zhendch commited on
Commit
1bcdef1
·
verified ·
1 Parent(s): 27b4b07

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "WanModel",
3
- "_diffusers_version": "0.35.0.dev0",
4
- "_name_or_path": "/wan2.1_i2v_480p_lightx2v_memoryinit",
5
  "audio_window": 5,
6
  "context_tokens": 32,
7
  "dim": 5120,
 
1
  {
2
  "_class_name": "WanModel",
3
+ "_diffusers_version": "0.32.2",
4
+ "_name_or_path": "/WanModel_audio200_armemory1_modifyema200700/",
5
  "audio_window": 5,
6
  "context_tokens": 32,
7
  "dim": 5120,
diffusion_pytorch_model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0602cb252d345550706127765bc225cd8b2ef8bd971276e5ce160f26cb1a5cf6
3
- size 9959859864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f67d7fb1299ea57377e79e104e4b6b6b5d0dc6169996de150603718c50903c
3
+ size 9959864176
diffusion_pytorch_model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e05a7319f21ca298dab0ff974ad3d34ed5e29e220c60cf6edb4fe7cf14f0d7b
3
  size 9987013400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb0093088a6f6ff6cfe6a3d96cdeb308a1c9c707174d703140dd228d244482a4
3
  size 9987013400
diffusion_pytorch_model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4034e59788c9ff9048dc2b6874f82e780f49d7ac05fdfc2ad500a4df46b45240
3
  size 9966299200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11dc45940b21e438959da11ef2f4a35d844d433715361d32c74373748d312ea8
3
  size 9966299200
diffusion_pytorch_model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f19dcfe4a26680e50dd601d36b2a8afdeb86de10b6a134e44bf4550b21481c4
3
  size 7855197520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f56758049531a0dbc2c375b6a0b6a84818888d15e617c15c2e85e8cab26a67f
3
  size 7855197520
diffusion_pytorch_model.safetensors.index.json CHANGED
@@ -53,6 +53,7 @@
53
  "blocks.0.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
54
  "blocks.0.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
55
  "blocks.0.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
56
  "blocks.0.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
57
  "blocks.0.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
58
  "blocks.1.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
@@ -95,6 +96,7 @@
95
  "blocks.1.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
96
  "blocks.1.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
97
  "blocks.1.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
98
  "blocks.1.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
99
  "blocks.1.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
100
  "blocks.10.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -137,6 +139,7 @@
137
  "blocks.10.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
138
  "blocks.10.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
139
  "blocks.10.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
140
  "blocks.10.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
141
  "blocks.10.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
142
  "blocks.11.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -179,6 +182,7 @@
179
  "blocks.11.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
180
  "blocks.11.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
181
  "blocks.11.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
182
  "blocks.11.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
183
  "blocks.11.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
184
  "blocks.12.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -221,6 +225,7 @@
221
  "blocks.12.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
222
  "blocks.12.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
223
  "blocks.12.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
224
  "blocks.12.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
225
  "blocks.12.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
226
  "blocks.13.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -263,6 +268,7 @@
263
  "blocks.13.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
264
  "blocks.13.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
265
  "blocks.13.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
266
  "blocks.13.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
267
  "blocks.13.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
268
  "blocks.14.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -305,6 +311,7 @@
305
  "blocks.14.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
306
  "blocks.14.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
307
  "blocks.14.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
308
  "blocks.14.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
309
  "blocks.14.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
310
  "blocks.15.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -347,6 +354,7 @@
347
  "blocks.15.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
348
  "blocks.15.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
349
  "blocks.15.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
350
  "blocks.15.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
351
  "blocks.15.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
352
  "blocks.16.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -389,6 +397,7 @@
389
  "blocks.16.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
390
  "blocks.16.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
391
  "blocks.16.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
392
  "blocks.16.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
393
  "blocks.16.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
394
  "blocks.17.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -431,6 +440,7 @@
431
  "blocks.17.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
432
  "blocks.17.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
433
  "blocks.17.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
434
  "blocks.17.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
435
  "blocks.17.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
436
  "blocks.18.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -473,6 +483,7 @@
473
  "blocks.18.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
474
  "blocks.18.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
475
  "blocks.18.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
476
  "blocks.18.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
477
  "blocks.18.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
478
  "blocks.19.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
@@ -515,6 +526,7 @@
515
  "blocks.19.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
516
  "blocks.19.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
517
  "blocks.19.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
518
  "blocks.19.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
519
  "blocks.19.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
520
  "blocks.2.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
@@ -557,6 +569,7 @@
557
  "blocks.2.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
558
  "blocks.2.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
559
  "blocks.2.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
560
  "blocks.2.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
561
  "blocks.2.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
562
  "blocks.20.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -599,6 +612,7 @@
599
  "blocks.20.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
600
  "blocks.20.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
601
  "blocks.20.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
602
  "blocks.20.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
603
  "blocks.20.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
604
  "blocks.21.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -641,6 +655,7 @@
641
  "blocks.21.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
642
  "blocks.21.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
643
  "blocks.21.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
644
  "blocks.21.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
645
  "blocks.21.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
646
  "blocks.22.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -683,6 +698,7 @@
683
  "blocks.22.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
684
  "blocks.22.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
685
  "blocks.22.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
686
  "blocks.22.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
687
  "blocks.22.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
688
  "blocks.23.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -725,6 +741,7 @@
725
  "blocks.23.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
726
  "blocks.23.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
727
  "blocks.23.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
728
  "blocks.23.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
729
  "blocks.23.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
730
  "blocks.24.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -767,6 +784,7 @@
767
  "blocks.24.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
768
  "blocks.24.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
769
  "blocks.24.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
770
  "blocks.24.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
771
  "blocks.24.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
772
  "blocks.25.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -809,6 +827,7 @@
809
  "blocks.25.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
810
  "blocks.25.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
811
  "blocks.25.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
812
  "blocks.25.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
813
  "blocks.25.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
814
  "blocks.26.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -851,6 +870,7 @@
851
  "blocks.26.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
852
  "blocks.26.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
853
  "blocks.26.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
854
  "blocks.26.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
855
  "blocks.26.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
856
  "blocks.27.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -893,6 +913,7 @@
893
  "blocks.27.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
894
  "blocks.27.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
895
  "blocks.27.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
896
  "blocks.27.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
897
  "blocks.27.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
898
  "blocks.28.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -935,6 +956,7 @@
935
  "blocks.28.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
936
  "blocks.28.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
937
  "blocks.28.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
938
  "blocks.28.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
939
  "blocks.28.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
940
  "blocks.29.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -977,6 +999,7 @@
977
  "blocks.29.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
978
  "blocks.29.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
979
  "blocks.29.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
980
  "blocks.29.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
981
  "blocks.29.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
982
  "blocks.3.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
@@ -1019,6 +1042,7 @@
1019
  "blocks.3.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1020
  "blocks.3.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1021
  "blocks.3.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1022
  "blocks.3.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1023
  "blocks.3.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1024
  "blocks.30.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
@@ -1061,6 +1085,7 @@
1061
  "blocks.30.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1062
  "blocks.30.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1063
  "blocks.30.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
1064
  "blocks.30.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1065
  "blocks.30.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1066
  "blocks.31.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
@@ -1103,6 +1128,7 @@
1103
  "blocks.31.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1104
  "blocks.31.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1105
  "blocks.31.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
1106
  "blocks.31.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1107
  "blocks.31.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1108
  "blocks.32.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
@@ -1145,6 +1171,7 @@
1145
  "blocks.32.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1146
  "blocks.32.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1147
  "blocks.32.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1148
  "blocks.32.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1149
  "blocks.32.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1150
  "blocks.33.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
@@ -1187,6 +1214,7 @@
1187
  "blocks.33.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1188
  "blocks.33.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1189
  "blocks.33.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1190
  "blocks.33.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1191
  "blocks.33.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1192
  "blocks.34.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
@@ -1229,6 +1257,7 @@
1229
  "blocks.34.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1230
  "blocks.34.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1231
  "blocks.34.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1232
  "blocks.34.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1233
  "blocks.34.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1234
  "blocks.35.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
@@ -1271,6 +1300,7 @@
1271
  "blocks.35.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1272
  "blocks.35.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1273
  "blocks.35.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1274
  "blocks.35.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1275
  "blocks.35.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1276
  "blocks.36.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
@@ -1313,6 +1343,7 @@
1313
  "blocks.36.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1314
  "blocks.36.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1315
  "blocks.36.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1316
  "blocks.36.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1317
  "blocks.36.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1318
  "blocks.37.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
@@ -1355,6 +1386,7 @@
1355
  "blocks.37.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1356
  "blocks.37.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1357
  "blocks.37.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1358
  "blocks.37.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1359
  "blocks.37.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1360
  "blocks.38.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
@@ -1397,6 +1429,7 @@
1397
  "blocks.38.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1398
  "blocks.38.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1399
  "blocks.38.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1400
  "blocks.38.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1401
  "blocks.38.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1402
  "blocks.39.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
@@ -1439,6 +1472,7 @@
1439
  "blocks.39.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1440
  "blocks.39.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1441
  "blocks.39.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1442
  "blocks.39.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1443
  "blocks.39.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1444
  "blocks.4.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
@@ -1481,6 +1515,7 @@
1481
  "blocks.4.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1482
  "blocks.4.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1483
  "blocks.4.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1484
  "blocks.4.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1485
  "blocks.4.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1486
  "blocks.5.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
@@ -1523,6 +1558,7 @@
1523
  "blocks.5.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1524
  "blocks.5.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1525
  "blocks.5.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1526
  "blocks.5.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1527
  "blocks.5.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1528
  "blocks.6.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
@@ -1565,6 +1601,7 @@
1565
  "blocks.6.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1566
  "blocks.6.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1567
  "blocks.6.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1568
  "blocks.6.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1569
  "blocks.6.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1570
  "blocks.7.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
@@ -1607,6 +1644,7 @@
1607
  "blocks.7.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1608
  "blocks.7.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1609
  "blocks.7.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1610
  "blocks.7.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1611
  "blocks.7.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1612
  "blocks.8.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
@@ -1649,6 +1687,7 @@
1649
  "blocks.8.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1650
  "blocks.8.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1651
  "blocks.8.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1652
  "blocks.8.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1653
  "blocks.8.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1654
  "blocks.9.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
@@ -1691,6 +1730,7 @@
1691
  "blocks.9.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1692
  "blocks.9.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1693
  "blocks.9.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1694
  "blocks.9.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1695
  "blocks.9.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1696
  "head.head.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
53
  "blocks.0.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
54
  "blocks.0.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
55
  "blocks.0.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
56
+ "blocks.0.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
57
  "blocks.0.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
58
  "blocks.0.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
59
  "blocks.1.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
96
  "blocks.1.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
97
  "blocks.1.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
98
  "blocks.1.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
99
+ "blocks.1.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
100
  "blocks.1.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
101
  "blocks.1.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
102
  "blocks.10.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
139
  "blocks.10.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
140
  "blocks.10.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
141
  "blocks.10.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
142
+ "blocks.10.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
143
  "blocks.10.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
144
  "blocks.10.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
145
  "blocks.11.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
182
  "blocks.11.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
183
  "blocks.11.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
184
  "blocks.11.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
185
+ "blocks.11.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
186
  "blocks.11.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
187
  "blocks.11.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
188
  "blocks.12.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
225
  "blocks.12.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
226
  "blocks.12.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
227
  "blocks.12.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
228
+ "blocks.12.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
229
  "blocks.12.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
230
  "blocks.12.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
231
  "blocks.13.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
268
  "blocks.13.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
269
  "blocks.13.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
270
  "blocks.13.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
271
+ "blocks.13.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
272
  "blocks.13.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
273
  "blocks.13.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
274
  "blocks.14.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
311
  "blocks.14.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
312
  "blocks.14.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
313
  "blocks.14.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
314
+ "blocks.14.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
315
  "blocks.14.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
316
  "blocks.14.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
317
  "blocks.15.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
354
  "blocks.15.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
355
  "blocks.15.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
356
  "blocks.15.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
357
+ "blocks.15.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
358
  "blocks.15.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
359
  "blocks.15.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
360
  "blocks.16.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
397
  "blocks.16.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
398
  "blocks.16.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
399
  "blocks.16.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
400
+ "blocks.16.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
401
  "blocks.16.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
402
  "blocks.16.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
403
  "blocks.17.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
440
  "blocks.17.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
441
  "blocks.17.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
442
  "blocks.17.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
443
+ "blocks.17.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
444
  "blocks.17.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
445
  "blocks.17.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
446
  "blocks.18.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
483
  "blocks.18.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
484
  "blocks.18.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
485
  "blocks.18.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
486
+ "blocks.18.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
487
  "blocks.18.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
488
  "blocks.18.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
489
  "blocks.19.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
 
526
  "blocks.19.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
527
  "blocks.19.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
528
  "blocks.19.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
529
+ "blocks.19.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
530
  "blocks.19.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
531
  "blocks.19.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
532
  "blocks.2.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
569
  "blocks.2.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
570
  "blocks.2.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
571
  "blocks.2.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
572
+ "blocks.2.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
573
  "blocks.2.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
574
  "blocks.2.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
575
  "blocks.20.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
612
  "blocks.20.self_attn.o.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
613
  "blocks.20.self_attn.q.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
614
  "blocks.20.self_attn.q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
615
+ "blocks.20.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
616
  "blocks.20.self_attn.v.bias": "diffusion_pytorch_model-00002-of-00004.safetensors",
617
  "blocks.20.self_attn.v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
618
  "blocks.21.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
655
  "blocks.21.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
656
  "blocks.21.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
657
  "blocks.21.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
658
+ "blocks.21.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
659
  "blocks.21.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
660
  "blocks.21.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
661
  "blocks.22.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
698
  "blocks.22.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
699
  "blocks.22.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
700
  "blocks.22.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
701
+ "blocks.22.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
702
  "blocks.22.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
703
  "blocks.22.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
704
  "blocks.23.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
741
  "blocks.23.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
742
  "blocks.23.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
743
  "blocks.23.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
744
+ "blocks.23.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
745
  "blocks.23.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
746
  "blocks.23.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
747
  "blocks.24.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
784
  "blocks.24.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
785
  "blocks.24.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
786
  "blocks.24.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
787
+ "blocks.24.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
788
  "blocks.24.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
789
  "blocks.24.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
790
  "blocks.25.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
827
  "blocks.25.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
828
  "blocks.25.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
829
  "blocks.25.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
830
+ "blocks.25.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
831
  "blocks.25.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
832
  "blocks.25.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
833
  "blocks.26.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
870
  "blocks.26.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
871
  "blocks.26.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
872
  "blocks.26.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
873
+ "blocks.26.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
874
  "blocks.26.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
875
  "blocks.26.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
876
  "blocks.27.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
913
  "blocks.27.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
914
  "blocks.27.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
915
  "blocks.27.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
916
+ "blocks.27.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
917
  "blocks.27.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
918
  "blocks.27.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
919
  "blocks.28.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
956
  "blocks.28.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
957
  "blocks.28.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
958
  "blocks.28.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
959
+ "blocks.28.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
960
  "blocks.28.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
961
  "blocks.28.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
962
  "blocks.29.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
999
  "blocks.29.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1000
  "blocks.29.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1001
  "blocks.29.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1002
+ "blocks.29.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1003
  "blocks.29.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1004
  "blocks.29.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1005
  "blocks.3.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1042
  "blocks.3.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1043
  "blocks.3.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1044
  "blocks.3.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1045
+ "blocks.3.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1046
  "blocks.3.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1047
  "blocks.3.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1048
  "blocks.30.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
 
1085
  "blocks.30.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1086
  "blocks.30.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1087
  "blocks.30.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1088
+ "blocks.30.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1089
  "blocks.30.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1090
  "blocks.30.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1091
  "blocks.31.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1128
  "blocks.31.self_attn.o.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1129
  "blocks.31.self_attn.q.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1130
  "blocks.31.self_attn.q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1131
+ "blocks.31.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1132
  "blocks.31.self_attn.v.bias": "diffusion_pytorch_model-00003-of-00004.safetensors",
1133
  "blocks.31.self_attn.v.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
1134
  "blocks.32.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1171
  "blocks.32.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1172
  "blocks.32.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1173
  "blocks.32.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1174
+ "blocks.32.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1175
  "blocks.32.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1176
  "blocks.32.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1177
  "blocks.33.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1214
  "blocks.33.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1215
  "blocks.33.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1216
  "blocks.33.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1217
+ "blocks.33.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1218
  "blocks.33.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1219
  "blocks.33.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1220
  "blocks.34.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1257
  "blocks.34.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1258
  "blocks.34.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1259
  "blocks.34.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1260
+ "blocks.34.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1261
  "blocks.34.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1262
  "blocks.34.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1263
  "blocks.35.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1300
  "blocks.35.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1301
  "blocks.35.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1302
  "blocks.35.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1303
+ "blocks.35.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1304
  "blocks.35.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1305
  "blocks.35.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1306
  "blocks.36.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1343
  "blocks.36.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1344
  "blocks.36.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1345
  "blocks.36.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1346
+ "blocks.36.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1347
  "blocks.36.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1348
  "blocks.36.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1349
  "blocks.37.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1386
  "blocks.37.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1387
  "blocks.37.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1388
  "blocks.37.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1389
+ "blocks.37.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1390
  "blocks.37.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1391
  "blocks.37.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1392
  "blocks.38.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1429
  "blocks.38.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1430
  "blocks.38.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1431
  "blocks.38.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1432
+ "blocks.38.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1433
  "blocks.38.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1434
  "blocks.38.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1435
  "blocks.39.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
 
1472
  "blocks.39.self_attn.o.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1473
  "blocks.39.self_attn.q.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1474
  "blocks.39.self_attn.q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1475
+ "blocks.39.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1476
  "blocks.39.self_attn.v.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",
1477
  "blocks.39.self_attn.v.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
1478
  "blocks.4.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1515
  "blocks.4.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1516
  "blocks.4.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1517
  "blocks.4.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1518
+ "blocks.4.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1519
  "blocks.4.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1520
  "blocks.4.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1521
  "blocks.5.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1558
  "blocks.5.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1559
  "blocks.5.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1560
  "blocks.5.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1561
+ "blocks.5.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1562
  "blocks.5.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1563
  "blocks.5.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1564
  "blocks.6.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1601
  "blocks.6.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1602
  "blocks.6.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1603
  "blocks.6.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1604
+ "blocks.6.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1605
  "blocks.6.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1606
  "blocks.6.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1607
  "blocks.7.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1644
  "blocks.7.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1645
  "blocks.7.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1646
  "blocks.7.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1647
+ "blocks.7.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1648
  "blocks.7.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1649
  "blocks.7.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1650
  "blocks.8.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1687
  "blocks.8.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1688
  "blocks.8.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1689
  "blocks.8.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1690
+ "blocks.8.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1691
  "blocks.8.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1692
  "blocks.8.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1693
  "blocks.9.audio_cross_attn.kv_linear.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
 
1730
  "blocks.9.self_attn.o.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1731
  "blocks.9.self_attn.q.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1732
  "blocks.9.self_attn.q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1733
+ "blocks.9.self_attn.te_dpa._extra_state": "diffusion_pytorch_model-00001-of-00004.safetensors",
1734
  "blocks.9.self_attn.v.bias": "diffusion_pytorch_model-00001-of-00004.safetensors",
1735
  "blocks.9.self_attn.v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
1736
  "head.head.bias": "diffusion_pytorch_model-00004-of-00004.safetensors",