
                            if do_classifier_free_guidance
                            else latent_model_input
                        )
                        latent_model_input = self.scheduler.scale_model_input(
                            latent_model_input, t
                        )

                        condition_image_input = condition_image_for_view
                        condition_image_input = (
                            condition_image_input.repeat_interleave(2, dim=0)
                            if do_classifier_free_guidance
                            else condition_image_input
                        )

                        prompt_embeds_input = torch.cat([prompt_embeds] * vb_size)
                        add_text_embeds_input = torch.cat([add_text_embeds] * vb_size)
                        add_time_ids_input = []
                        for h_start, h_end, w_start, w_end in batch_view:
                            add_time_ids_ = add_time_ids.clone()
                            add_time_ids_[:, 2] = h_start * self.vae_scale_factor
                            add_time_ids_[:, 3] = w_start * self.vae_scale_factor
                            add_time_ids_input.append(add_time_ids_)
                        add_time_ids_input = torch.cat(add_time_ids_input)

                        added_cond_kwargs = {
                            "text_embeds": add_text_embeds_input,
                            "time_ids": add_time_ids_input,
                        }

                        # controlnet(s) inference
                        if guess_mode and do_classifier_free_guidance:
                            # Infer ControlNet only for the conditional batch.
                            control_model_input = latent_model_input
                            control_model_input = self.scheduler.scale_model_input(
                                control_model_input, t
                            )
                            controlnet_prompt_embeds = prompt_embeds_input.chunk(2)[1]
                            controlnet_added_cond_kwargs = {
                                "text_embeds": add_text_embeds_input.chunk(2)[1],
                                "time_ids": add_time_ids_input.chunk(2)[1],
                            }
                        else:
                            control_model_input = latent_model_input
                            controlnet_prompt_embeds = prompt_embeds_input
                            controlnet_added_cond_kwargs = added_cond_kwargs

                        if isinstance(controlnet_keep[i], list):
                            cond_scale = [
                                c * s
                                for c, s in zip(
                                    controlnet_conditioning_scale, controlnet_keep[i]
                                )
                            ]
                        else:
                            controlnet_cond_scale = controlnet_conditioning_scale
                            if isinstance(controlnet_cond_scale, list):
                                controlnet_cond_scale = controlnet_cond_scale[0]
                            cond_scale = controlnet_cond_scale * controlnet_keep[i]

                        down_block_res_samples, mid_block_res_sample = self.controlnet(
                            control_model_input,
                            t,
                            encoder_hidden_states=controlnet_prompt_embeds,
                            controlnet_cond=condition_image_input,
                            conditioning_scale=cond_scale,
                            guess_mode=guess_mode,
                            added_cond_kwargs=controlnet_added_cond_kwargs,
                            return_dict=False,
                        )

                        if guess_mode and do_classifier_free_guidance:
                            # Infered ControlNet only for the conditional batch.
                            # To apply the output of ControlNet to both the unconditional and conditional batches,
                            # add 0 to the unconditional batch to keep it unchanged.
                            down_block_res_samples = [
                                torch.cat([torch.zeros_like(d), d])
                                for d in down_block_res_samples
                            ]
                            mid_block_res_sample = torch.cat(
                                [
                                    torch.zeros_like(mid_block_res_sample),
                                    mid_block_res_sample,
                                ]
                            )

                        # predict the noise residual
                        noise_pred = self.unet(
                            latent_model_input,
                            t,
                            encoder_hidden_states=prompt_embeds_input,
                            cross_attention_kwargs=cross_attention_kwargs,
                            down_block_additional_residuals=down_block_res_samples,
                            mid_block_additional_residual=mid_block_res_sample,
                            added_cond_kwargs=added_cond_kwargs,
                            return_dict=False,
                        )[0]

                        if do_classifier_free_guidance:
                            noise_pred_uncond, noise_pred_text = (
                                noise_pred[::2],
                                noise_pred[1::2],
                            )
                            noise_pred = (
                                noise_pred_uncond
                                + guidance_scale
                                * (noise_pred_text - noise_pred_uncond)
                                * 1
                            )

                        # compute the previous noisy sample x_t -> x_t-1
                        self.scheduler._init_step_index(t)
                        latents_denoised_batch = self.scheduler.step(
                            noise_pred,
                            t,
                            latents_for_view,
                            **extra_step_kwargs,
                            return_dict=False,
                        )[0]

                        # extract value from batch
                        for latents_view_denoised, (
                            h_start,
                            h_end,
                            w_start,
                            w_end,
                        ) in zip(latents_denoised_batch.chunk(vb_size), batch_view):
                            value_local[
                                :, :, h_start:h_end, w_start:w_end
                            ] += latents_view_denoised
                            count_local[:, :, h_start:h_end, w_start:w_end] += 1

                    value_local = value_local[
                        :,
                        :,
                        jitter_range : jitter_range
                        + current_height // self.vae_scale_factor,
                        jitter_range : jitter_range
                        + current_width // self.vae_scale_factor,
                    ]
                    count_local = count_local[
                        :,
                        :,
                        jitter_range : jitter_range
                        + current_height // self.vae_scale_factor,
                        jitter_range : jitter_range
                        + current_width // self.vae_scale_factor,
                    ]

                    c2 = cosine_factor**cosine_scale_2

                    value += value_local / count_local * (1 - c2)
                    count += torch.ones_like(value_local) * (1 - c2)

                    ############################################# Dilated Sampling #############################################

                    h_pad = (
                        current_scale_num - (latents.size(2) % current_scale_num)
                    ) % current_scale_num
                    w_pad = (
                        current_scale_num - (latents.size(3) % current_scale_num)
                    ) % current_scale_num
                    latents_ = F.pad(latents, (w_pad, 0, h_pad, 0), "constant", 0)

                    count_global = torch.zeros_like(latents_)
                    value_global = torch.zeros_like(latents_)

                    c3 = 0.99 * cosine_factor**cosine_scale_3 + 1e-2
                    std_, mean_ = latents_.std(), latents_.mean()
                    latents_gaussian = gaussian_filter(
                        latents_,
                        kernel_size=(2 * current_scale_num - 1),
                        sigma=sigma * c3,
                    )
                    latents_gaussian = (
                        latents_gaussian - latents_gaussian.mean()
                    ) / latents_gaussian.std() * std_ + mean_

                    latents_for_view = []
                    for h in range(current_scale_num):
                        for w in range(current_scale_num):
                            latents_for_view.append(
                                latents_[
                                    :, :, h::current_scale_num, w::current_scale_num
                                ]
                            )
                    latents_for_view = torch.cat(latents_for_view)

                    latents_for_view_gaussian = []
                    for h in range(current_scale_num):
                        for w in range(current_scale_num):
                            latents_for_view_gaussian.append(
                                latents_gaussian[
                                    :, :, h::current_scale_num, w::current_scale_num
                                ]
                            )
                    latents_for_view_gaussian = torch.cat(latents_for_view_gaussian)

                    condition_image_for_view = []
                    for h in range(current_scale_num):
                        for w in range(current_scale_num):
                            condition_image_ = F.pad(
                                condition_image,
                                (
                                    w_pad * self.vae_scale_factor,
                                    w * self.vae_scale_factor,
                                    h_pad * self.vae_scale_factor,
                                    h * self.vae_scale_factor,
                                ),
                                "constant",
                                0,
                            )
                            condition_image_for_view.append(
                                condition_image_[
                                    0:1,
                                    :,
                                    h * self.vae_scale_factor :: current_scale_num,
                                    w * self.vae_scale_factor :: current_scale_num,
                                ]
                            )
                    condition_image_for_view = torch.cat(condition_image_for_view)

                    vb_size = latents_for_view.size(0)

                    # expand the latents if we are doing classifier free guidance
                    latent_model_input = latents_for_view_gaussian
                    latent_model_input = (
                        latent_model_input.repeat_interleave(2, dim=0)
                        if do_classifier_free_guidance
                        else latent_model_input
                    )
                    latent_model_input = self.scheduler.scale_model_input(
                        latent_model_input, t
                    )

                    condition_image_input = condition_image_for_view
                    condition_image_input = (
                        condition_image_input.repeat_interleave(2, dim=0)
                        if do_classifier_free_guidance
                        else condition_image_input
                    )

                    prompt_embeds_input = torch.cat([prompt_embeds] * vb_size)
                    add_text_embeds_input = torch.cat([add_text_embeds] * vb_size)
                    add_time_ids_input = torch.cat([add_time_ids] * vb_size)

                    added_cond_kwargs = {
                        "text_embeds": add_text_embeds_input,
                        "time_ids": add_time_ids_input,
                    }

                    # controlnet(s) inference
                    if guess_mode and do_classifier_free_guidance:
                        # Infer ControlNet only for the conditional batch.
                        control_model_input = latent_model_input
                        control_model_input = self.scheduler.scale_model_input(
                            control_model_input, t
                        )
                        controlnet_prompt_embeds = prompt_embeds_input.chunk(2)[1]
                        controlnet_added_cond_kwargs = {
                            "text_embeds": add_text_embeds_input.chunk(2)[1],
                            "time_ids": add_time_ids_input.chunk(2)[1],
                        }
                    else:
                        control_model_input = latent_model_input
                        controlnet_prompt_embeds = prompt_embeds_input
                        controlnet_added_cond_kwargs = added_cond_kwargs

                    if isinstance(controlnet_keep[i], list):
                        cond_scale = [
                            c * s
                            for c, s in zip(
                                controlnet_conditioning_scale, controlnet_keep[i]
                            )
                        ]
                    else:
                        controlnet_cond_scale = controlnet_conditioning_scale
                        if isinstance(controlnet_cond_scale, list):
                            controlnet_cond_scale = controlnet_cond_scale[0]
                        cond_scale = controlnet_cond_scale * controlnet_keep[i]

                    down_block_res_samples, mid_block_res_sample = self.controlnet(
                        control_model_input,
                        t,
                        encoder_hidden_states=controlnet_prompt_embeds,
                        controlnet_cond=condition_image_input,
                        conditioning_scale=cond_scale,
                        guess_mode=guess_mode,
                        added_cond_kwargs=controlnet_added_cond_kwargs,
                        return_dict=False,
                    )

                    if guess_mode and do_classifier_free_guidance:
                        # Infered ControlNet only for the conditional batch.
                        # To apply the output of ControlNet to both the unconditional and conditional batches,
                        # add 0 to the unconditional batch to keep it unchanged.
                        down_block_res_samples = [
                            torch.cat([torch.zeros_like(d), d])
                            for d in down_block_res_samples
                        ]
                        mid_block_res_sample = torch.cat(
                            [
                                torch.zeros_like(mid_block_res_sample),
                                mid_block_res_sample,
                            ]
                        )

                    # predict the noise residual
                    noise_pred = self.unet(
                        latent_model_input,
                        t,
                        encoder_hidden_states=prompt_embeds_input,
                        cross_attention_kwargs=cross_attention_kwargs,
                        down_block_additional_residuals=down_block_res_samples,
                        mid_block_additional_residual=mid_block_res_sample,
                        added_cond_kwargs=added_cond_kwargs,
                        return_dict=False,
                    )[0]

                    if do_classifier_free_guidance:
                        noise_pred_uncond, noise_pred_text = (
                            noise_pred[::2],
                            noise_pred[1::2],
                        )
                        noise_pred = noise_pred_uncond + guidance_scale * (
                            noise_pred_text - noise_pred_uncond
                        )

                    # extract value from batch
                    for h in range(current_scale_num):
                        for w in range(current_scale_num):
                            noise_pred_ = noise_pred.chunk(vb_size)[
                                h * current_scale_num + w
                            ]
                            value_global[
                                :, :, h::current_scale_num, w::current_scale_num
                            ] += noise_pred_
                            count_global[
                                :, :, h::current_scale_num, w::current_scale_num
                            ] += 1

                    # compute the previous noisy sample x_t -> x_t-1
                    self.scheduler._init_step_index(t)
                    value_global = self.scheduler.step(
                        value_global,
                        t,
                        latents_,
                        **extra_step_kwargs,
                        return_dict=False,
                    )[0]

                    c2 = cosine_factor**cosine_scale_2

                    value_global = value_global[:, :, h_pad:, w_pad:]

                    value += value_global * c2
                    count += torch.ones_like(value_global) * c2

                    ###########################################################

                    latents = torch.where(count > 0, value / count, value)

                    # call the callback, if provided
                    if i == len(timesteps) - 1 or (
                        (i + 1) > num_warmup_steps
                        and (i + 1) % self.scheduler.order == 0
                    ):
                        progress_bar.update()
                        if callback is not None and i % callback_steps == 0:
                            step_idx = i // getattr(self.scheduler, "order", 1)
                            callback(step_idx, t, latents)

                #########################################################################################################################################

                latents = (
                    latents - latents.mean()
                ) / latents.std() * anchor_std + anchor_mean
                if self.lowvram:
                    latents = latents.cpu()
                    torch.cuda.empty_cache()
                if not output_type == "latent":
                    # make sure the VAE is in float32 mode, as it overflows in float16
                    needs_upcasting = (
                        self.vae.dtype == torch.float16 and self.vae.config.force_upcast
                    )

                    if self.lowvram:
                        needs_upcasting = (
                            False  # use madebyollin/sdxl-vae-fp16-fix in lowvram mode!
                        )
                        self.unet.cpu()
                        self.vae.to(device)

                    if needs_upcasting:
                        self.upcast_vae()
                        latents = latents.to(
                            next(iter(self.vae.post_quant_conv.parameters())).dtype
                        )

                    print("### Phase {} Decoding ###".format(current_scale_num))
                    if multi_decoder:
                        image = self.tiled_decode(
                            latents, current_height, current_width
                        )
                    else:
                        image = self.vae.decode(
                            latents / self.vae.config.scaling_factor, return_dict=False
                        )[0]

                    # cast back to fp16 if needed
                    if needs_upcasting:
                        self.vae.to(dtype=torch.float16)
                else:
                    image = latents

                if not output_type == "latent":
                    image = self.image_processor.postprocess(
                        image, output_type=output_type
                    )
                    if show_image:
                        plt.figure(figsize=(10, 10))
                        plt.imshow(image[0])
                        plt.axis("off")  # Turn off axis numbers and ticks
                        plt.show()
                    output_images.append(image[0])

        # Offload all models
        self.maybe_free_model_hooks()

        return output_images

    # Overrride to properly handle the loading and unloading of the additional text encoder.
    def load_lora_weights(
        self,
        pretrained_model_name_or_path_or_dict: Union[str, Dict[str, torch.Tensor]],
        **kwargs,
    ):
        # We could have accessed the unet config from `lora_state_dict()` too. We pass
        # it here explicitly to be able to tell that it's coming from an SDXL
        # pipeline.

        # Remove any existing hooks.
        if is_accelerate_available() and is_accelerate_version(">=", "0.17.0.dev0"):
            from accelerate.hooks import (
                AlignDevicesHook,
                CpuOffload,
                remove_hook_from_module,
            )
        else:
            raise ImportError("Offloading requires `accelerate v0.17.0` or higher.")

        is_model_cpu_offload = False
        is_sequential_cpu_offload = False
        recursive = False
        for _, component in self.components.items():
            if isinstance(component, torch.nn.Module):
                if hasattr(component, "_hf_hook"):
                    is_model_cpu_offload = isinstance(
                        getattr(component, "_hf_hook"), CpuOffload
                    )
                    is_sequential_cpu_offload = isinstance(
                        getattr(component, "_hf_hook"), AlignDevicesHook
                    )
                    logger.info(
                        "Accelerate hooks detected. Since you have called `load_lora_weights()`, the previous hooks will be first removed. Then the LoRA parameters will be loaded and the hooks will be applied again."
                    )
                    recursive = is_sequential_cpu_offload
                    remove_hook_from_module(component, recurse=recursive)
        state_dict, network_alphas = self.lora_state_dict(
            pretrained_model_name_or_path_or_dict,
            unet_config=self.unet.config,
            **kwargs,
        )
        self.load_lora_into_unet(
            state_dict, network_alphas=network_alphas, unet=self.unet
        )

        text_encoder_state_dict = {
            k: v for k, v in state_dict.items() if "text_encoder." in k
        }
        if len(text_encoder_state_dict) > 0:
            self.load_lora_into_text_encoder(
                text_encoder_state_dict,
                network_alphas=network_alphas,
                text_encoder=self.text_encoder,
                prefix="text_encoder",
                lora_scale=self.lora_scale,
            )

        text_encoder_2_state_dict = {
            k: v for k, v in state_dict.items() if "text_encoder_2." in k
        }
        if len(text_encoder_2_state_dict) > 0:
            self.load_lora_into_text_encoder(
                text_encoder_2_state_dict,
                network_alphas=network_alphas,
                text_encoder=self.text_encoder_2,
                prefix="text_encoder_2",
                lora_scale=self.lora_scale,
            )

        # Offload back.
        if is_model_cpu_offload:
            self.enable_model_cpu_offload()
        elif is_sequential_cpu_offload:
            self.enable_sequential_cpu_offload()

    @classmethod
    def save_lora_weights(
        self,
        save_directory: Union[str, os.PathLike],
        unet_lora_layers: Dict[str, Union[torch.nn.Module, torch.Tensor]] = None,
        text_encoder_lora_layers: Dict[
            str, Union[torch.nn.Module, torch.Tensor]
        ] = None,
        text_encoder_2_lora_layers: Dict[
            str, Union[torch.nn.Module, torch.Tensor]
        ] = None,
        is_main_process: bool = True,
        weight_name: str = None,
        save_function: Callable = None,
        safe_serialization: bool = True,
    ):
        state_dict = {}

        def pack_weights(layers, prefix):
            layers_weights = (
                layers.state_dict() if isinstance(layers, torch.nn.Module) else layers
            )
            layers_state_dict = {
                f"{prefix}.{module_name}": param
                for module_name, param in layers_weights.items()
            }
            return layers_state_dict

        if not (
            unet_lora_layers or text_encoder_lora_layers or text_encoder_2_lora_layers
        ):
            raise ValueError(
                "You must pass at least one of `unet_lora_layers`, `text_encoder_lora_layers` or `text_encoder_2_lora_layers`."
            )

        if unet_lora_layers:
            state_dict.update(pack_weights(unet_lora_layers, "unet"))

        if text_encoder_lora_layers and text_encoder_2_lora_layers:
            state_dict.update(pack_weights(text_encoder_lora_layers, "text_encoder"))
            state_dict.update(
                pack_weights(text_encoder_2_lora_layers, "text_encoder_2")
            )

        self.write_lora_layers(
            state_dict=state_dict,
            save_directory=save_directory,
            is_main_process=is_main_process,
            weight_name=weight_name,
            save_function=save_function,
            safe_serialization=safe_serialization,
        )

    def _remove_text_encoder_monkey_patch(self):
        self._remove_text_encoder_monkey_patch_classmethod(self.text_encoder)
        self._remove_text_encoder_monkey_patch_classmethod(self.text_encoder_2)