Hugging Face's logo

Spaces:
chansung
/
auto-diffuser-config
Running

App Files Community
auto-diffuser-config
File size: 120,938 Bytes 
aae35f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
2025-05-29 14:50:28,409 - __main__ - INFO - Initializing GradioAutodiffusers
2025-05-29 14:50:28,409 - __main__ - DEBUG - API key found, length: 39
2025-05-29 14:50:28,409 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
2025-05-29 14:50:28,409 - auto_diffusers - DEBUG - API key length: 39
2025-05-29 14:50:28,409 - auto_diffusers - INFO - Successfully configured Gemini AI model
2025-05-29 14:50:28,409 - hardware_detector - INFO - Initializing HardwareDetector
2025-05-29 14:50:28,409 - hardware_detector - DEBUG - Starting system hardware detection
2025-05-29 14:50:28,409 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
2025-05-29 14:50:28,409 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
2025-05-29 14:50:28,409 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
2025-05-29 14:50:28,413 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
2025-05-29 14:50:28,413 - hardware_detector - DEBUG - Checking PyTorch availability
2025-05-29 14:50:28,856 - hardware_detector - INFO - PyTorch 2.7.0 detected
2025-05-29 14:50:28,856 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
2025-05-29 14:50:28,856 - hardware_detector - INFO - Hardware detection completed successfully
2025-05-29 14:50:28,856 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
2025-05-29 14:50:28,856 - auto_diffusers - INFO - Hardware detector initialized successfully
2025-05-29 14:50:28,856 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
2025-05-29 14:50:28,856 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
2025-05-29 14:50:28,856 - simple_memory_calculator - DEBUG - HuggingFace API initialized
2025-05-29 14:50:28,856 - __main__ - ERROR - Failed to initialize SimpleMemoryCalculator: 'SimpleMemoryCalculator' object has no attribute 'known_models'
2025-05-29 14:52:16,109 - __main__ - INFO - Initializing GradioAutodiffusers
2025-05-29 14:52:16,109 - __main__ - DEBUG - API key found, length: 39
2025-05-29 14:52:16,109 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
2025-05-29 14:52:16,109 - auto_diffusers - DEBUG - API key length: 39
2025-05-29 14:52:16,109 - auto_diffusers - INFO - Successfully configured Gemini AI model
2025-05-29 14:52:16,109 - hardware_detector - INFO - Initializing HardwareDetector
2025-05-29 14:52:16,109 - hardware_detector - DEBUG - Starting system hardware detection
2025-05-29 14:52:16,109 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
2025-05-29 14:52:16,109 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
2025-05-29 14:52:16,109 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
2025-05-29 14:52:16,113 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
2025-05-29 14:52:16,113 - hardware_detector - DEBUG - Checking PyTorch availability
2025-05-29 14:52:16,551 - hardware_detector - INFO - PyTorch 2.7.0 detected
2025-05-29 14:52:16,551 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
2025-05-29 14:52:16,551 - hardware_detector - INFO - Hardware detection completed successfully
2025-05-29 14:52:16,551 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
2025-05-29 14:52:16,551 - auto_diffusers - INFO - Hardware detector initialized successfully
2025-05-29 14:52:16,551 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
2025-05-29 14:52:16,551 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
2025-05-29 14:52:16,551 - simple_memory_calculator - DEBUG - HuggingFace API initialized
2025-05-29 14:52:16,551 - simple_memory_calculator - DEBUG - Known models in database: 4
2025-05-29 14:52:16,551 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
2025-05-29 14:52:16,551 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
2025-05-29 14:52:16,553 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 14:52:16,566 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
2025-05-29 14:52:16,572 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 14:52:16,648 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 14:52:16,683 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None
2025-05-29 14:52:16,684 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fb10b50>
2025-05-29 14:52:16,684 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 14:52:16,684 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 14:52:16,684 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 14:52:16,684 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 05:52:16 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
2025-05-29 14:52:16,685 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK"
2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 14:52:16,685 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 14:52:16,685 - httpcore.connection - DEBUG - close.started
2025-05-29 14:52:16,685 - httpcore.connection - DEBUG - close.complete
2025-05-29 14:52:16,686 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None
2025-05-29 14:52:16,686 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fbd0810>
2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 14:52:16,686 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 05:52:16 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73070'), (b'content-type', b'text/html; charset=utf-8')])
2025-05-29 14:52:16,692 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 14:52:16,692 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 14:52:16,692 - httpcore.connection - DEBUG - close.started
2025-05-29 14:52:16,692 - httpcore.connection - DEBUG - close.complete
2025-05-29 14:52:16,703 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
2025-05-29 14:52:16,842 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11f765050>
2025-05-29 14:52:16,842 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x10b538b90> server_hostname='api.gradio.app' timeout=3
2025-05-29 14:52:16,852 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
2025-05-29 14:52:16,861 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11f733390>
2025-05-29 14:52:16,861 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11fafe960> server_hostname='api.gradio.app' timeout=30
2025-05-29 14:52:17,179 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11d14c950>
2025-05-29 14:52:17,179 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 14:52:17,180 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 14:52:17,180 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 14:52:17,180 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 14:52:17,180 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 14:52:17,182 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11f751e10>
2025-05-29 14:52:17,182 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 14:52:17,182 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 14:52:17,182 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 14:52:17,183 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 14:52:17,183 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 05:52:17 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
2025-05-29 14:52:17,340 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 14:52:17,340 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 14:52:17,340 - httpcore.connection - DEBUG - close.started
2025-05-29 14:52:17,340 - httpcore.connection - DEBUG - close.complete
2025-05-29 14:52:17,354 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 05:52:17 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
2025-05-29 14:52:17,355 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
2025-05-29 14:52:17,355 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 14:52:17,355 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 14:52:17,355 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 14:52:17,355 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 14:52:17,355 - httpcore.connection - DEBUG - close.started
2025-05-29 14:52:17,355 - httpcore.connection - DEBUG - close.complete
2025-05-29 14:52:18,360 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 14:52:18,573 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
2025-05-29 15:59:34,212 - __main__ - INFO - Initializing GradioAutodiffusers
2025-05-29 15:59:34,212 - __main__ - DEBUG - API key found, length: 39
2025-05-29 15:59:34,212 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
2025-05-29 15:59:34,212 - auto_diffusers - DEBUG - API key length: 39
2025-05-29 15:59:34,212 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
2025-05-29 15:59:34,212 - hardware_detector - INFO - Initializing HardwareDetector
2025-05-29 15:59:34,212 - hardware_detector - DEBUG - Starting system hardware detection
2025-05-29 15:59:34,212 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
2025-05-29 15:59:34,212 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
2025-05-29 15:59:34,212 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
2025-05-29 15:59:34,216 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
2025-05-29 15:59:34,216 - hardware_detector - DEBUG - Checking PyTorch availability
2025-05-29 15:59:34,645 - hardware_detector - INFO - PyTorch 2.7.0 detected
2025-05-29 15:59:34,646 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
2025-05-29 15:59:34,646 - hardware_detector - INFO - Hardware detection completed successfully
2025-05-29 15:59:34,646 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
2025-05-29 15:59:34,646 - auto_diffusers - INFO - Hardware detector initialized successfully
2025-05-29 15:59:34,646 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
2025-05-29 15:59:34,646 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
2025-05-29 15:59:34,646 - simple_memory_calculator - DEBUG - HuggingFace API initialized
2025-05-29 15:59:34,646 - simple_memory_calculator - DEBUG - Known models in database: 4
2025-05-29 15:59:34,646 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
2025-05-29 15:59:34,646 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
2025-05-29 15:59:34,648 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 15:59:34,661 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
2025-05-29 15:59:34,667 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 15:59:34,749 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 15:59:34,784 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None
2025-05-29 15:59:34,785 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12991f5d0>
2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 15:59:34,785 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 06:59:34 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
2025-05-29 15:59:34,786 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK"
2025-05-29 15:59:34,786 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 15:59:34,786 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 15:59:34,786 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 15:59:34,786 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 15:59:34,786 - httpcore.connection - DEBUG - close.started
2025-05-29 15:59:34,786 - httpcore.connection - DEBUG - close.complete
2025-05-29 15:59:34,786 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None
2025-05-29 15:59:34,787 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1299d57d0>
2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 15:59:34,787 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 06:59:34 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73058'), (b'content-type', b'text/html; charset=utf-8')])
2025-05-29 15:59:34,792 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 15:59:34,792 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 15:59:34,793 - httpcore.connection - DEBUG - close.started
2025-05-29 15:59:34,793 - httpcore.connection - DEBUG - close.complete
2025-05-29 15:59:34,803 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
2025-05-29 15:59:34,825 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11e39d590>
2025-05-29 15:59:34,825 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x10f3209e0> server_hostname='api.gradio.app' timeout=3
2025-05-29 15:59:34,940 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11e971610>
2025-05-29 15:59:34,940 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11f5c36e0> server_hostname='api.gradio.app' timeout=30
2025-05-29 15:59:34,971 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
2025-05-29 15:59:35,099 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x10f31ba90>
2025-05-29 15:59:35,099 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 15:59:35,100 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 15:59:35,100 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 15:59:35,100 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 15:59:35,100 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 15:59:35,222 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11de99d10>
2025-05-29 15:59:35,222 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 15:59:35,223 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 15:59:35,223 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 15:59:35,223 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 15:59:35,223 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 15:59:35,237 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 06:59:35 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
2025-05-29 15:59:35,238 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
2025-05-29 15:59:35,238 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 15:59:35,238 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 15:59:35,238 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 15:59:35,238 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 15:59:35,238 - httpcore.connection - DEBUG - close.started
2025-05-29 15:59:35,239 - httpcore.connection - DEBUG - close.complete
2025-05-29 15:59:35,362 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 06:59:35 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
2025-05-29 15:59:35,363 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
2025-05-29 15:59:35,363 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 15:59:35,364 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 15:59:35,364 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 15:59:35,364 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 15:59:35,365 - httpcore.connection - DEBUG - close.started
2025-05-29 15:59:35,365 - httpcore.connection - DEBUG - close.complete
2025-05-29 15:59:36,012 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 15:59:36,260 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
2025-05-29 16:02:12,960 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:12,961 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:12,961 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
2025-05-29 16:02:12,961 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:02:12,961 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:12,962 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:12,962 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:02:12,962 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:12,962 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:32,785 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:32,785 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:32,785 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:02:32,785 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:32,785 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:32,786 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:02:32,786 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:32,786 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:47,460 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:47,460 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:47,460 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:02:47,460 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:47,460 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:47,460 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:02:47,460 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:47,460 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,300 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,300 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,300 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:02:52,300 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,300 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,300 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:02:52,300 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,300 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,452 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,452 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,452 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:02:52,452 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,452 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,452 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:02:52,452 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:52,452 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:54,804 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:54,804 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:54,804 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:02:54,804 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:54,804 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:54,804 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:02:54,804 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:54,804 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:54,804 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
2025-05-29 16:02:54,804 - auto_diffusers - INFO - Using manual hardware specifications
2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': [{'name': 'RTX 5090', 'memory_mb': 32768}]}
2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - GPU detected with 32.0 GB VRAM
2025-05-29 16:02:54,804 - auto_diffusers - INFO - Selected optimization profile: performance
2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
2025-05-29 16:02:54,804 - auto_diffusers - DEBUG - Prompt length: 3456 characters
2025-05-29 16:02:54,804 - auto_diffusers - INFO - Sending request to Gemini API with tool calling enabled
2025-05-29 16:03:10,966 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
2025-05-29 16:03:10,966 - auto_diffusers - DEBUG - Response length: 1710 characters
2025-05-29 16:08:00,894 - __main__ - INFO - Initializing GradioAutodiffusers
2025-05-29 16:08:00,894 - __main__ - DEBUG - API key found, length: 39
2025-05-29 16:08:00,894 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
2025-05-29 16:08:00,894 - auto_diffusers - DEBUG - API key length: 39
2025-05-29 16:08:00,894 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
2025-05-29 16:08:00,894 - hardware_detector - INFO - Initializing HardwareDetector
2025-05-29 16:08:00,894 - hardware_detector - DEBUG - Starting system hardware detection
2025-05-29 16:08:00,894 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
2025-05-29 16:08:00,894 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
2025-05-29 16:08:00,894 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
2025-05-29 16:08:00,898 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
2025-05-29 16:08:00,898 - hardware_detector - DEBUG - Checking PyTorch availability
2025-05-29 16:08:01,310 - hardware_detector - INFO - PyTorch 2.7.0 detected
2025-05-29 16:08:01,310 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
2025-05-29 16:08:01,310 - hardware_detector - INFO - Hardware detection completed successfully
2025-05-29 16:08:01,310 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
2025-05-29 16:08:01,310 - auto_diffusers - INFO - Hardware detector initialized successfully
2025-05-29 16:08:01,310 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
2025-05-29 16:08:01,310 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
2025-05-29 16:08:01,310 - simple_memory_calculator - DEBUG - HuggingFace API initialized
2025-05-29 16:08:01,310 - simple_memory_calculator - DEBUG - Known models in database: 4
2025-05-29 16:08:01,310 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
2025-05-29 16:08:01,310 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
2025-05-29 16:08:01,312 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 16:08:01,325 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
2025-05-29 16:08:01,325 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 16:08:01,404 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 16:08:01,439 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None
2025-05-29 16:08:01,440 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12e540090>
2025-05-29 16:08:01,440 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:08:01,440 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:08:01,440 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:08:01 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
2025-05-29 16:08:01,441 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK"
2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:08:01,441 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:08:01,441 - httpcore.connection - DEBUG - close.started
2025-05-29 16:08:01,441 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:08:01,442 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None
2025-05-29 16:08:01,442 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12e541610>
2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:08:01,442 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
2025-05-29 16:08:01,447 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:08:01 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73065'), (b'content-type', b'text/html; charset=utf-8')])
2025-05-29 16:08:01,448 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
2025-05-29 16:08:01,448 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
2025-05-29 16:08:01,448 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:08:01,448 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:08:01,448 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:08:01,448 - httpcore.connection - DEBUG - close.started
2025-05-29 16:08:01,448 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:08:01,459 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
2025-05-29 16:08:01,611 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
2025-05-29 16:08:01,746 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x129d2c510>
2025-05-29 16:08:01,746 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12e42f6e0> server_hostname='api.gradio.app' timeout=30
2025-05-29 16:08:01,764 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12a564450>
2025-05-29 16:08:01,764 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x119258a70> server_hostname='api.gradio.app' timeout=3
2025-05-29 16:08:02,034 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x129854a90>
2025-05-29 16:08:02,035 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:08:02,035 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:08:02,036 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:08:02,036 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:08:02,036 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:08:02,101 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12a51b310>
2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:08:02,101 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:08:02,186 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:08:02 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
2025-05-29 16:08:02,186 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
2025-05-29 16:08:02,187 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:08:02,187 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:08:02,187 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:08:02,187 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:08:02,187 - httpcore.connection - DEBUG - close.started
2025-05-29 16:08:02,187 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:08:02,272 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:08:02 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
2025-05-29 16:08:02,273 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
2025-05-29 16:08:02,273 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:08:02,273 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:08:02,273 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:08:02,273 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:08:02,273 - httpcore.connection - DEBUG - close.started
2025-05-29 16:08:02,273 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:08:02,845 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 16:08:03,061 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
2025-05-29 16:08:25,941 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:25,942 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:25,942 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
2025-05-29 16:08:25,942 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:08:25,942 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:25,942 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:25,942 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:08:25,942 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:25,943 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:30,760 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:30,761 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:30,761 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:08:30,761 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:30,761 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:30,761 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:08:30,761 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:30,761 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,477 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,477 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,478 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:08:37,478 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,478 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,478 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:08:37,480 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,480 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,527 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,527 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,527 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:08:37,527 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,527 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,527 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:08:37,527 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:37,527 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:39,349 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:39,350 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:39,350 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:08:39,350 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:39,350 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:39,351 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:08:39,351 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:39,351 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:39,351 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:08:39,351 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
2025-05-29 16:08:39,351 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
2025-05-29 16:08:39,351 - auto_diffusers - INFO - Using manual hardware specifications
2025-05-29 16:08:39,351 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': [{'name': 'RTX 5090', 'memory_mb': 32768}]}
2025-05-29 16:08:39,352 - auto_diffusers - DEBUG - GPU detected with 32.0 GB VRAM
2025-05-29 16:08:39,352 - auto_diffusers - INFO - Selected optimization profile: performance
2025-05-29 16:08:39,352 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
2025-05-29 16:08:39,352 - auto_diffusers - DEBUG - Prompt length: 3456 characters
2025-05-29 16:08:39,352 - auto_diffusers - INFO - ================================================================================
2025-05-29 16:08:39,352 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API:
2025-05-29 16:08:39,352 - auto_diffusers - INFO - ================================================================================
2025-05-29 16:08:39,352 - auto_diffusers - INFO - 
You are an expert in optimizing diffusers library code for different hardware configurations.

NOTE: Advanced tool calling features are available when dependencies are installed.

TASK: Generate optimized Python code for running a diffusion model with the following specifications:
- Model: black-forest-labs/FLUX.1-schnell
- Prompt: "A cat holding a sign that says hello world"
- Image size: 768x1360
- Inference steps: 4

HARDWARE SPECIFICATIONS:
- Platform: Linux (manual_input)
- CPU Cores: 8
- CUDA Available: False
- MPS Available: False
- Optimization Profile: performance
- GPU: RTX 5090 (32.0 GB VRAM)

MEMORY ANALYSIS:
- Model Memory Requirements: 36.0 GB (FP16 inference)
- Model Weights Size: 24.0 GB (FP16)
- Memory Recommendation: ⚠️ Model weights fit, enable memory optimizations
- Recommended Precision: float16
- Attention Slicing Recommended: True
- VAE Slicing Recommended: True

OPTIMIZATION REQUIREMENTS:
Please scrape and analyze the latest optimization techniques from this URL: https://huggingface.co/docs/diffusers/main/en/optimization

IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed.

Based on the hardware specs and optimization profile, generate Python code that includes:

1. **Memory Optimizations** (if low VRAM):
   - Model offloading (enable_model_cpu_offload, enable_sequential_cpu_offload)
   - Attention slicing (enable_attention_slicing)
   - VAE slicing (enable_vae_slicing)
   - Memory efficient attention

2. **Speed Optimizations**:
   - Appropriate torch.compile() usage
   - Optimal dtype selection (torch.float16, torch.bfloat16)
   - Device placement optimization

3. **Hardware-Specific Optimizations**:
   - CUDA optimizations for NVIDIA GPUs
   - MPS optimizations for Apple Silicon
   - CPU fallbacks when needed

4. **Model-Specific Optimizations**:
   - Appropriate scheduler selection
   - Optimal inference parameters
   - Pipeline configuration

5. **Data Type (dtype) Selection**:
   - If user specified a dtype, use that exact dtype in the code
   - If no dtype specified, automatically select the optimal dtype based on hardware:
     * Apple Silicon (MPS): prefer torch.bfloat16
     * NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 based on capability
     * CPU only: use torch.float32
   - Add a comment explaining why that dtype was chosen

IMPORTANT GUIDELINES:
- Include all necessary imports
- Add brief comments explaining optimization choices
- Use the most current and effective optimization techniques
- Ensure code is production-ready

CODE STYLE REQUIREMENTS - GENERATE COMPACT CODE:
- Assign static values directly to function arguments instead of using variables when possible
- Minimize variable declarations - inline values where it improves readability
- Reduce exception handling to essential cases only - assume normal operation
- Use concise, direct code patterns
- Combine operations where logical and readable
- Avoid unnecessary intermediate variables
- Keep code clean and minimal while maintaining functionality

Examples of preferred compact style:
- pipe = Pipeline.from_pretrained("model", torch_dtype=torch.float16) instead of storing dtype in variable
- image = pipe("prompt", num_inference_steps=4, height=768, width=1360) instead of separate variables
- Direct assignment: device = "cuda" if torch.cuda.is_available() else "cpu"

Generate ONLY the Python code, no explanations before or after the code block.

2025-05-29 16:08:39,353 - auto_diffusers - INFO - ================================================================================
2025-05-29 16:08:39,353 - auto_diffusers - INFO - Sending request to Gemini API
2025-05-29 16:08:54,821 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
2025-05-29 16:08:54,821 - auto_diffusers - DEBUG - Response length: 2512 characters
2025-05-29 16:16:14,940 - __main__ - INFO - Initializing GradioAutodiffusers
2025-05-29 16:16:14,940 - __main__ - DEBUG - API key found, length: 39
2025-05-29 16:16:14,940 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
2025-05-29 16:16:14,940 - auto_diffusers - DEBUG - API key length: 39
2025-05-29 16:16:14,940 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
2025-05-29 16:16:14,940 - hardware_detector - INFO - Initializing HardwareDetector
2025-05-29 16:16:14,940 - hardware_detector - DEBUG - Starting system hardware detection
2025-05-29 16:16:14,940 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
2025-05-29 16:16:14,940 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
2025-05-29 16:16:14,940 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
2025-05-29 16:16:14,943 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
2025-05-29 16:16:14,943 - hardware_detector - DEBUG - Checking PyTorch availability
2025-05-29 16:16:15,359 - hardware_detector - INFO - PyTorch 2.7.0 detected
2025-05-29 16:16:15,359 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
2025-05-29 16:16:15,359 - hardware_detector - INFO - Hardware detection completed successfully
2025-05-29 16:16:15,359 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
2025-05-29 16:16:15,359 - auto_diffusers - INFO - Hardware detector initialized successfully
2025-05-29 16:16:15,359 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
2025-05-29 16:16:15,359 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
2025-05-29 16:16:15,359 - simple_memory_calculator - DEBUG - HuggingFace API initialized
2025-05-29 16:16:15,359 - simple_memory_calculator - DEBUG - Known models in database: 4
2025-05-29 16:16:15,359 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
2025-05-29 16:16:15,359 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
2025-05-29 16:16:15,362 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 16:16:15,374 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
2025-05-29 16:16:15,381 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 16:16:15,454 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 16:16:15,488 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None
2025-05-29 16:16:15,489 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x130ad4a90>
2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:16:15,489 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:16:15 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
2025-05-29 16:16:15,490 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK"
2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:16:15,490 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:16:15,490 - httpcore.connection - DEBUG - close.started
2025-05-29 16:16:15,490 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:16:15,490 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None
2025-05-29 16:16:15,491 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x130ad5e10>
2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:16:15,491 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:16:15 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73064'), (b'content-type', b'text/html; charset=utf-8')])
2025-05-29 16:16:15,496 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:16:15,496 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:16:15,496 - httpcore.connection - DEBUG - close.started
2025-05-29 16:16:15,496 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:16:15,507 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
2025-05-29 16:16:15,593 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x13047a3d0>
2025-05-29 16:16:15,593 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x13008d250> server_hostname='api.gradio.app' timeout=3
2025-05-29 16:16:15,648 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x124f7acd0>
2025-05-29 16:16:15,648 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x1309cb920> server_hostname='api.gradio.app' timeout=30
2025-05-29 16:16:15,663 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
2025-05-29 16:16:15,894 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x13093ec50>
2025-05-29 16:16:15,895 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:16:15,896 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:16:15,896 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:16:15,896 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:16:15,896 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:16:15,930 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127aef8d0>
2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:16:15,931 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:16:16,047 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:16:16 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
2025-05-29 16:16:16,047 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
2025-05-29 16:16:16,047 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:16:16,048 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:16:16,048 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:16:16,048 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:16:16,048 - httpcore.connection - DEBUG - close.started
2025-05-29 16:16:16,048 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:16:16,073 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:16:16 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
2025-05-29 16:16:16,074 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
2025-05-29 16:16:16,074 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:16:16,074 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:16:16,074 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:16:16,074 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:16:16,074 - httpcore.connection - DEBUG - close.started
2025-05-29 16:16:16,074 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:16:16,750 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 16:16:16,967 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
2025-05-29 16:16:50,011 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:50,012 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:50,012 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
2025-05-29 16:16:50,012 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:16:50,012 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:50,012 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:50,012 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:16:50,012 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:50,012 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:56,212 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:56,212 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:56,212 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:16:56,212 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:56,212 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:56,212 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:16:56,212 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:16:56,212 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,382 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,382 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,383 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:17:00,383 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,383 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,383 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:17:00,383 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,383 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,534 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,534 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,534 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:17:00,534 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,534 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,534 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:17:00,534 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:00,535 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:02,112 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:02,112 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:02,112 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:17:02,112 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:02,112 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:02,112 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:17:02,112 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:02,112 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:02,112 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
2025-05-29 16:17:02,112 - auto_diffusers - INFO - Using manual hardware specifications
2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': [{'name': 'RTX 5090', 'memory_mb': 32768}]}
2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - GPU detected with 32.0 GB VRAM
2025-05-29 16:17:02,112 - auto_diffusers - INFO - Selected optimization profile: performance
2025-05-29 16:17:02,112 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
2025-05-29 16:17:02,113 - auto_diffusers - DEBUG - Prompt length: 3456 characters
2025-05-29 16:17:02,113 - auto_diffusers - INFO - ================================================================================
2025-05-29 16:17:02,113 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API:
2025-05-29 16:17:02,113 - auto_diffusers - INFO - ================================================================================
2025-05-29 16:17:02,113 - auto_diffusers - INFO - 
You are an expert in optimizing diffusers library code for different hardware configurations.

NOTE: Advanced tool calling features are available when dependencies are installed.

TASK: Generate optimized Python code for running a diffusion model with the following specifications:
- Model: black-forest-labs/FLUX.1-schnell
- Prompt: "A cat holding a sign that says hello world"
- Image size: 768x1360
- Inference steps: 4

HARDWARE SPECIFICATIONS:
- Platform: Linux (manual_input)
- CPU Cores: 8
- CUDA Available: False
- MPS Available: False
- Optimization Profile: performance
- GPU: RTX 5090 (32.0 GB VRAM)

MEMORY ANALYSIS:
- Model Memory Requirements: 36.0 GB (FP16 inference)
- Model Weights Size: 24.0 GB (FP16)
- Memory Recommendation: ⚠️ Model weights fit, enable memory optimizations
- Recommended Precision: float16
- Attention Slicing Recommended: True
- VAE Slicing Recommended: True

OPTIMIZATION REQUIREMENTS:
Please scrape and analyze the latest optimization techniques from this URL: https://huggingface.co/docs/diffusers/main/en/optimization

IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed.

Based on the hardware specs and optimization profile, generate Python code that includes:

1. **Memory Optimizations** (if low VRAM):
   - Model offloading (enable_model_cpu_offload, enable_sequential_cpu_offload)
   - Attention slicing (enable_attention_slicing)
   - VAE slicing (enable_vae_slicing)
   - Memory efficient attention

2. **Speed Optimizations**:
   - Appropriate torch.compile() usage
   - Optimal dtype selection (torch.float16, torch.bfloat16)
   - Device placement optimization

3. **Hardware-Specific Optimizations**:
   - CUDA optimizations for NVIDIA GPUs
   - MPS optimizations for Apple Silicon
   - CPU fallbacks when needed

4. **Model-Specific Optimizations**:
   - Appropriate scheduler selection
   - Optimal inference parameters
   - Pipeline configuration

5. **Data Type (dtype) Selection**:
   - If user specified a dtype, use that exact dtype in the code
   - If no dtype specified, automatically select the optimal dtype based on hardware:
     * Apple Silicon (MPS): prefer torch.bfloat16
     * NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 based on capability
     * CPU only: use torch.float32
   - Add a comment explaining why that dtype was chosen

IMPORTANT GUIDELINES:
- Include all necessary imports
- Add brief comments explaining optimization choices
- Use the most current and effective optimization techniques
- Ensure code is production-ready

CODE STYLE REQUIREMENTS - GENERATE COMPACT CODE:
- Assign static values directly to function arguments instead of using variables when possible
- Minimize variable declarations - inline values where it improves readability
- Reduce exception handling to essential cases only - assume normal operation
- Use concise, direct code patterns
- Combine operations where logical and readable
- Avoid unnecessary intermediate variables
- Keep code clean and minimal while maintaining functionality

Examples of preferred compact style:
- pipe = Pipeline.from_pretrained("model", torch_dtype=torch.float16) instead of storing dtype in variable
- image = pipe("prompt", num_inference_steps=4, height=768, width=1360) instead of separate variables
- Direct assignment: device = "cuda" if torch.cuda.is_available() else "cpu"

Generate ONLY the Python code, no explanations before or after the code block.

2025-05-29 16:17:02,113 - auto_diffusers - INFO - ================================================================================
2025-05-29 16:17:02,113 - auto_diffusers - INFO - Sending request to Gemini API
2025-05-29 16:17:17,152 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
2025-05-29 16:17:17,153 - auto_diffusers - DEBUG - Response length: 2451 characters
2025-05-29 16:47:23,476 - __main__ - INFO - Initializing GradioAutodiffusers
2025-05-29 16:47:23,476 - __main__ - DEBUG - API key found, length: 39
2025-05-29 16:47:23,476 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
2025-05-29 16:47:23,476 - auto_diffusers - DEBUG - API key length: 39
2025-05-29 16:47:23,477 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
2025-05-29 16:47:23,477 - hardware_detector - INFO - Initializing HardwareDetector
2025-05-29 16:47:23,477 - hardware_detector - DEBUG - Starting system hardware detection
2025-05-29 16:47:23,477 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
2025-05-29 16:47:23,477 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
2025-05-29 16:47:23,477 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
2025-05-29 16:47:23,480 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
2025-05-29 16:47:23,480 - hardware_detector - DEBUG - Checking PyTorch availability
2025-05-29 16:47:23,928 - hardware_detector - INFO - PyTorch 2.7.0 detected
2025-05-29 16:47:23,928 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
2025-05-29 16:47:23,928 - hardware_detector - INFO - Hardware detection completed successfully
2025-05-29 16:47:23,928 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
2025-05-29 16:47:23,928 - auto_diffusers - INFO - Hardware detector initialized successfully
2025-05-29 16:47:23,928 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
2025-05-29 16:47:23,928 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
2025-05-29 16:47:23,928 - simple_memory_calculator - DEBUG - HuggingFace API initialized
2025-05-29 16:47:23,928 - simple_memory_calculator - DEBUG - Known models in database: 4
2025-05-29 16:47:23,928 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
2025-05-29 16:47:23,928 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
2025-05-29 16:47:23,930 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 16:47:23,944 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
2025-05-29 16:47:23,950 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 16:47:24,025 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 16:47:24,059 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None
2025-05-29 16:47:24,060 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x129f2bf90>
2025-05-29 16:47:24,060 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:47:24,060 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:47:24,060 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:47:24 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
2025-05-29 16:47:24,061 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK"
2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:47:24,061 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:47:24,061 - httpcore.connection - DEBUG - close.started
2025-05-29 16:47:24,061 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:47:24,062 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None
2025-05-29 16:47:24,062 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12cbb3f90>
2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:47:24,062 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:47:24 GMT'), (b'server', b'uvicorn'), (b'content-length', b'73064'), (b'content-type', b'text/html; charset=utf-8')])
2025-05-29 16:47:24,068 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:47:24,068 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:47:24,068 - httpcore.connection - DEBUG - close.started
2025-05-29 16:47:24,068 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:47:24,079 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
2025-05-29 16:47:24,140 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12833f750>
2025-05-29 16:47:24,140 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x118154dd0> server_hostname='api.gradio.app' timeout=3
2025-05-29 16:47:24,220 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1286ce850>
2025-05-29 16:47:24,220 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12a1cf890> server_hostname='api.gradio.app' timeout=30
2025-05-29 16:47:24,223 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
2025-05-29 16:47:24,415 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1280130d0>
2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:47:24,415 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:47:24,504 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x129f29090>
2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:47:24,505 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:47:24,553 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:47:24 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
2025-05-29 16:47:24,554 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
2025-05-29 16:47:24,554 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:47:24,554 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:47:24,554 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:47:24,554 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:47:24,554 - httpcore.connection - DEBUG - close.started
2025-05-29 16:47:24,554 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:47:24 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
2025-05-29 16:47:24,648 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:47:24,648 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:47:24,649 - httpcore.connection - DEBUG - close.started
2025-05-29 16:47:24,649 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:47:25,332 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 16:47:25,554 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
2025-05-29 16:47:35,239 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:35,239 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:35,239 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
2025-05-29 16:47:35,239 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:47:35,239 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:35,239 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:35,239 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:47:35,240 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:35,240 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:40,282 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:40,282 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:40,282 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:47:40,282 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:40,282 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:40,282 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:47:40,282 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:40,282 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:43,895 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:43,895 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:43,895 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:47:43,895 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:43,895 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:43,895 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:47:43,895 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:43,896 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:44,048 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:44,048 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:44,048 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:47:44,048 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:44,048 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:44,048 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:47:44,048 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:44,048 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:48,011 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:48,011 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:48,011 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
2025-05-29 16:47:48,011 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:48,011 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:48,011 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:47:48,011 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:48,012 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:48,012 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
2025-05-29 16:47:48,012 - auto_diffusers - INFO - Using manual hardware specifications
2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': [{'name': 'RTX 5090', 'memory_mb': 32768}]}
2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - GPU detected with 32.0 GB VRAM
2025-05-29 16:47:48,012 - auto_diffusers - INFO - Selected optimization profile: performance
2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
2025-05-29 16:47:48,012 - auto_diffusers - DEBUG - Prompt length: 7613 characters
2025-05-29 16:47:48,012 - auto_diffusers - INFO - ================================================================================
2025-05-29 16:47:48,012 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API:
2025-05-29 16:47:48,013 - auto_diffusers - INFO - ================================================================================
2025-05-29 16:47:48,013 - auto_diffusers - INFO - 
You are an expert in optimizing diffusers library code for different hardware configurations.

NOTE: This system includes curated optimization knowledge from HuggingFace documentation.

TASK: Generate optimized Python code for running a diffusion model with the following specifications:
- Model: black-forest-labs/FLUX.1-schnell
- Prompt: "A cat holding a sign that says hello world"
- Image size: 768x1360
- Inference steps: 4

HARDWARE SPECIFICATIONS:
- Platform: Linux (manual_input)
- CPU Cores: 8
- CUDA Available: False
- MPS Available: False
- Optimization Profile: performance
- GPU: RTX 5090 (32.0 GB VRAM)

MEMORY ANALYSIS:
- Model Memory Requirements: 36.0 GB (FP16 inference)
- Model Weights Size: 24.0 GB (FP16)
- Memory Recommendation: ⚠️ Model weights fit, enable memory optimizations
- Recommended Precision: float16
- Attention Slicing Recommended: True
- VAE Slicing Recommended: True

OPTIMIZATION KNOWLEDGE BASE:

# DIFFUSERS OPTIMIZATION TECHNIQUES

## Memory Optimization Techniques

### 1. Model CPU Offloading
Use `enable_model_cpu_offload()` to move models between GPU and CPU automatically:
```python
pipe.enable_model_cpu_offload()
```
- Saves significant VRAM by keeping only active models on GPU
- Automatic management, no manual intervention needed
- Compatible with all pipelines

### 2. Sequential CPU Offloading  
Use `enable_sequential_cpu_offload()` for more aggressive memory saving:
```python
pipe.enable_sequential_cpu_offload()
```
- More memory efficient than model offloading
- Moves models to CPU after each forward pass
- Best for very limited VRAM scenarios

### 3. Attention Slicing
Use `enable_attention_slicing()` to reduce memory during attention computation:
```python
pipe.enable_attention_slicing()
# or specify slice size
pipe.enable_attention_slicing("max")  # maximum slicing
pipe.enable_attention_slicing(1)      # slice_size = 1
```
- Trades compute time for memory
- Most effective for high-resolution images
- Can be combined with other techniques

### 4. VAE Slicing
Use `enable_vae_slicing()` for large batch processing:
```python
pipe.enable_vae_slicing()
```
- Decodes images one at a time instead of all at once
- Essential for batch sizes > 4
- Minimal performance impact on single images

### 5. VAE Tiling
Use `enable_vae_tiling()` for high-resolution image generation:
```python
pipe.enable_vae_tiling()
```
- Enables 4K+ image generation on 8GB VRAM
- Splits images into overlapping tiles
- Automatically disabled for 512x512 or smaller images

### 6. Memory Efficient Attention (xFormers)
Use `enable_xformers_memory_efficient_attention()` if xFormers is installed:
```python
pipe.enable_xformers_memory_efficient_attention()
```
- Significantly reduces memory usage and improves speed
- Requires xformers library installation
- Compatible with most models

## Performance Optimization Techniques

### 1. Half Precision (FP16/BF16)
Use lower precision for better memory and speed:
```python
# FP16 (widely supported)
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)

# BF16 (better numerical stability, newer hardware)
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
```
- FP16: Halves memory usage, widely supported
- BF16: Better numerical stability, requires newer GPUs
- Essential for most optimization scenarios

### 2. Torch Compile (PyTorch 2.0+)
Use `torch.compile()` for significant speed improvements:
```python
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
# For some models, compile VAE too:
pipe.vae.decode = torch.compile(pipe.vae.decode, mode="reduce-overhead", fullgraph=True)
```
- 5-50% speed improvement
- Requires PyTorch 2.0+
- First run is slower due to compilation

### 3. Fast Schedulers
Use faster schedulers for fewer steps:
```python
from diffusers import LMSDiscreteScheduler, UniPCMultistepScheduler

# LMS Scheduler (good quality, fast)
pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config)

# UniPC Scheduler (fastest)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
```

## Hardware-Specific Optimizations

### NVIDIA GPU Optimizations
```python
# Enable Tensor Cores
torch.backends.cudnn.benchmark = True

# Optimal data type for NVIDIA
torch_dtype = torch.float16  # or torch.bfloat16 for RTX 30/40 series
```

### Apple Silicon (MPS) Optimizations
```python
# Use MPS device
device = "mps" if torch.backends.mps.is_available() else "cpu"
pipe = pipe.to(device)

# Recommended dtype for Apple Silicon
torch_dtype = torch.bfloat16  # Better than float16 on Apple Silicon

# Attention slicing often helps on MPS
pipe.enable_attention_slicing()
```

### CPU Optimizations
```python
# Use float32 for CPU
torch_dtype = torch.float32

# Enable optimized attention
pipe.enable_attention_slicing()
```

## Model-Specific Guidelines

### FLUX Models
- Do NOT use guidance_scale parameter (not needed for FLUX)
- Use 4-8 inference steps maximum
- BF16 dtype recommended
- Enable attention slicing for memory optimization

### Stable Diffusion XL
- Enable attention slicing for high resolutions
- Use refiner model sparingly to save memory
- Consider VAE tiling for >1024px images

### Stable Diffusion 1.5/2.1
- Very memory efficient base models
- Can often run without optimizations on 8GB+ VRAM
- Enable VAE slicing for batch processing

## Memory Usage Estimation
- FLUX.1: ~24GB for full precision, ~12GB for FP16
- SDXL: ~7GB for FP16, ~14GB for FP32
- SD 1.5: ~2GB for FP16, ~4GB for FP32

## Optimization Combinations by VRAM

### 24GB+ VRAM (High-end)
```python
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
```

### 12-24GB VRAM (Mid-range)
```python
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe.enable_model_cpu_offload()
pipe.enable_xformers_memory_efficient_attention()
```

### 8-12GB VRAM (Entry-level)
```python
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.enable_sequential_cpu_offload()
pipe.enable_attention_slicing()
pipe.enable_vae_slicing()
pipe.enable_xformers_memory_efficient_attention()
```

### <8GB VRAM (Low-end)
```python
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.enable_sequential_cpu_offload()
pipe.enable_attention_slicing("max")
pipe.enable_vae_slicing()
pipe.enable_vae_tiling()
```


IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed.

Using the OPTIMIZATION KNOWLEDGE BASE above, generate Python code that:

1. **Selects the best optimization techniques** for the specific hardware profile
2. **Applies appropriate memory optimizations** based on available VRAM
3. **Uses optimal data types** for the target hardware:
   - User specified dtype (if provided): Use exactly as specified
   - Apple Silicon (MPS): prefer torch.bfloat16
   - NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 
   - CPU only: use torch.float32
4. **Implements hardware-specific optimizations** (CUDA, MPS, CPU)
5. **Follows model-specific guidelines** (e.g., FLUX guidance_scale handling)

IMPORTANT GUIDELINES:
- Reference the OPTIMIZATION KNOWLEDGE BASE to select appropriate techniques
- Include all necessary imports
- Add brief comments explaining optimization choices
- Generate compact, production-ready code
- Inline values where possible for concise code
- Generate ONLY the Python code, no explanations before or after the code block

2025-05-29 16:47:48,013 - auto_diffusers - INFO - ================================================================================
2025-05-29 16:47:48,013 - auto_diffusers - INFO - Sending request to Gemini API
2025-05-29 16:48:09,467 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
2025-05-29 16:48:09,467 - auto_diffusers - DEBUG - Response length: 3996 characters
2025-05-29 16:57:34,668 - __main__ - INFO - Initializing GradioAutodiffusers
2025-05-29 16:57:34,668 - __main__ - DEBUG - API key found, length: 39
2025-05-29 16:57:34,668 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
2025-05-29 16:57:34,668 - auto_diffusers - DEBUG - API key length: 39
2025-05-29 16:57:34,668 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
2025-05-29 16:57:34,668 - hardware_detector - INFO - Initializing HardwareDetector
2025-05-29 16:57:34,668 - hardware_detector - DEBUG - Starting system hardware detection
2025-05-29 16:57:34,668 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
2025-05-29 16:57:34,668 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
2025-05-29 16:57:34,668 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
2025-05-29 16:57:34,672 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
2025-05-29 16:57:34,672 - hardware_detector - DEBUG - Checking PyTorch availability
2025-05-29 16:57:35,129 - hardware_detector - INFO - PyTorch 2.7.0 detected
2025-05-29 16:57:35,129 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
2025-05-29 16:57:35,129 - hardware_detector - INFO - Hardware detection completed successfully
2025-05-29 16:57:35,129 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
2025-05-29 16:57:35,129 - auto_diffusers - INFO - Hardware detector initialized successfully
2025-05-29 16:57:35,129 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
2025-05-29 16:57:35,129 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
2025-05-29 16:57:35,129 - simple_memory_calculator - DEBUG - HuggingFace API initialized
2025-05-29 16:57:35,129 - simple_memory_calculator - DEBUG - Known models in database: 4
2025-05-29 16:57:35,129 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
2025-05-29 16:57:35,129 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
2025-05-29 16:57:35,131 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 16:57:35,145 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
2025-05-29 16:57:35,145 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 16:57:35,222 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 16:57:35,257 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None
2025-05-29 16:57:35,257 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12d2dff90>
2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:57:35,258 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:57:35 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
2025-05-29 16:57:35,259 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK"
2025-05-29 16:57:35,259 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:57:35,259 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:57:35,259 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:57:35,259 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:57:35,259 - httpcore.connection - DEBUG - close.started
2025-05-29 16:57:35,259 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:57:35,259 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None
2025-05-29 16:57:35,260 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12fd72390>
2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:57:35,260 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
2025-05-29 16:57:35,265 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 07:57:35 GMT'), (b'server', b'uvicorn'), (b'content-length', b'75554'), (b'content-type', b'text/html; charset=utf-8')])
2025-05-29 16:57:35,265 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
2025-05-29 16:57:35,265 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
2025-05-29 16:57:35,265 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:57:35,265 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:57:35,266 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:57:35,266 - httpcore.connection - DEBUG - close.started
2025-05-29 16:57:35,266 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:57:35,276 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
2025-05-29 16:57:35,346 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12be9e610>
2025-05-29 16:57:35,346 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12bb8d1c0> server_hostname='api.gradio.app' timeout=3
2025-05-29 16:57:35,425 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
2025-05-29 16:57:35,434 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12a944910>
2025-05-29 16:57:35,434 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12fd37890> server_hostname='api.gradio.app' timeout=30
2025-05-29 16:57:35,637 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12be1f910>
2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:57:35,638 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:57:35,751 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12b17b850>
2025-05-29 16:57:35,751 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 16:57:35,752 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 16:57:35,752 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 16:57:35,752 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 16:57:35,752 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 16:57:35,786 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:57:35 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
2025-05-29 16:57:35,787 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
2025-05-29 16:57:35,787 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:57:35,787 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:57:35,787 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:57:35,787 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:57:35,787 - httpcore.connection - DEBUG - close.started
2025-05-29 16:57:35,788 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 07:57:35 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
2025-05-29 16:57:35,912 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 16:57:35,912 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 16:57:35,912 - httpcore.connection - DEBUG - close.started
2025-05-29 16:57:35,912 - httpcore.connection - DEBUG - close.complete
2025-05-29 16:57:36,487 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 16:57:36,707 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
2025-05-29 16:57:49,246 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:57:49,246 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:57:49,246 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
2025-05-29 16:57:49,246 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 16:57:49,246 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:57:49,246 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 16:57:49,247 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 16:57:49,247 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 16:57:49,247 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 17:00:22,113 - __main__ - INFO - Initializing GradioAutodiffusers
2025-05-29 17:00:22,113 - __main__ - DEBUG - API key found, length: 39
2025-05-29 17:00:22,113 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
2025-05-29 17:00:22,113 - auto_diffusers - DEBUG - API key length: 39
2025-05-29 17:00:22,113 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
2025-05-29 17:00:22,113 - hardware_detector - INFO - Initializing HardwareDetector
2025-05-29 17:00:22,113 - hardware_detector - DEBUG - Starting system hardware detection
2025-05-29 17:00:22,113 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
2025-05-29 17:00:22,113 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
2025-05-29 17:00:22,113 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
2025-05-29 17:00:22,117 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
2025-05-29 17:00:22,117 - hardware_detector - DEBUG - Checking PyTorch availability
2025-05-29 17:00:22,530 - hardware_detector - INFO - PyTorch 2.7.0 detected
2025-05-29 17:00:22,530 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
2025-05-29 17:00:22,530 - hardware_detector - INFO - Hardware detection completed successfully
2025-05-29 17:00:22,530 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
2025-05-29 17:00:22,530 - auto_diffusers - INFO - Hardware detector initialized successfully
2025-05-29 17:00:22,530 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
2025-05-29 17:00:22,530 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
2025-05-29 17:00:22,530 - simple_memory_calculator - DEBUG - HuggingFace API initialized
2025-05-29 17:00:22,530 - simple_memory_calculator - DEBUG - Known models in database: 4
2025-05-29 17:00:22,530 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
2025-05-29 17:00:22,530 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
2025-05-29 17:00:22,532 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 17:00:22,545 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
2025-05-29 17:00:22,550 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 17:00:22,624 - asyncio - DEBUG - Using selector: KqueueSelector
2025-05-29 17:00:22,657 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None
2025-05-29 17:00:22,657 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127bd1190>
2025-05-29 17:00:22,657 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 17:00:22,657 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 08:00:22 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
2025-05-29 17:00:22,658 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK"
2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 17:00:22,658 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 17:00:22,658 - httpcore.connection - DEBUG - close.started
2025-05-29 17:00:22,658 - httpcore.connection - DEBUG - close.complete
2025-05-29 17:00:22,659 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None
2025-05-29 17:00:22,659 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127bd2510>
2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 17:00:22,659 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 08:00:22 GMT'), (b'server', b'uvicorn'), (b'content-length', b'75615'), (b'content-type', b'text/html; charset=utf-8')])
2025-05-29 17:00:22,665 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 17:00:22,665 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 17:00:22,665 - httpcore.connection - DEBUG - close.started
2025-05-29 17:00:22,665 - httpcore.connection - DEBUG - close.complete
2025-05-29 17:00:22,676 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
2025-05-29 17:00:22,750 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x121dda850>
2025-05-29 17:00:22,750 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x107f2cdd0> server_hostname='api.gradio.app' timeout=3
2025-05-29 17:00:22,815 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1278afd10>
2025-05-29 17:00:22,815 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x127937890> server_hostname='api.gradio.app' timeout=30
2025-05-29 17:00:22,823 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
2025-05-29 17:00:23,027 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x123a7e850>
2025-05-29 17:00:23,028 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 17:00:23,028 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 17:00:23,029 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 17:00:23,029 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 17:00:23,029 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 17:00:23,090 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x123a771d0>
2025-05-29 17:00:23,090 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
2025-05-29 17:00:23,091 - httpcore.http11 - DEBUG - send_request_headers.complete
2025-05-29 17:00:23,091 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
2025-05-29 17:00:23,091 - httpcore.http11 - DEBUG - send_request_body.complete
2025-05-29 17:00:23,091 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
2025-05-29 17:00:23,199 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 08:00:23 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
2025-05-29 17:00:23,201 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
2025-05-29 17:00:23,201 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 17:00:23,201 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 17:00:23,201 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 17:00:23,201 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 17:00:23,201 - httpcore.connection - DEBUG - close.started
2025-05-29 17:00:23,202 - httpcore.connection - DEBUG - close.complete
2025-05-29 17:00:23,232 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 08:00:23 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
2025-05-29 17:00:23,232 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
2025-05-29 17:00:23,232 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
2025-05-29 17:00:23,233 - httpcore.http11 - DEBUG - receive_response_body.complete
2025-05-29 17:00:23,233 - httpcore.http11 - DEBUG - response_closed.started
2025-05-29 17:00:23,233 - httpcore.http11 - DEBUG - response_closed.complete
2025-05-29 17:00:23,233 - httpcore.connection - DEBUG - close.started
2025-05-29 17:00:23,233 - httpcore.connection - DEBUG - close.complete
2025-05-29 17:00:23,883 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
2025-05-29 17:00:24,103 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
2025-05-29 17:00:34,004 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 17:00:34,004 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 17:00:34,005 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
2025-05-29 17:00:34,005 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
2025-05-29 17:00:34,005 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 17:00:34,005 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
2025-05-29 17:00:34,005 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
2025-05-29 17:00:34,005 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
2025-05-29 17:00:34,005 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell