File size: 96,102 Bytes
dc1ad90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
wild mixture of
https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
https://github.com/openai/improved-diffusion/blob/e94489283bb876ac1477d5dd7709bbbd2d9902ce/improved_diffusion/gaussian_diffusion.py
https://github.com/CompVis/taming-transformers
-- merci
"""

import torch
import torch.nn as nn
import numpy as np
import pytorch_lightning as pl
from torch.optim.lr_scheduler import LambdaLR
from einops import rearrange, repeat
from contextlib import contextmanager, nullcontext
from functools import partial
import itertools
from tqdm import tqdm
from torchvision.utils import make_grid
from pytorch_lightning.utilities.distributed import rank_zero_only
from omegaconf import ListConfig

from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
from ldm.modules.ema import LitEma
from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.modules.attention import CrossAttention


__conditioning_keys__ = {'concat': 'c_concat',
                         'crossattn': 'c_crossattn',
                         'adm': 'y'}


def disabled_train(self, mode=True):
    """Overwrite model.train with this function to make sure train/eval mode
    does not change anymore."""
    return self


def uniform_on_device(r1, r2, shape, device):
    return (r1 - r2) * torch.rand(*shape, device=device) + r2


class DDPM(pl.LightningModule):
    # classic DDPM with Gaussian diffusion, in image space
    def __init__(self,
                 unet_config,
                 timesteps=1000,
                 beta_schedule="linear",
                 loss_type="l2",
                 ckpt_path=None,
                 ignore_keys=[],
                 load_only_unet=False,
                 monitor="val/loss",
                 use_ema=True,
                 first_stage_key="image",
                 image_size=256,
                 channels=3,
                 log_every_t=100,
                 clip_denoised=True,
                 linear_start=1e-4,
                 linear_end=2e-2,
                 cosine_s=8e-3,
                 given_betas=None,
                 original_elbo_weight=0.,
                 v_posterior=0.,  # weight for choosing posterior variance as sigma = (1-v) * beta_tilde + v * beta
                 l_simple_weight=1.,
                 conditioning_key=None,
                 parameterization="eps",  # all assuming fixed variance schedules
                 scheduler_config=None,
                 use_positional_encodings=False,
                 learn_logvar=False,
                 logvar_init=0.,
                 make_it_fit=False,
                 ucg_training=None,
                 ):
        super().__init__()
        assert parameterization in ["eps", "x0"], 'currently only supporting "eps" and "x0"'
        self.parameterization = parameterization
        print(f"{self.__class__.__name__}: Running in {self.parameterization}-prediction mode")
        self.cond_stage_model = None
        self.clip_denoised = clip_denoised
        self.log_every_t = log_every_t
        self.first_stage_key = first_stage_key
        self.image_size = image_size  # try conv?
        self.channels = channels
        self.use_positional_encodings = use_positional_encodings
        self.model = DiffusionWrapper(unet_config, conditioning_key)
        count_params(self.model, verbose=True)
        self.use_ema = use_ema
        if self.use_ema:
            self.model_ema = LitEma(self.model)
            print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")

        self.use_scheduler = scheduler_config is not None
        if self.use_scheduler:
            self.scheduler_config = scheduler_config

        self.v_posterior = v_posterior
        self.original_elbo_weight = original_elbo_weight
        self.l_simple_weight = l_simple_weight

        if monitor is not None:
            self.monitor = monitor
        self.make_it_fit = make_it_fit
        if ckpt_path is not None:
            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)

        self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
                               linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)

        self.loss_type = loss_type

        self.learn_logvar = learn_logvar
        self.logvar = torch.full(fill_value=logvar_init, size=(self.num_timesteps,))
        if self.learn_logvar:
            self.logvar = nn.Parameter(self.logvar, requires_grad=True)

        self.ucg_training = ucg_training or dict()
        if self.ucg_training:
            self.ucg_prng = np.random.RandomState()

    def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000,
                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
        if exists(given_betas):
            betas = given_betas
        else:
            betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end,
                                       cosine_s=cosine_s)
        alphas = 1. - betas
        alphas_cumprod = np.cumprod(alphas, axis=0)
        alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])

        timesteps, = betas.shape
        self.num_timesteps = int(timesteps)
        self.linear_start = linear_start
        self.linear_end = linear_end
        assert alphas_cumprod.shape[0] == self.num_timesteps, 'alphas have to be defined for each timestep'

        to_torch = partial(torch.tensor, dtype=torch.float32)

        self.register_buffer('betas', to_torch(betas))
        self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
        self.register_buffer('alphas_cumprod_prev', to_torch(alphas_cumprod_prev))

        # calculations for diffusion q(x_t | x_{t-1}) and others
        self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod)))
        self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod)))
        self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod)))
        self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod)))
        self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod - 1)))

        # calculations for posterior q(x_{t-1} | x_t, x_0)
        posterior_variance = (1 - self.v_posterior) * betas * (1. - alphas_cumprod_prev) / (
                    1. - alphas_cumprod) + self.v_posterior * betas
        # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
        self.register_buffer('posterior_variance', to_torch(posterior_variance))
        # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
        self.register_buffer('posterior_log_variance_clipped', to_torch(np.log(np.maximum(posterior_variance, 1e-20))))
        self.register_buffer('posterior_mean_coef1', to_torch(
            betas * np.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod)))
        self.register_buffer('posterior_mean_coef2', to_torch(
            (1. - alphas_cumprod_prev) * np.sqrt(alphas) / (1. - alphas_cumprod)))

        if self.parameterization == "eps":
            lvlb_weights = self.betas ** 2 / (
                        2 * self.posterior_variance * to_torch(alphas) * (1 - self.alphas_cumprod))
        elif self.parameterization == "x0":
            lvlb_weights = 0.5 * np.sqrt(torch.Tensor(alphas_cumprod)) / (2. * 1 - torch.Tensor(alphas_cumprod))
        else:
            raise NotImplementedError("mu not supported")
        # TODO how to choose this term
        lvlb_weights[0] = lvlb_weights[1]
        self.register_buffer('lvlb_weights', lvlb_weights, persistent=False)
        assert not torch.isnan(self.lvlb_weights).all()

    @contextmanager
    def ema_scope(self, context=None):
        if self.use_ema:
            self.model_ema.store(self.model.parameters())
            self.model_ema.copy_to(self.model)
            if context is not None:
                print(f"{context}: Switched to EMA weights")
        try:
            yield None
        finally:
            if self.use_ema:
                self.model_ema.restore(self.model.parameters())
                if context is not None:
                    print(f"{context}: Restored training weights")

    @torch.no_grad()
    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
        sd = torch.load(path, map_location="cpu")
        if "state_dict" in list(sd.keys()):
            sd = sd["state_dict"]
        keys = list(sd.keys())

        if self.make_it_fit:
            n_params = len([name for name, _ in
                            itertools.chain(self.named_parameters(),
                                            self.named_buffers())])
            for name, param in tqdm(
                    itertools.chain(self.named_parameters(),
                                    self.named_buffers()),
                    desc="Fitting old weights to new weights",
                    total=n_params
            ):
                if not name in sd:
                    continue
                old_shape = sd[name].shape
                new_shape = param.shape
                assert len(old_shape)==len(new_shape)
                if len(new_shape) > 2:
                    # we only modify first two axes
                    assert new_shape[2:] == old_shape[2:]
                # assumes first axis corresponds to output dim
                if not new_shape == old_shape:
                    new_param = param.clone()
                    old_param = sd[name]
                    if len(new_shape) == 1:
                        for i in range(new_param.shape[0]):
                            new_param[i] = old_param[i % old_shape[0]]
                    elif len(new_shape) >= 2:
                        for i in range(new_param.shape[0]):
                            for j in range(new_param.shape[1]):
                                new_param[i, j] = old_param[i % old_shape[0], j % old_shape[1]]

                        n_used_old = torch.ones(old_shape[1])
                        for j in range(new_param.shape[1]):
                            n_used_old[j % old_shape[1]] += 1
                        n_used_new = torch.zeros(new_shape[1])
                        for j in range(new_param.shape[1]):
                            n_used_new[j] = n_used_old[j % old_shape[1]]

                        n_used_new = n_used_new[None, :]
                        while len(n_used_new.shape) < len(new_shape):
                            n_used_new = n_used_new.unsqueeze(-1)
                        new_param /= n_used_new

                    sd[name] = new_param

        missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
            sd, strict=False)
        print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
        if len(missing) > 0:
            print(f"Missing Keys: {missing}")
        if len(unexpected) > 0:
            print(f"Unexpected Keys: {unexpected}")

    def q_mean_variance(self, x_start, t):
        """
        Get the distribution q(x_t | x_0).
        :param x_start: the [N x C x ...] tensor of noiseless inputs.
        :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
        :return: A tuple (mean, variance, log_variance), all of x_start's shape.
        """
        mean = (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start)
        variance = extract_into_tensor(1.0 - self.alphas_cumprod, t, x_start.shape)
        log_variance = extract_into_tensor(self.log_one_minus_alphas_cumprod, t, x_start.shape)
        return mean, variance, log_variance

    def predict_start_from_noise(self, x_t, t, noise):
        return (
                extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t -
                extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
        )

    def q_posterior(self, x_start, x_t, t):
        posterior_mean = (
                extract_into_tensor(self.posterior_mean_coef1, t, x_t.shape) * x_start +
                extract_into_tensor(self.posterior_mean_coef2, t, x_t.shape) * x_t
        )
        posterior_variance = extract_into_tensor(self.posterior_variance, t, x_t.shape)
        posterior_log_variance_clipped = extract_into_tensor(self.posterior_log_variance_clipped, t, x_t.shape)
        return posterior_mean, posterior_variance, posterior_log_variance_clipped

    def p_mean_variance(self, x, t, clip_denoised: bool):
        model_out = self.model(x, t)
        if self.parameterization == "eps":
            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
        elif self.parameterization == "x0":
            x_recon = model_out
        if clip_denoised:
            x_recon.clamp_(-1., 1.)

        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
        return model_mean, posterior_variance, posterior_log_variance

    @torch.no_grad()
    def p_sample(self, x, t, clip_denoised=True, repeat_noise=False):
        b, *_, device = *x.shape, x.device
        model_mean, _, model_log_variance = self.p_mean_variance(x=x, t=t, clip_denoised=clip_denoised)
        noise = noise_like(x.shape, device, repeat_noise)
        # no noise when t == 0
        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
        return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise

    @torch.no_grad()
    def p_sample_loop(self, shape, return_intermediates=False):
        device = self.betas.device
        b = shape[0]
        img = torch.randn(shape, device=device)
        intermediates = [img]
        for i in tqdm(reversed(range(0, self.num_timesteps)), desc='Sampling t', total=self.num_timesteps):
            img = self.p_sample(img, torch.full((b,), i, device=device, dtype=torch.long),
                                clip_denoised=self.clip_denoised)
            if i % self.log_every_t == 0 or i == self.num_timesteps - 1:
                intermediates.append(img)
        if return_intermediates:
            return img, intermediates
        return img

    @torch.no_grad()
    def sample(self, batch_size=16, return_intermediates=False):
        image_size = self.image_size
        channels = self.channels
        return self.p_sample_loop((batch_size, channels, image_size, image_size),
                                  return_intermediates=return_intermediates)

    def q_sample(self, x_start, t, noise=None):
        noise = default(noise, lambda: torch.randn_like(x_start))
        return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
                extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)

    def get_loss(self, pred, target, mean=True):
        if self.loss_type == 'l1':
            loss = (target - pred).abs()
            if mean:
                loss = loss.mean()
        elif self.loss_type == 'l2':
            if mean:
                loss = torch.nn.functional.mse_loss(target, pred)
            else:
                loss = torch.nn.functional.mse_loss(target, pred, reduction='none')
        else:
            raise NotImplementedError("unknown loss type '{loss_type}'")

        return loss

    def p_losses(self, x_start, t, noise=None):
        noise = default(noise, lambda: torch.randn_like(x_start))
        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
        model_out = self.model(x_noisy, t)

        loss_dict = {}
        if self.parameterization == "eps":
            target = noise
        elif self.parameterization == "x0":
            target = x_start
        else:
            raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")

        loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])

        log_prefix = 'train' if self.training else 'val'

        loss_dict.update({f'{log_prefix}/loss_simple': loss.mean()})
        loss_simple = loss.mean() * self.l_simple_weight

        loss_vlb = (self.lvlb_weights[t] * loss).mean()
        loss_dict.update({f'{log_prefix}/loss_vlb': loss_vlb})

        loss = loss_simple + self.original_elbo_weight * loss_vlb

        loss_dict.update({f'{log_prefix}/loss': loss})

        return loss, loss_dict

    def forward(self, x, *args, **kwargs):
        # b, c, h, w, device, img_size, = *x.shape, x.device, self.image_size
        # assert h == img_size and w == img_size, f'height and width of image must be {img_size}'
        t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
        return self.p_losses(x, t, *args, **kwargs)

    def get_input(self, batch, k):
        x = batch[k]
        if len(x.shape) == 3:
            x = x[..., None]
        x = rearrange(x, 'b h w c -> b c h w')
        x = x.to(memory_format=torch.contiguous_format).float()
        return x

    def shared_step(self, batch):
        x = self.get_input(batch, self.first_stage_key)
        loss, loss_dict = self(x)
        return loss, loss_dict

    def training_step(self, batch, batch_idx):
        for k in self.ucg_training:
            p = self.ucg_training[k]["p"]
            val = self.ucg_training[k]["val"]
            if val is None:
                val = ""
            for i in range(len(batch[k])):
                if self.ucg_prng.choice(2, p=[1-p, p]):
                    batch[k][i] = val

        loss, loss_dict = self.shared_step(batch)

        self.log_dict(loss_dict, prog_bar=True,
                      logger=True, on_step=True, on_epoch=True)

        self.log("global_step", self.global_step,
                 prog_bar=True, logger=True, on_step=True, on_epoch=False)

        if self.use_scheduler:
            lr = self.optimizers().param_groups[0]['lr']
            self.log('lr_abs', lr, prog_bar=True, logger=True, on_step=True, on_epoch=False)

        return loss

    @torch.no_grad()
    def validation_step(self, batch, batch_idx):
        _, loss_dict_no_ema = self.shared_step(batch)
        with self.ema_scope():
            _, loss_dict_ema = self.shared_step(batch)
            loss_dict_ema = {key + '_ema': loss_dict_ema[key] for key in loss_dict_ema}
        self.log_dict(loss_dict_no_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
        self.log_dict(loss_dict_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)

    def on_train_batch_end(self, *args, **kwargs):
        if self.use_ema:
            self.model_ema(self.model)

    def _get_rows_from_list(self, samples):
        n_imgs_per_row = len(samples)
        denoise_grid = rearrange(samples, 'n b c h w -> b n c h w')
        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
        return denoise_grid

    @torch.no_grad()
    def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
        log = dict()
        x = self.get_input(batch, self.first_stage_key)
        N = min(x.shape[0], N)
        n_row = min(x.shape[0], n_row)
        x = x.to(self.device)[:N]
        log["inputs"] = x

        # get diffusion row
        diffusion_row = list()
        x_start = x[:n_row]

        for t in range(self.num_timesteps):
            if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
                t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
                t = t.to(self.device).long()
                noise = torch.randn_like(x_start)
                x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
                diffusion_row.append(x_noisy)

        log["diffusion_row"] = self._get_rows_from_list(diffusion_row)

        if sample:
            # get denoise row
            with self.ema_scope("Plotting"):
                samples, denoise_row = self.sample(batch_size=N, return_intermediates=True)

            log["samples"] = samples
            log["denoise_row"] = self._get_rows_from_list(denoise_row)

        if return_keys:
            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
                return log
            else:
                return {key: log[key] for key in return_keys}
        return log

    def configure_optimizers(self):
        lr = self.learning_rate
        params = list(self.model.parameters())
        if self.learn_logvar:
            params = params + [self.logvar]
        opt = torch.optim.AdamW(params, lr=lr)
        return opt


class LatentDiffusion(DDPM):
    """main class"""
    def __init__(self,
                 first_stage_config,
                 cond_stage_config,
                 num_timesteps_cond=None,
                 cond_stage_key="image",
                 cond_stage_trainable=False,
                 concat_mode=True,
                 cond_stage_forward=None,
                 conditioning_key=None,
                 scale_factor=1.0,
                 scale_by_std=False,
                 unet_trainable=True,
                 *args, **kwargs):
        self.num_timesteps_cond = default(num_timesteps_cond, 1)
        self.scale_by_std = scale_by_std
        assert self.num_timesteps_cond <= kwargs['timesteps']
        # for backwards compatibility after implementation of DiffusionWrapper
        if conditioning_key is None:
            conditioning_key = 'concat' if concat_mode else 'crossattn'
        if cond_stage_config == '__is_unconditional__':
            conditioning_key = None
        ckpt_path = kwargs.pop("ckpt_path", None)
        ignore_keys = kwargs.pop("ignore_keys", [])
        super().__init__(conditioning_key=conditioning_key, *args, **kwargs)
        self.concat_mode = concat_mode
        self.cond_stage_trainable = cond_stage_trainable
        self.unet_trainable = unet_trainable
        self.cond_stage_key = cond_stage_key
        try:
            self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
        except:
            self.num_downs = 0
        if not scale_by_std:
            self.scale_factor = scale_factor
        else:
            self.register_buffer('scale_factor', torch.tensor(scale_factor))
        self.instantiate_first_stage(first_stage_config)
        self.instantiate_cond_stage(cond_stage_config)
        self.cond_stage_forward = cond_stage_forward

        # construct linear projection layer for concatenating image CLIP embedding and RT
        self.cc_projection = nn.Linear(772, 768)
        nn.init.eye_(list(self.cc_projection.parameters())[0][:768, :768])
        nn.init.zeros_(list(self.cc_projection.parameters())[1])
        self.cc_projection.requires_grad_(True)
        
        self.clip_denoised = False
        self.bbox_tokenizer = None

        self.restarted_from_ckpt = False
        if ckpt_path is not None:
            self.init_from_ckpt(ckpt_path, ignore_keys)
            self.restarted_from_ckpt = True

    def make_cond_schedule(self, ):
        self.cond_ids = torch.full(size=(self.num_timesteps,), fill_value=self.num_timesteps - 1, dtype=torch.long)
        ids = torch.round(torch.linspace(0, self.num_timesteps - 1, self.num_timesteps_cond)).long()
        self.cond_ids[:self.num_timesteps_cond] = ids

    @rank_zero_only
    @torch.no_grad()
    def on_train_batch_start(self, batch, batch_idx, dataloader_idx):
        # only for very first batch
        if self.scale_by_std and self.current_epoch == 0 and self.global_step == 0 and batch_idx == 0 and not self.restarted_from_ckpt:
            assert self.scale_factor == 1., 'rather not use custom rescaling and std-rescaling simultaneously'
            # set rescale weight to 1./std of encodings
            print("### USING STD-RESCALING ###")
            x = super().get_input(batch, self.first_stage_key)
            x = x.to(self.device)
            encoder_posterior = self.encode_first_stage(x)
            z = self.get_first_stage_encoding(encoder_posterior).detach()
            del self.scale_factor
            self.register_buffer('scale_factor', 1. / z.flatten().std())
            print(f"setting self.scale_factor to {self.scale_factor}")
            print("### USING STD-RESCALING ###")

    def register_schedule(self,
                          given_betas=None, beta_schedule="linear", timesteps=1000,
                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
        super().register_schedule(given_betas, beta_schedule, timesteps, linear_start, linear_end, cosine_s)

        self.shorten_cond_schedule = self.num_timesteps_cond > 1
        if self.shorten_cond_schedule:
            self.make_cond_schedule()

    def instantiate_first_stage(self, config):
        model = instantiate_from_config(config)
        self.first_stage_model = model.eval()
        self.first_stage_model.train = disabled_train
        for param in self.first_stage_model.parameters():
            param.requires_grad = False

    def instantiate_cond_stage(self, config):
        if not self.cond_stage_trainable:
            if config == "__is_first_stage__":
                print("Using first stage also as cond stage.")
                self.cond_stage_model = self.first_stage_model
            elif config == "__is_unconditional__":
                print(f"Training {self.__class__.__name__} as an unconditional model.")
                self.cond_stage_model = None
                # self.be_unconditional = True
            else:
                model = instantiate_from_config(config)
                self.cond_stage_model = model.eval()
                self.cond_stage_model.train = disabled_train
                for param in self.cond_stage_model.parameters():
                    param.requires_grad = False
        else:
            assert config != '__is_first_stage__'
            assert config != '__is_unconditional__'
            model = instantiate_from_config(config)
            self.cond_stage_model = model

    def _get_denoise_row_from_list(self, samples, desc='', force_no_decoder_quantization=False):
        denoise_row = []
        for zd in tqdm(samples, desc=desc):
            denoise_row.append(self.decode_first_stage(zd.to(self.device),
                                                            force_not_quantize=force_no_decoder_quantization))
        n_imgs_per_row = len(denoise_row)
        denoise_row = torch.stack(denoise_row)  # n_log_step, n_row, C, H, W
        denoise_grid = rearrange(denoise_row, 'n b c h w -> b n c h w')
        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
        return denoise_grid

    def get_first_stage_encoding(self, encoder_posterior):
        if isinstance(encoder_posterior, DiagonalGaussianDistribution):
            z = encoder_posterior.sample()
        elif isinstance(encoder_posterior, torch.Tensor):
            z = encoder_posterior
        else:
            raise NotImplementedError(f"encoder_posterior of type '{type(encoder_posterior)}' not yet implemented")
        return self.scale_factor * z

    def get_learned_conditioning(self, c):
        if self.cond_stage_forward is None:
            if hasattr(self.cond_stage_model, 'encode') and callable(self.cond_stage_model.encode):
                c = self.cond_stage_model.encode(c)
                if isinstance(c, DiagonalGaussianDistribution):
                    c = c.mode()
            else:
                c = self.cond_stage_model(c)
        else:
            assert hasattr(self.cond_stage_model, self.cond_stage_forward)
            c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
        return c

    def meshgrid(self, h, w):
        y = torch.arange(0, h).view(h, 1, 1).repeat(1, w, 1)
        x = torch.arange(0, w).view(1, w, 1).repeat(h, 1, 1)

        arr = torch.cat([y, x], dim=-1)
        return arr

    def delta_border(self, h, w):
        """
        :param h: height
        :param w: width
        :return: normalized distance to image border,
         wtith min distance = 0 at border and max dist = 0.5 at image center
        """
        lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
        arr = self.meshgrid(h, w) / lower_right_corner
        dist_left_up = torch.min(arr, dim=-1, keepdims=True)[0]
        dist_right_down = torch.min(1 - arr, dim=-1, keepdims=True)[0]
        edge_dist = torch.min(torch.cat([dist_left_up, dist_right_down], dim=-1), dim=-1)[0]
        return edge_dist

    def get_weighting(self, h, w, Ly, Lx, device):
        weighting = self.delta_border(h, w)
        weighting = torch.clip(weighting, self.split_input_params["clip_min_weight"],
                               self.split_input_params["clip_max_weight"], )
        weighting = weighting.view(1, h * w, 1).repeat(1, 1, Ly * Lx).to(device)

        if self.split_input_params["tie_braker"]:
            L_weighting = self.delta_border(Ly, Lx)
            L_weighting = torch.clip(L_weighting,
                                     self.split_input_params["clip_min_tie_weight"],
                                     self.split_input_params["clip_max_tie_weight"])

            L_weighting = L_weighting.view(1, 1, Ly * Lx).to(device)
            weighting = weighting * L_weighting
        return weighting

    def get_fold_unfold(self, x, kernel_size, stride, uf=1, df=1):  # todo load once not every time, shorten code
        """
        :param x: img of size (bs, c, h, w)
        :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
        """
        bs, nc, h, w = x.shape

        # number of crops in image
        Ly = (h - kernel_size[0]) // stride[0] + 1
        Lx = (w - kernel_size[1]) // stride[1] + 1

        if uf == 1 and df == 1:
            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
            unfold = torch.nn.Unfold(**fold_params)

            fold = torch.nn.Fold(output_size=x.shape[2:], **fold_params)

            weighting = self.get_weighting(kernel_size[0], kernel_size[1], Ly, Lx, x.device).to(x.dtype)
            normalization = fold(weighting).view(1, 1, h, w)  # normalizes the overlap
            weighting = weighting.view((1, 1, kernel_size[0], kernel_size[1], Ly * Lx))

        elif uf > 1 and df == 1:
            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
            unfold = torch.nn.Unfold(**fold_params)

            fold_params2 = dict(kernel_size=(kernel_size[0] * uf, kernel_size[0] * uf),
                                dilation=1, padding=0,
                                stride=(stride[0] * uf, stride[1] * uf))
            fold = torch.nn.Fold(output_size=(x.shape[2] * uf, x.shape[3] * uf), **fold_params2)

            weighting = self.get_weighting(kernel_size[0] * uf, kernel_size[1] * uf, Ly, Lx, x.device).to(x.dtype)
            normalization = fold(weighting).view(1, 1, h * uf, w * uf)  # normalizes the overlap
            weighting = weighting.view((1, 1, kernel_size[0] * uf, kernel_size[1] * uf, Ly * Lx))

        elif df > 1 and uf == 1:
            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
            unfold = torch.nn.Unfold(**fold_params)

            fold_params2 = dict(kernel_size=(kernel_size[0] // df, kernel_size[0] // df),
                                dilation=1, padding=0,
                                stride=(stride[0] // df, stride[1] // df))
            fold = torch.nn.Fold(output_size=(x.shape[2] // df, x.shape[3] // df), **fold_params2)

            weighting = self.get_weighting(kernel_size[0] // df, kernel_size[1] // df, Ly, Lx, x.device).to(x.dtype)
            normalization = fold(weighting).view(1, 1, h // df, w // df)  # normalizes the overlap
            weighting = weighting.view((1, 1, kernel_size[0] // df, kernel_size[1] // df, Ly * Lx))

        else:
            raise NotImplementedError

        return fold, unfold, normalization, weighting

    
    @torch.no_grad()
    def get_input(self, batch, k, return_first_stage_outputs=False, force_c_encode=False,
                  cond_key=None, return_original_cond=False, bs=None, uncond=0.05):
        x = super().get_input(batch, k)
        T = batch['T'].to(memory_format=torch.contiguous_format).float()
        
        if bs is not None:
            x = x[:bs]
            T = T[:bs].to(self.device)

        x = x.to(self.device)
        encoder_posterior = self.encode_first_stage(x)
        z = self.get_first_stage_encoding(encoder_posterior).detach()
        cond_key = cond_key or self.cond_stage_key
        xc = super().get_input(batch, cond_key).to(self.device)
        if bs is not None:
            xc = xc[:bs]
        cond = {}

        # To support classifier-free guidance, randomly drop out only text conditioning 5%, only image conditioning 5%, and both 5%.
        random = torch.rand(x.size(0), device=x.device)
        prompt_mask = rearrange(random < 2 * uncond, "n -> n 1 1")
        input_mask = 1 - rearrange((random >= uncond).float() * (random < 3 * uncond).float(), "n -> n 1 1 1")
        null_prompt = self.get_learned_conditioning([""])

        # z.shape: [8, 4, 64, 64]; c.shape: [8, 1, 768]
        # print('=========== xc shape ===========', xc.shape)
        with torch.enable_grad():
            clip_emb = self.get_learned_conditioning(xc).detach()
            null_prompt = self.get_learned_conditioning([""]).detach()
            cond["c_crossattn"] = [self.cc_projection(torch.cat([torch.where(prompt_mask, null_prompt, clip_emb), T[:, None, :]], dim=-1))]
        cond["c_concat"] = [input_mask * self.encode_first_stage((xc.to(self.device))).mode().detach()]
        out = [z, cond]
        if return_first_stage_outputs:
            xrec = self.decode_first_stage(z)
            out.extend([x, xrec])
        if return_original_cond:
            out.append(xc)
        return out

    # @torch.no_grad()
    def decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
        if predict_cids:
            if z.dim() == 4:
                z = torch.argmax(z.exp(), dim=1).long()
            z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
            z = rearrange(z, 'b h w c -> b c h w').contiguous()

        z = 1. / self.scale_factor * z

        if hasattr(self, "split_input_params"):
            if self.split_input_params["patch_distributed_vq"]:
                ks = self.split_input_params["ks"]  # eg. (128, 128)
                stride = self.split_input_params["stride"]  # eg. (64, 64)
                uf = self.split_input_params["vqf"]
                bs, nc, h, w = z.shape
                if ks[0] > h or ks[1] > w:
                    ks = (min(ks[0], h), min(ks[1], w))
                    print("reducing Kernel")

                if stride[0] > h or stride[1] > w:
                    stride = (min(stride[0], h), min(stride[1], w))
                    print("reducing stride")

                fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)

                z = unfold(z)  # (bn, nc * prod(**ks), L)
                # 1. Reshape to img shape
                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )

                # 2. apply model loop over last dim
                if isinstance(self.first_stage_model, VQModelInterface):
                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
                                                                 force_not_quantize=predict_cids or force_not_quantize)
                                   for i in range(z.shape[-1])]
                else:

                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
                                   for i in range(z.shape[-1])]

                o = torch.stack(output_list, axis=-1)  # # (bn, nc, ks[0], ks[1], L)
                o = o * weighting
                # Reverse 1. reshape to img shape
                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
                # stitch crops together
                decoded = fold(o)
                decoded = decoded / normalization  # norm is shape (1, 1, h, w)
                return decoded
            else:
                if isinstance(self.first_stage_model, VQModelInterface):
                    return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
                else:
                    return self.first_stage_model.decode(z)

        else:
            if isinstance(self.first_stage_model, VQModelInterface):
                return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
            else:
                return self.first_stage_model.decode(z)

    @torch.no_grad()
    def encode_first_stage(self, x):
        if hasattr(self, "split_input_params"):
            if self.split_input_params["patch_distributed_vq"]:
                ks = self.split_input_params["ks"]  # eg. (128, 128)
                stride = self.split_input_params["stride"]  # eg. (64, 64)
                df = self.split_input_params["vqf"]
                self.split_input_params['original_image_size'] = x.shape[-2:]
                bs, nc, h, w = x.shape
                if ks[0] > h or ks[1] > w:
                    ks = (min(ks[0], h), min(ks[1], w))
                    print("reducing Kernel")

                if stride[0] > h or stride[1] > w:
                    stride = (min(stride[0], h), min(stride[1], w))
                    print("reducing stride")

                fold, unfold, normalization, weighting = self.get_fold_unfold(x, ks, stride, df=df)
                z = unfold(x)  # (bn, nc * prod(**ks), L)
                # Reshape to img shape
                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )

                output_list = [self.first_stage_model.encode(z[:, :, :, :, i])
                               for i in range(z.shape[-1])]

                o = torch.stack(output_list, axis=-1)
                o = o * weighting

                # Reverse reshape to img shape
                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
                # stitch crops together
                decoded = fold(o)
                decoded = decoded / normalization
                return decoded

            else:
                return self.first_stage_model.encode(x)
        else:
            return self.first_stage_model.encode(x)

    def shared_step(self, batch, **kwargs):
        x, c = self.get_input(batch, self.first_stage_key)
        loss = self(x, c)
        return loss

    def forward(self, x, c, *args, **kwargs):
        t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
        if self.model.conditioning_key is not None:
            assert c is not None
            # if self.cond_stage_trainable:
            #     c = self.get_learned_conditioning(c)
            if self.shorten_cond_schedule:  # TODO: drop this option
                tc = self.cond_ids[t].to(self.device)
                c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
        return self.p_losses(x, c, t, *args, **kwargs)

    def _rescale_annotations(self, bboxes, crop_coordinates):  # TODO: move to dataset
        def rescale_bbox(bbox):
            x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
            y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
            w = min(bbox[2] / crop_coordinates[2], 1 - x0)
            h = min(bbox[3] / crop_coordinates[3], 1 - y0)
            return x0, y0, w, h

        return [rescale_bbox(b) for b in bboxes]

    def apply_model(self, x_noisy, t, cond, return_ids=False):

        if isinstance(cond, dict):
            # hybrid case, cond is exptected to be a dict
            pass
        else:
            if not isinstance(cond, list):
                cond = [cond]
            key = 'c_concat' if self.model.conditioning_key == 'concat' else 'c_crossattn'
            cond = {key: cond}

        if hasattr(self, "split_input_params"):
            assert len(cond) == 1  # todo can only deal with one conditioning atm
            assert not return_ids
            ks = self.split_input_params["ks"]  # eg. (128, 128)
            stride = self.split_input_params["stride"]  # eg. (64, 64)

            h, w = x_noisy.shape[-2:]

            fold, unfold, normalization, weighting = self.get_fold_unfold(x_noisy, ks, stride)

            z = unfold(x_noisy)  # (bn, nc * prod(**ks), L)
            # Reshape to img shape
            z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
            z_list = [z[:, :, :, :, i] for i in range(z.shape[-1])]

            if self.cond_stage_key in ["image", "LR_image", "segmentation",
                                       'bbox_img'] and self.model.conditioning_key:  # todo check for completeness
                c_key = next(iter(cond.keys()))  # get key
                c = next(iter(cond.values()))  # get value
                assert (len(c) == 1)  # todo extend to list with more than one elem
                c = c[0]  # get element

                c = unfold(c)
                c = c.view((c.shape[0], -1, ks[0], ks[1], c.shape[-1]))  # (bn, nc, ks[0], ks[1], L )

                cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]

            elif self.cond_stage_key == 'coordinates_bbox':
                assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'

                # assuming padding of unfold is always 0 and its dilation is always 1
                n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
                full_img_h, full_img_w = self.split_input_params['original_image_size']
                # as we are operating on latents, we need the factor from the original image size to the
                # spatial latent size to properly rescale the crops for regenerating the bbox annotations
                num_downs = self.first_stage_model.encoder.num_resolutions - 1
                rescale_latent = 2 ** (num_downs)

                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
                # need to rescale the tl patch coordinates to be in between (0,1)
                tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
                                         rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)
                                        for patch_nr in range(z.shape[-1])]

                # patch_limits are tl_coord, width and height coordinates as (x_tl, y_tl, h, w)
                patch_limits = [(x_tl, y_tl,
                                 rescale_latent * ks[0] / full_img_w,
                                 rescale_latent * ks[1] / full_img_h) for x_tl, y_tl in tl_patch_coordinates]
                # patch_values = [(np.arange(x_tl,min(x_tl+ks, 1.)),np.arange(y_tl,min(y_tl+ks, 1.))) for x_tl, y_tl in tl_patch_coordinates]

                # tokenize crop coordinates for the bounding boxes of the respective patches
                patch_limits_tknzd = [torch.LongTensor(self.bbox_tokenizer._crop_encoder(bbox))[None].to(self.device)
                                      for bbox in patch_limits]  # list of length l with tensors of shape (1, 2)
                # cut tknzd crop position from conditioning
                assert isinstance(cond, dict), 'cond must be dict to be fed into model'
                cut_cond = cond['c_crossattn'][0][..., :-2].to(self.device)

                adapted_cond = torch.stack([torch.cat([cut_cond, p], dim=1) for p in patch_limits_tknzd])
                adapted_cond = rearrange(adapted_cond, 'l b n -> (l b) n')
                adapted_cond = self.get_learned_conditioning(adapted_cond)
                adapted_cond = rearrange(adapted_cond, '(l b) n d -> l b n d', l=z.shape[-1])

                cond_list = [{'c_crossattn': [e]} for e in adapted_cond]

            else:
                cond_list = [cond for i in range(z.shape[-1])]  # Todo make this more efficient

            # apply model by loop over crops
            output_list = [self.model(z_list[i], t, **cond_list[i]) for i in range(z.shape[-1])]
            assert not isinstance(output_list[0],
                                  tuple)  # todo cant deal with multiple model outputs check this never happens

            o = torch.stack(output_list, axis=-1)
            o = o * weighting
            # Reverse reshape to img shape
            o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
            # stitch crops together
            x_recon = fold(o) / normalization

        else:
            x_recon = self.model(x_noisy, t, **cond)

        if isinstance(x_recon, tuple) and not return_ids:
            return x_recon[0]
        else:
            return x_recon

    def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
        return (extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t - pred_xstart) / \
               extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)

    def _prior_bpd(self, x_start):
        """
        Get the prior KL term for the variational lower-bound, measured in
        bits-per-dim.
        This term can't be optimized, as it only depends on the encoder.
        :param x_start: the [N x C x ...] tensor of inputs.
        :return: a batch of [N] KL values (in bits), one per batch element.
        """
        batch_size = x_start.shape[0]
        t = torch.tensor([self.num_timesteps - 1] * batch_size, device=x_start.device)
        qt_mean, _, qt_log_variance = self.q_mean_variance(x_start, t)
        kl_prior = normal_kl(mean1=qt_mean, logvar1=qt_log_variance, mean2=0.0, logvar2=0.0)
        return mean_flat(kl_prior) / np.log(2.0)

    def p_losses(self, x_start, cond, t, noise=None):
        noise = default(noise, lambda: torch.randn_like(x_start))
        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
        model_output = self.apply_model(x_noisy, t, cond)

        loss_dict = {}
        prefix = 'train' if self.training else 'val'

        if self.parameterization == "x0":
            target = x_start
        elif self.parameterization == "eps":
            target = noise
        else:
            raise NotImplementedError()

        loss_simple = self.get_loss(model_output, target, mean=False).mean([1, 2, 3])
        loss_dict.update({f'{prefix}/loss_simple': loss_simple.mean()})

        logvar_t = self.logvar[t].to(self.device)
        loss = loss_simple / torch.exp(logvar_t) + logvar_t
        # loss = loss_simple / torch.exp(self.logvar) + self.logvar
        if self.learn_logvar:
            loss_dict.update({f'{prefix}/loss_gamma': loss.mean()})
            loss_dict.update({'logvar': self.logvar.data.mean()})

        loss = self.l_simple_weight * loss.mean()

        loss_vlb = self.get_loss(model_output, target, mean=False).mean(dim=(1, 2, 3))
        loss_vlb = (self.lvlb_weights[t] * loss_vlb).mean()
        loss_dict.update({f'{prefix}/loss_vlb': loss_vlb})
        loss += (self.original_elbo_weight * loss_vlb)
        loss_dict.update({f'{prefix}/loss': loss})

        return loss, loss_dict

    def p_mean_variance(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
                        return_x0=False, score_corrector=None, corrector_kwargs=None):
        t_in = t
        model_out = self.apply_model(x, t_in, c, return_ids=return_codebook_ids)

        if score_corrector is not None:
            assert self.parameterization == "eps"
            model_out = score_corrector.modify_score(self, model_out, x, t, c, **corrector_kwargs)

        if return_codebook_ids:
            model_out, logits = model_out

        if self.parameterization == "eps":
            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
        elif self.parameterization == "x0":
            x_recon = model_out
        else:
            raise NotImplementedError()

        if clip_denoised:
            x_recon.clamp_(-1., 1.)
        if quantize_denoised:
            x_recon, _, [_, _, indices] = self.first_stage_model.quantize(x_recon)
        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
        if return_codebook_ids:
            return model_mean, posterior_variance, posterior_log_variance, logits
        elif return_x0:
            return model_mean, posterior_variance, posterior_log_variance, x_recon
        else:
            return model_mean, posterior_variance, posterior_log_variance

    @torch.no_grad()
    def p_sample(self, x, c, t, clip_denoised=False, repeat_noise=False,
                 return_codebook_ids=False, quantize_denoised=False, return_x0=False,
                 temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None):
        b, *_, device = *x.shape, x.device
        outputs = self.p_mean_variance(x=x, c=c, t=t, clip_denoised=clip_denoised,
                                       return_codebook_ids=return_codebook_ids,
                                       quantize_denoised=quantize_denoised,
                                       return_x0=return_x0,
                                       score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
        if return_codebook_ids:
            raise DeprecationWarning("Support dropped.")
            model_mean, _, model_log_variance, logits = outputs
        elif return_x0:
            model_mean, _, model_log_variance, x0 = outputs
        else:
            model_mean, _, model_log_variance = outputs

        noise = noise_like(x.shape, device, repeat_noise) * temperature
        if noise_dropout > 0.:
            noise = torch.nn.functional.dropout(noise, p=noise_dropout)
        # no noise when t == 0
        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))

        if return_codebook_ids:
            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, logits.argmax(dim=1)
        if return_x0:
            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, x0
        else:
            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise

    @torch.no_grad()
    def progressive_denoising(self, cond, shape, verbose=True, callback=None, quantize_denoised=False,
                              img_callback=None, mask=None, x0=None, temperature=1., noise_dropout=0.,
                              score_corrector=None, corrector_kwargs=None, batch_size=None, x_T=None, start_T=None,
                              log_every_t=None):
        if not log_every_t:
            log_every_t = self.log_every_t
        timesteps = self.num_timesteps
        if batch_size is not None:
            b = batch_size if batch_size is not None else shape[0]
            shape = [batch_size] + list(shape)
        else:
            b = batch_size = shape[0]
        if x_T is None:
            img = torch.randn(shape, device=self.device)
        else:
            img = x_T
        intermediates = []
        if cond is not None:
            if isinstance(cond, dict):
                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
            else:
                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]

        if start_T is not None:
            timesteps = min(timesteps, start_T)
        iterator = tqdm(reversed(range(0, timesteps)), desc='Progressive Generation',
                        total=timesteps) if verbose else reversed(
            range(0, timesteps))
        if type(temperature) == float:
            temperature = [temperature] * timesteps

        for i in iterator:
            ts = torch.full((b,), i, device=self.device, dtype=torch.long)
            if self.shorten_cond_schedule:
                assert self.model.conditioning_key != 'hybrid'
                tc = self.cond_ids[ts].to(cond.device)
                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))

            img, x0_partial = self.p_sample(img, cond, ts,
                                            clip_denoised=self.clip_denoised,
                                            quantize_denoised=quantize_denoised, return_x0=True,
                                            temperature=temperature[i], noise_dropout=noise_dropout,
                                            score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
            if mask is not None:
                assert x0 is not None
                img_orig = self.q_sample(x0, ts)
                img = img_orig * mask + (1. - mask) * img

            if i % log_every_t == 0 or i == timesteps - 1:
                intermediates.append(x0_partial)
            if callback: callback(i)
            if img_callback: img_callback(img, i)
        return img, intermediates

    @torch.no_grad()
    def p_sample_loop(self, cond, shape, return_intermediates=False,
                      x_T=None, verbose=True, callback=None, timesteps=None, quantize_denoised=False,
                      mask=None, x0=None, img_callback=None, start_T=None,
                      log_every_t=None):

        if not log_every_t:
            log_every_t = self.log_every_t
        device = self.betas.device
        b = shape[0]
        if x_T is None:
            img = torch.randn(shape, device=device)
        else:
            img = x_T

        intermediates = [img]
        if timesteps is None:
            timesteps = self.num_timesteps

        if start_T is not None:
            timesteps = min(timesteps, start_T)
        iterator = tqdm(reversed(range(0, timesteps)), desc='Sampling t', total=timesteps) if verbose else reversed(
            range(0, timesteps))

        if mask is not None:
            assert x0 is not None
            assert x0.shape[2:3] == mask.shape[2:3]  # spatial size has to match

        for i in iterator:
            ts = torch.full((b,), i, device=device, dtype=torch.long)
            if self.shorten_cond_schedule:
                assert self.model.conditioning_key != 'hybrid'
                tc = self.cond_ids[ts].to(cond.device)
                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))

            img = self.p_sample(img, cond, ts,
                                clip_denoised=self.clip_denoised,
                                quantize_denoised=quantize_denoised)
            if mask is not None:
                img_orig = self.q_sample(x0, ts)
                img = img_orig * mask + (1. - mask) * img

            if i % log_every_t == 0 or i == timesteps - 1:
                intermediates.append(img)
            if callback: callback(i)
            if img_callback: img_callback(img, i)

        if return_intermediates:
            return img, intermediates
        return img

    @torch.no_grad()
    def sample(self, cond, batch_size=16, return_intermediates=False, x_T=None,
               verbose=True, timesteps=None, quantize_denoised=False,
               mask=None, x0=None, shape=None,**kwargs):
        if shape is None:
            shape = (batch_size, self.channels, self.image_size, self.image_size)
        if cond is not None:
            if isinstance(cond, dict):
                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
            else:
                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
        return self.p_sample_loop(cond,
                                  shape,
                                  return_intermediates=return_intermediates, x_T=x_T,
                                  verbose=verbose, timesteps=timesteps, quantize_denoised=quantize_denoised,
                                  mask=mask, x0=x0)

    @torch.no_grad()
    def sample_log(self, cond, batch_size, ddim, ddim_steps, **kwargs):
        if ddim:
            ddim_sampler = DDIMSampler(self)
            shape = (self.channels, self.image_size, self.image_size)
            samples, intermediates = ddim_sampler.sample(ddim_steps, batch_size,
                                                         shape, cond, verbose=False, **kwargs)

        else:
            samples, intermediates = self.sample(cond=cond, batch_size=batch_size,
                                                 return_intermediates=True, **kwargs)

        return samples, intermediates

    @torch.no_grad()
    def get_unconditional_conditioning(self, batch_size, null_label=None, image_size=512):
        if null_label is not None:
            xc = null_label
            if isinstance(xc, ListConfig):
                xc = list(xc)
            if isinstance(xc, dict) or isinstance(xc, list):
                c = self.get_learned_conditioning(xc)
            else:
                if hasattr(xc, "to"):
                    xc = xc.to(self.device)
                c = self.get_learned_conditioning(xc)
        else:
            # todo: get null label from cond_stage_model
            raise NotImplementedError()
        c = repeat(c, '1 ... -> b ...', b=batch_size).to(self.device)
        cond = {}
        cond["c_crossattn"] = [c]
        cond["c_concat"] = [torch.zeros([batch_size, 4, image_size // 8, image_size // 8]).to(self.device)]
        return cond

    @torch.no_grad()
    def log_images(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
                   quantize_denoised=True, inpaint=True, plot_denoise_rows=False, plot_progressive_rows=True,
                   plot_diffusion_rows=True, unconditional_guidance_scale=1., unconditional_guidance_label=None,
                   use_ema_scope=True,
                   **kwargs):
        ema_scope = self.ema_scope if use_ema_scope else nullcontext
        use_ddim = ddim_steps is not None

        log = dict()
        z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
                                           return_first_stage_outputs=True,
                                           force_c_encode=True,
                                           return_original_cond=True,
                                           bs=N)
        N = min(x.shape[0], N)
        n_row = min(x.shape[0], n_row)
        log["inputs"] = x
        log["reconstruction"] = xrec
        if self.model.conditioning_key is not None:
            if hasattr(self.cond_stage_model, "decode"):
                xc = self.cond_stage_model.decode(c)
                log["conditioning"] = xc
            elif self.cond_stage_key in ["caption", "txt"]:
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch[self.cond_stage_key], size=x.shape[2]//25)
                log["conditioning"] = xc
            elif self.cond_stage_key == 'class_label':
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"], size=x.shape[2]//25)
                log['conditioning'] = xc
            elif isimage(xc):
                log["conditioning"] = xc
            if ismap(xc):
                log["original_conditioning"] = self.to_rgb(xc)

        if plot_diffusion_rows:
            # get diffusion row
            diffusion_row = list()
            z_start = z[:n_row]
            for t in range(self.num_timesteps):
                if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
                    t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
                    t = t.to(self.device).long()
                    noise = torch.randn_like(z_start)
                    z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
                    diffusion_row.append(self.decode_first_stage(z_noisy))

            diffusion_row = torch.stack(diffusion_row)  # n_log_step, n_row, C, H, W
            diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
            diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
            diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
            log["diffusion_row"] = diffusion_grid

        if sample:
            # get denoise row
            with ema_scope("Sampling"):
                samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
                                                         ddim_steps=ddim_steps,eta=ddim_eta)
                # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
            x_samples = self.decode_first_stage(samples)
            log["samples"] = x_samples
            if plot_denoise_rows:
                denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
                log["denoise_row"] = denoise_grid

            if quantize_denoised and not isinstance(self.first_stage_model, AutoencoderKL) and not isinstance(
                    self.first_stage_model, IdentityFirstStage):
                # also display when quantizing x0 while sampling
                with ema_scope("Plotting Quantized Denoised"):
                    samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
                                                             ddim_steps=ddim_steps,eta=ddim_eta,
                                                             quantize_denoised=True)
                    # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True,
                    #                                      quantize_denoised=True)
                x_samples = self.decode_first_stage(samples.to(self.device))
                log["samples_x0_quantized"] = x_samples

        if unconditional_guidance_scale > 1.0:
            uc = self.get_unconditional_conditioning(N, unconditional_guidance_label, image_size=x.shape[-1])
            # uc = torch.zeros_like(c)
            with ema_scope("Sampling with classifier-free guidance"):
                samples_cfg, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,
                                                 ddim_steps=ddim_steps, eta=ddim_eta,
                                                 unconditional_guidance_scale=unconditional_guidance_scale,
                                                 unconditional_conditioning=uc,
                                                 )
                x_samples_cfg = self.decode_first_stage(samples_cfg)
                log[f"samples_cfg_scale_{unconditional_guidance_scale:.2f}"] = x_samples_cfg

        if inpaint:
            # make a simple center square
            b, h, w = z.shape[0], z.shape[2], z.shape[3]
            mask = torch.ones(N, h, w).to(self.device)
            # zeros will be filled in
            mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
            mask = mask[:, None, ...]
            with ema_scope("Plotting Inpaint"):

                samples, _ = self.sample_log(cond=c,batch_size=N,ddim=use_ddim, eta=ddim_eta,
                                            ddim_steps=ddim_steps, x0=z[:N], mask=mask)
            x_samples = self.decode_first_stage(samples.to(self.device))
            log["samples_inpainting"] = x_samples
            log["mask"] = mask

            # outpaint
            mask = 1. - mask
            with ema_scope("Plotting Outpaint"):
                samples, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,eta=ddim_eta,
                                            ddim_steps=ddim_steps, x0=z[:N], mask=mask)
            x_samples = self.decode_first_stage(samples.to(self.device))
            log["samples_outpainting"] = x_samples

        if plot_progressive_rows:
            with ema_scope("Plotting Progressives"):
                img, progressives = self.progressive_denoising(c,
                                                               shape=(self.channels, self.image_size, self.image_size),
                                                               batch_size=N)
            prog_row = self._get_denoise_row_from_list(progressives, desc="Progressive Generation")
            log["progressive_row"] = prog_row

        if return_keys:
            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
                return log
            else:
                return {key: log[key] for key in return_keys}
        return log

    def configure_optimizers(self):
        lr = self.learning_rate
        params = []
        if self.unet_trainable == "attn":
            print("Training only unet attention layers")
            for n, m in self.model.named_modules():
                if isinstance(m, CrossAttention) and n.endswith('attn2'):
                    params.extend(m.parameters())
        if self.unet_trainable == "conv_in":
            print("Training only unet input conv layers")
            params = list(self.model.diffusion_model.input_blocks[0][0].parameters())
        elif self.unet_trainable is True or self.unet_trainable == "all":
            print("Training the full unet")
            params = list(self.model.parameters())
        else:
            raise ValueError(f"Unrecognised setting for unet_trainable: {self.unet_trainable}")

        if self.cond_stage_trainable:
            print(f"{self.__class__.__name__}: Also optimizing conditioner params!")
            params = params + list(self.cond_stage_model.parameters())
        if self.learn_logvar:
            print('Diffusion model optimizing logvar')
            params.append(self.logvar)

        if self.cc_projection is not None:
            params = params + list(self.cc_projection.parameters())
            print('========== optimizing for cc projection weight ==========')

        opt = torch.optim.AdamW([{"params": self.model.parameters(), "lr": lr},
                                {"params": self.cc_projection.parameters(), "lr": 10. * lr}], lr=lr)
        if self.use_scheduler:
            assert 'target' in self.scheduler_config
            scheduler = instantiate_from_config(self.scheduler_config)

            print("Setting up LambdaLR scheduler...")
            scheduler = [
                {
                    'scheduler': LambdaLR(opt, lr_lambda=scheduler.schedule),
                    'interval': 'step',
                    'frequency': 1
                }]
            return [opt], scheduler
        return opt

    @torch.no_grad()
    def to_rgb(self, x):
        x = x.float()
        if not hasattr(self, "colorize"):
            self.colorize = torch.randn(3, x.shape[1], 1, 1).to(x)
        x = nn.functional.conv2d(x, weight=self.colorize)
        x = 2. * (x - x.min()) / (x.max() - x.min()) - 1.
        return x


class DiffusionWrapper(pl.LightningModule):
    def __init__(self, diff_model_config, conditioning_key):
        super().__init__()
        self.diffusion_model = instantiate_from_config(diff_model_config)
        self.conditioning_key = conditioning_key
        assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm', 'hybrid-adm']

    def forward(self, x, t, c_concat: list = None, c_crossattn: list = None, c_adm=None):
        if self.conditioning_key is None:
            out = self.diffusion_model(x, t)
        elif self.conditioning_key == 'concat':
            xc = torch.cat([x] + c_concat, dim=1)
            out = self.diffusion_model(xc, t)
        elif self.conditioning_key == 'crossattn':
            # c_crossattn dimension:  torch.Size([8, 1, 768]) 1
            # cc dimension:  torch.Size([8, 1, 768]
            cc = torch.cat(c_crossattn, 1)
            out = self.diffusion_model(x, t, context=cc)
        elif self.conditioning_key == 'hybrid':
            xc = torch.cat([x] + c_concat, dim=1)
            cc = torch.cat(c_crossattn, 1)
            out = self.diffusion_model(xc, t, context=cc)
        elif self.conditioning_key == 'hybrid-adm':
            assert c_adm is not None
            xc = torch.cat([x] + c_concat, dim=1)
            cc = torch.cat(c_crossattn, 1)
            out = self.diffusion_model(xc, t, context=cc, y=c_adm)
        elif self.conditioning_key == 'adm':
            cc = c_crossattn[0]
            out = self.diffusion_model(x, t, y=cc)
        else:
            raise NotImplementedError()

        return out


class LatentUpscaleDiffusion(LatentDiffusion):
    def __init__(self, *args, low_scale_config, low_scale_key="LR", **kwargs):
        super().__init__(*args, **kwargs)
        # assumes that neither the cond_stage nor the low_scale_model contain trainable params
        assert not self.cond_stage_trainable
        self.instantiate_low_stage(low_scale_config)
        self.low_scale_key = low_scale_key

    def instantiate_low_stage(self, config):
        model = instantiate_from_config(config)
        self.low_scale_model = model.eval()
        self.low_scale_model.train = disabled_train
        for param in self.low_scale_model.parameters():
            param.requires_grad = False

    @torch.no_grad()
    def get_input(self, batch, k, cond_key=None, bs=None, log_mode=False):
        if not log_mode:
            z, c = super().get_input(batch, k, force_c_encode=True, bs=bs)
        else:
            z, c, x, xrec, xc = super().get_input(batch, self.first_stage_key, return_first_stage_outputs=True,
                                                  force_c_encode=True, return_original_cond=True, bs=bs)
        x_low = batch[self.low_scale_key][:bs]
        x_low = rearrange(x_low, 'b h w c -> b c h w')
        x_low = x_low.to(memory_format=torch.contiguous_format).float()
        zx, noise_level = self.low_scale_model(x_low)
        all_conds = {"c_concat": [zx], "c_crossattn": [c], "c_adm": noise_level}
        #import pudb; pu.db
        if log_mode:
            # TODO: maybe disable if too expensive
            interpretability = False
            if interpretability:
                zx = zx[:, :, ::2, ::2]
            x_low_rec = self.low_scale_model.decode(zx)
            return z, all_conds, x, xrec, xc, x_low, x_low_rec, noise_level
        return z, all_conds

    @torch.no_grad()
    def log_images(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
                   plot_denoise_rows=False, plot_progressive_rows=True, plot_diffusion_rows=True,
                   unconditional_guidance_scale=1., unconditional_guidance_label=None, use_ema_scope=True,
                   **kwargs):
        ema_scope = self.ema_scope if use_ema_scope else nullcontext
        use_ddim = ddim_steps is not None

        log = dict()
        z, c, x, xrec, xc, x_low, x_low_rec, noise_level = self.get_input(batch, self.first_stage_key, bs=N,
                                                                          log_mode=True)
        N = min(x.shape[0], N)
        n_row = min(x.shape[0], n_row)
        log["inputs"] = x
        log["reconstruction"] = xrec
        log["x_lr"] = x_low
        log[f"x_lr_rec_@noise_levels{'-'.join(map(lambda x: str(x), list(noise_level.cpu().numpy())))}"] = x_low_rec
        if self.model.conditioning_key is not None:
            if hasattr(self.cond_stage_model, "decode"):
                xc = self.cond_stage_model.decode(c)
                log["conditioning"] = xc
            elif self.cond_stage_key in ["caption", "txt"]:
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch[self.cond_stage_key], size=x.shape[2]//25)
                log["conditioning"] = xc
            elif self.cond_stage_key == 'class_label':
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"], size=x.shape[2]//25)
                log['conditioning'] = xc
            elif isimage(xc):
                log["conditioning"] = xc
            if ismap(xc):
                log["original_conditioning"] = self.to_rgb(xc)

        if plot_diffusion_rows:
            # get diffusion row
            diffusion_row = list()
            z_start = z[:n_row]
            for t in range(self.num_timesteps):
                if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
                    t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
                    t = t.to(self.device).long()
                    noise = torch.randn_like(z_start)
                    z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
                    diffusion_row.append(self.decode_first_stage(z_noisy))

            diffusion_row = torch.stack(diffusion_row)  # n_log_step, n_row, C, H, W
            diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
            diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
            diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
            log["diffusion_row"] = diffusion_grid

        if sample:
            # get denoise row
            with ema_scope("Sampling"):
                samples, z_denoise_row = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,
                                                         ddim_steps=ddim_steps, eta=ddim_eta)
                # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
            x_samples = self.decode_first_stage(samples)
            log["samples"] = x_samples
            if plot_denoise_rows:
                denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
                log["denoise_row"] = denoise_grid

        if unconditional_guidance_scale > 1.0:
            uc_tmp = self.get_unconditional_conditioning(N, unconditional_guidance_label)
            # TODO explore better "unconditional" choices for the other keys
            # maybe guide away from empty text label and highest noise level and maximally degraded zx?
            uc = dict()
            for k in c:
                if k == "c_crossattn":
                    assert isinstance(c[k], list) and len(c[k]) == 1
                    uc[k] = [uc_tmp]
                elif k == "c_adm":  # todo: only run with text-based guidance?
                    assert isinstance(c[k], torch.Tensor)
                    uc[k] = torch.ones_like(c[k]) * self.low_scale_model.max_noise_level
                elif isinstance(c[k], list):
                    uc[k] = [c[k][i] for i in range(len(c[k]))]
                else:
                    uc[k] = c[k]

            with ema_scope("Sampling with classifier-free guidance"):
                samples_cfg, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,
                                                 ddim_steps=ddim_steps, eta=ddim_eta,
                                                 unconditional_guidance_scale=unconditional_guidance_scale,
                                                 unconditional_conditioning=uc,
                                                 )
                x_samples_cfg = self.decode_first_stage(samples_cfg)
                log[f"samples_cfg_scale_{unconditional_guidance_scale:.2f}"] = x_samples_cfg

        if plot_progressive_rows:
            with ema_scope("Plotting Progressives"):
                img, progressives = self.progressive_denoising(c,
                                                               shape=(self.channels, self.image_size, self.image_size),
                                                               batch_size=N)
            prog_row = self._get_denoise_row_from_list(progressives, desc="Progressive Generation")
            log["progressive_row"] = prog_row

        return log


class LatentInpaintDiffusion(LatentDiffusion):
    """
    can either run as pure inpainting model (only concat mode) or with mixed conditionings,
    e.g. mask as concat and text via cross-attn.
    To disable finetuning mode, set finetune_keys to None
     """
    def __init__(self,
                 finetune_keys=("model.diffusion_model.input_blocks.0.0.weight",
                                "model_ema.diffusion_modelinput_blocks00weight"
                                ),
                 concat_keys=("mask", "masked_image"),
                 masked_image_key="masked_image",
                 keep_finetune_dims=4,  # if model was trained without concat mode before and we would like to keep these channels
                 c_concat_log_start=None, # to log reconstruction of c_concat codes
                 c_concat_log_end=None,
                 *args, **kwargs
                 ):
        ckpt_path = kwargs.pop("ckpt_path", None)
        ignore_keys = kwargs.pop("ignore_keys", list())
        super().__init__(*args, **kwargs)
        self.masked_image_key = masked_image_key
        assert self.masked_image_key in concat_keys
        self.finetune_keys = finetune_keys
        self.concat_keys = concat_keys
        self.keep_dims = keep_finetune_dims
        self.c_concat_log_start = c_concat_log_start
        self.c_concat_log_end = c_concat_log_end
        if exists(self.finetune_keys): assert exists(ckpt_path), 'can only finetune from a given checkpoint'
        if exists(ckpt_path):
            self.init_from_ckpt(ckpt_path, ignore_keys)

    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
        sd = torch.load(path, map_location="cpu")
        if "state_dict" in list(sd.keys()):
            sd = sd["state_dict"]
        keys = list(sd.keys())
        for k in keys:
            for ik in ignore_keys:
                if k.startswith(ik):
                    print("Deleting key {} from state_dict.".format(k))
                    del sd[k]

            # make it explicit, finetune by including extra input channels
            if exists(self.finetune_keys) and k in self.finetune_keys:
                new_entry = None
                for name, param in self.named_parameters():
                    if name in self.finetune_keys:
                        print(f"modifying key '{name}' and keeping its original {self.keep_dims} (channels) dimensions only")
                        new_entry = torch.zeros_like(param)  # zero init
                assert exists(new_entry), 'did not find matching parameter to modify'
                new_entry[:, :self.keep_dims, ...] = sd[k]
                sd[k] = new_entry

        missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(sd, strict=False)
        print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
        if len(missing) > 0:
            print(f"Missing Keys: {missing}")
        if len(unexpected) > 0:
            print(f"Unexpected Keys: {unexpected}")

    @torch.no_grad()
    def get_input(self, batch, k, cond_key=None, bs=None, return_first_stage_outputs=False):
        # note: restricted to non-trainable encoders currently
        assert not self.cond_stage_trainable, 'trainable cond stages not yet supported for inpainting'
        z, c, x, xrec, xc = super().get_input(batch, self.first_stage_key, return_first_stage_outputs=True,
                                              force_c_encode=True, return_original_cond=True, bs=bs)

        assert exists(self.concat_keys)
        c_cat = list()
        for ck in self.concat_keys:
            cc = rearrange(batch[ck], 'b h w c -> b c h w').to(memory_format=torch.contiguous_format).float()
            if bs is not None:
                cc = cc[:bs]
                cc = cc.to(self.device)
            bchw = z.shape
            if ck != self.masked_image_key:
                cc = torch.nn.functional.interpolate(cc, size=bchw[-2:])
            else:
                cc = self.get_first_stage_encoding(self.encode_first_stage(cc))
            c_cat.append(cc)
        c_cat = torch.cat(c_cat, dim=1)
        all_conds = {"c_concat": [c_cat], "c_crossattn": [c]}
        if return_first_stage_outputs:
            return z, all_conds, x, xrec, xc
        return z, all_conds

    @torch.no_grad()
    def log_images(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
                   quantize_denoised=True, inpaint=True, plot_denoise_rows=False, plot_progressive_rows=True,
                   plot_diffusion_rows=True, unconditional_guidance_scale=1., unconditional_guidance_label=None,
                   use_ema_scope=True,
                   **kwargs):
        ema_scope = self.ema_scope if use_ema_scope else nullcontext
        use_ddim = ddim_steps is not None

        log = dict()
        z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key, bs=N, return_first_stage_outputs=True)
        c_cat, c = c["c_concat"][0], c["c_crossattn"][0]
        N = min(x.shape[0], N)
        n_row = min(x.shape[0], n_row)
        log["inputs"] = x
        log["reconstruction"] = xrec
        if self.model.conditioning_key is not None:
            if hasattr(self.cond_stage_model, "decode"):
                xc = self.cond_stage_model.decode(c)
                log["conditioning"] = xc
            elif self.cond_stage_key in ["caption", "txt"]:
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch[self.cond_stage_key], size=x.shape[2] // 25)
                log["conditioning"] = xc
            elif self.cond_stage_key == 'class_label':
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"], size=x.shape[2] // 25)
                log['conditioning'] = xc
            elif isimage(xc):
                log["conditioning"] = xc
            if ismap(xc):
                log["original_conditioning"] = self.to_rgb(xc)

        if not (self.c_concat_log_start is None and self.c_concat_log_end is None):
            log["c_concat_decoded"] = self.decode_first_stage(c_cat[:,self.c_concat_log_start:self.c_concat_log_end])

        if plot_diffusion_rows:
            # get diffusion row
            diffusion_row = list()
            z_start = z[:n_row]
            for t in range(self.num_timesteps):
                if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
                    t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
                    t = t.to(self.device).long()
                    noise = torch.randn_like(z_start)
                    z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
                    diffusion_row.append(self.decode_first_stage(z_noisy))

            diffusion_row = torch.stack(diffusion_row)  # n_log_step, n_row, C, H, W
            diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
            diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
            diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
            log["diffusion_row"] = diffusion_grid

        if sample:
            # get denoise row
            with ema_scope("Sampling"):
                samples, z_denoise_row = self.sample_log(cond={"c_concat": [c_cat], "c_crossattn": [c]},
                                                         batch_size=N, ddim=use_ddim,
                                                         ddim_steps=ddim_steps, eta=ddim_eta)
                # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
            x_samples = self.decode_first_stage(samples)
            log["samples"] = x_samples
            if plot_denoise_rows:
                denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
                log["denoise_row"] = denoise_grid

        if unconditional_guidance_scale > 1.0:
            uc_cross = self.get_unconditional_conditioning(N, unconditional_guidance_label)
            uc_cat = c_cat
            uc_full = {"c_concat": [uc_cat], "c_crossattn": [uc_cross]}
            with ema_scope("Sampling with classifier-free guidance"):
                samples_cfg, _ = self.sample_log(cond={"c_concat": [c_cat], "c_crossattn": [c]},
                                                 batch_size=N, ddim=use_ddim,
                                                 ddim_steps=ddim_steps, eta=ddim_eta,
                                                 unconditional_guidance_scale=unconditional_guidance_scale,
                                                 unconditional_conditioning=uc_full,
                                                 )
                x_samples_cfg = self.decode_first_stage(samples_cfg)
                log[f"samples_cfg_scale_{unconditional_guidance_scale:.2f}"] = x_samples_cfg

        log["masked_image"] = rearrange(batch["masked_image"],
                                        'b h w c -> b c h w').to(memory_format=torch.contiguous_format).float()
        return log


class Layout2ImgDiffusion(LatentDiffusion):
    # TODO: move all layout-specific hacks to this class
    def __init__(self, cond_stage_key, *args, **kwargs):
        assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
        super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)

    def log_images(self, batch, N=8, *args, **kwargs):
        logs = super().log_images(batch=batch, N=N, *args, **kwargs)

        key = 'train' if self.training else 'validation'
        dset = self.trainer.datamodule.datasets[key]
        mapper = dset.conditional_builders[self.cond_stage_key]

        bbox_imgs = []
        map_fn = lambda catno: dset.get_textual_label(dset.get_category_id(catno))
        for tknzd_bbox in batch[self.cond_stage_key][:N]:
            bboximg = mapper.plot(tknzd_bbox.detach().cpu(), map_fn, (256, 256))
            bbox_imgs.append(bboximg)

        cond_img = torch.stack(bbox_imgs, dim=0)
        logs['bbox_image'] = cond_img
        return logs


class SimpleUpscaleDiffusion(LatentDiffusion):
    def __init__(self, *args, low_scale_key="LR", **kwargs):
        super().__init__(*args, **kwargs)
        # assumes that neither the cond_stage nor the low_scale_model contain trainable params
        assert not self.cond_stage_trainable
        self.low_scale_key = low_scale_key

    @torch.no_grad()
    def get_input(self, batch, k, cond_key=None, bs=None, log_mode=False):
        if not log_mode:
            z, c = super().get_input(batch, k, force_c_encode=True, bs=bs)
        else:
            z, c, x, xrec, xc = super().get_input(batch, self.first_stage_key, return_first_stage_outputs=True,
                                                  force_c_encode=True, return_original_cond=True, bs=bs)
        x_low = batch[self.low_scale_key][:bs]
        x_low = rearrange(x_low, 'b h w c -> b c h w')
        x_low = x_low.to(memory_format=torch.contiguous_format).float()

        encoder_posterior = self.encode_first_stage(x_low)
        zx = self.get_first_stage_encoding(encoder_posterior).detach()
        all_conds = {"c_concat": [zx], "c_crossattn": [c]}

        if log_mode:
            # TODO: maybe disable if too expensive
            interpretability = False
            if interpretability:
                zx = zx[:, :, ::2, ::2]
            return z, all_conds, x, xrec, xc, x_low
        return z, all_conds

    @torch.no_grad()
    def log_images(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
                   plot_denoise_rows=False, plot_progressive_rows=True, plot_diffusion_rows=True,
                   unconditional_guidance_scale=1., unconditional_guidance_label=None, use_ema_scope=True,
                   **kwargs):
        ema_scope = self.ema_scope if use_ema_scope else nullcontext
        use_ddim = ddim_steps is not None

        log = dict()
        z, c, x, xrec, xc, x_low = self.get_input(batch, self.first_stage_key, bs=N, log_mode=True)
        N = min(x.shape[0], N)
        n_row = min(x.shape[0], n_row)
        log["inputs"] = x
        log["reconstruction"] = xrec
        log["x_lr"] = x_low

        if self.model.conditioning_key is not None:
            if hasattr(self.cond_stage_model, "decode"):
                xc = self.cond_stage_model.decode(c)
                log["conditioning"] = xc
            elif self.cond_stage_key in ["caption", "txt"]:
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch[self.cond_stage_key], size=x.shape[2]//25)
                log["conditioning"] = xc
            elif self.cond_stage_key == 'class_label':
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"], size=x.shape[2]//25)
                log['conditioning'] = xc
            elif isimage(xc):
                log["conditioning"] = xc
            if ismap(xc):
                log["original_conditioning"] = self.to_rgb(xc)

        if sample:
            # get denoise row
            with ema_scope("Sampling"):
                samples, z_denoise_row = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,
                                                         ddim_steps=ddim_steps, eta=ddim_eta)
                # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
            x_samples = self.decode_first_stage(samples)
            log["samples"] = x_samples

        if unconditional_guidance_scale > 1.0:
            uc_tmp = self.get_unconditional_conditioning(N, unconditional_guidance_label)
            uc = dict()
            for k in c:
                if k == "c_crossattn":
                    assert isinstance(c[k], list) and len(c[k]) == 1
                    uc[k] = [uc_tmp]
                elif isinstance(c[k], list):
                    uc[k] = [c[k][i] for i in range(len(c[k]))]
                else:
                    uc[k] = c[k]

            with ema_scope("Sampling with classifier-free guidance"):
                samples_cfg, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,
                                                 ddim_steps=ddim_steps, eta=ddim_eta,
                                                 unconditional_guidance_scale=unconditional_guidance_scale,
                                                 unconditional_conditioning=uc,
                                                 )
                x_samples_cfg = self.decode_first_stage(samples_cfg)
                log[f"samples_cfg_scale_{unconditional_guidance_scale:.2f}"] = x_samples_cfg
        return log

class MultiCatFrameDiffusion(LatentDiffusion):
    def __init__(self, *args, low_scale_key="LR", **kwargs):
        super().__init__(*args, **kwargs)
        # assumes that neither the cond_stage nor the low_scale_model contain trainable params
        assert not self.cond_stage_trainable
        self.low_scale_key = low_scale_key

    @torch.no_grad()
    def get_input(self, batch, k, cond_key=None, bs=None, log_mode=False):
        n = 2
        if not log_mode:
            z, c = super().get_input(batch, k, force_c_encode=True, bs=bs)
        else:
            z, c, x, xrec, xc = super().get_input(batch, self.first_stage_key, return_first_stage_outputs=True,
                                                  force_c_encode=True, return_original_cond=True, bs=bs)
        cat_conds = batch[self.low_scale_key][:bs]
        cats = []
        for i in range(n):
            x_low = cat_conds[:,:,:,3*i:3*(i+1)]
            x_low = rearrange(x_low, 'b h w c -> b c h w')
            x_low = x_low.to(memory_format=torch.contiguous_format).float()
            encoder_posterior = self.encode_first_stage(x_low)
            zx = self.get_first_stage_encoding(encoder_posterior).detach()
            cats.append(zx)

        all_conds = {"c_concat": [torch.cat(cats, dim=1)], "c_crossattn": [c]}

        if log_mode:
            # TODO: maybe disable if too expensive
            interpretability = False
            if interpretability:
                zx = zx[:, :, ::2, ::2]
            return z, all_conds, x, xrec, xc, x_low
        return z, all_conds

    @torch.no_grad()
    def log_images(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
                   plot_denoise_rows=False, plot_progressive_rows=True, plot_diffusion_rows=True,
                   unconditional_guidance_scale=1., unconditional_guidance_label=None, use_ema_scope=True,
                   **kwargs):
        ema_scope = self.ema_scope if use_ema_scope else nullcontext
        use_ddim = ddim_steps is not None

        log = dict()
        z, c, x, xrec, xc, x_low = self.get_input(batch, self.first_stage_key, bs=N, log_mode=True)
        N = min(x.shape[0], N)
        n_row = min(x.shape[0], n_row)
        log["inputs"] = x
        log["reconstruction"] = xrec
        log["x_lr"] = x_low

        if self.model.conditioning_key is not None:
            if hasattr(self.cond_stage_model, "decode"):
                xc = self.cond_stage_model.decode(c)
                log["conditioning"] = xc
            elif self.cond_stage_key in ["caption", "txt"]:
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch[self.cond_stage_key], size=x.shape[2]//25)
                log["conditioning"] = xc
            elif self.cond_stage_key == 'class_label':
                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"], size=x.shape[2]//25)
                log['conditioning'] = xc
            elif isimage(xc):
                log["conditioning"] = xc
            if ismap(xc):
                log["original_conditioning"] = self.to_rgb(xc)

        if sample:
            # get denoise row
            with ema_scope("Sampling"):
                samples, z_denoise_row = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,
                                                         ddim_steps=ddim_steps, eta=ddim_eta)
                # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
            x_samples = self.decode_first_stage(samples)
            log["samples"] = x_samples

        if unconditional_guidance_scale > 1.0:
            uc_tmp = self.get_unconditional_conditioning(N, unconditional_guidance_label)
            uc = dict()
            for k in c:
                if k == "c_crossattn":
                    assert isinstance(c[k], list) and len(c[k]) == 1
                    uc[k] = [uc_tmp]
                elif isinstance(c[k], list):
                    uc[k] = [c[k][i] for i in range(len(c[k]))]
                else:
                    uc[k] = c[k]

            with ema_scope("Sampling with classifier-free guidance"):
                samples_cfg, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,
                                                 ddim_steps=ddim_steps, eta=ddim_eta,
                                                 unconditional_guidance_scale=unconditional_guidance_scale,
                                                 unconditional_conditioning=uc,
                                                 )
                x_samples_cfg = self.decode_first_stage(samples_cfg)
                log[f"samples_cfg_scale_{unconditional_guidance_scale:.2f}"] = x_samples_cfg
        return log