forked from yisol/IDM-VTON
-
Notifications
You must be signed in to change notification settings - Fork 7
/
com.log
401 lines (401 loc) · 18.5 KB
/
com.log
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
Compare UNet2DConditionModel(
(conv_in): Conv2d(9, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_proj): Timesteps()
(time_embedding): TimestepEmbedding(
(linear_1): Linear(in_features=320, out_features=1280, bias=True)
(act): SiLU()
(linear_2): Linear(in_features=1280, out_features=1280, bias=True)
)
(add_time_proj): Timesteps()
(add_embedding): TimestepEmbedding(
(linear_1): Linear(in_features=2816, out_features=1280, bias=True)
(act): SiLU()
(linear_2): Linear(in_features=1280, out_features=1280, bias=True)
)
(down_blocks): ModuleList(
(0): DownBlock2D(
(resnets): ModuleList(
(0-1): 2 x ResnetBlock2D(
(norm1): GroupNorm(32, 320, eps=1e-05, affine=True)
(conv1): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=320, bias=True)
(norm2): GroupNorm(32, 320, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
(downsamplers): ModuleList(
(0): Downsample2D(
(conv): Conv2d(320, 320, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
)
)
(1): CrossAttnDownBlock2D(
(attentions): ModuleList(
(0-1): 2 x Transformer2DModel(
(norm): GroupNorm(32, 640, eps=1e-06, affine=True)
(proj_in): Linear(in_features=640, out_features=640, bias=True)
(transformer_blocks): ModuleList(
(0-1): 2 x BasicTransformerBlock(
(norm1): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
(attn1): Attention(
(to_q): Linear(in_features=640, out_features=640, bias=False)
(to_k): Linear(in_features=640, out_features=640, bias=False)
(to_v): Linear(in_features=640, out_features=640, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=640, out_features=640, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm2): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
(attn2): Attention(
(to_q): Linear(in_features=640, out_features=640, bias=False)
(to_k): Linear(in_features=2048, out_features=640, bias=False)
(to_v): Linear(in_features=2048, out_features=640, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=640, out_features=640, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm3): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
(ff): FeedForward(
(net): ModuleList(
(0): GEGLU(
(proj): Linear(in_features=640, out_features=5120, bias=True)
)
(1): Dropout(p=0.0, inplace=False)
(2): Linear(in_features=2560, out_features=640, bias=True)
)
)
)
)
(proj_out): Linear(in_features=640, out_features=640, bias=True)
)
)
(resnets): ModuleList(
(0): ResnetBlock2D(
(norm1): GroupNorm(32, 320, eps=1e-05, affine=True)
(conv1): Conv2d(320, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=640, bias=True)
(norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(320, 640, kernel_size=(1, 1), stride=(1, 1))
)
(1): ResnetBlock2D(
(norm1): GroupNorm(32, 640, eps=1e-05, affine=True)
(conv1): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=640, bias=True)
(norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
(downsamplers): ModuleList(
(0): Downsample2D(
(conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
)
)
(2): CrossAttnDownBlock2D(
(attentions): ModuleList(
(0-1): 2 x Transformer2DModel(
(norm): GroupNorm(32, 1280, eps=1e-06, affine=True)
(proj_in): Linear(in_features=1280, out_features=1280, bias=True)
(transformer_blocks): ModuleList(
(0-9): 10 x BasicTransformerBlock(
(norm1): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
(attn1): Attention(
(to_q): Linear(in_features=1280, out_features=1280, bias=False)
(to_k): Linear(in_features=1280, out_features=1280, bias=False)
(to_v): Linear(in_features=1280, out_features=1280, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=1280, out_features=1280, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm2): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
(attn2): Attention(
(to_q): Linear(in_features=1280, out_features=1280, bias=False)
(to_k): Linear(in_features=2048, out_features=1280, bias=False)
(to_v): Linear(in_features=2048, out_features=1280, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=1280, out_features=1280, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm3): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
(ff): FeedForward(
(net): ModuleList(
(0): GEGLU(
(proj): Linear(in_features=1280, out_features=10240, bias=True)
)
(1): Dropout(p=0.0, inplace=False)
(2): Linear(in_features=5120, out_features=1280, bias=True)
)
)
)
)
(proj_out): Linear(in_features=1280, out_features=1280, bias=True)
)
)
(resnets): ModuleList(
(0): ResnetBlock2D(
(norm1): GroupNorm(32, 640, eps=1e-05, affine=True)
(conv1): Conv2d(640, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=1280, bias=True)
(norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(640, 1280, kernel_size=(1, 1), stride=(1, 1))
)
(1): ResnetBlock2D(
(norm1): GroupNorm(32, 1280, eps=1e-05, affine=True)
(conv1): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=1280, bias=True)
(norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
)
)
(up_blocks): ModuleList(
(0): CrossAttnUpBlock2D(
(attentions): ModuleList(
(0-2): 3 x Transformer2DModel(
(norm): GroupNorm(32, 1280, eps=1e-06, affine=True)
(proj_in): Linear(in_features=1280, out_features=1280, bias=True)
(transformer_blocks): ModuleList(
(0-9): 10 x BasicTransformerBlock(
(norm1): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
(attn1): Attention(
(to_q): Linear(in_features=1280, out_features=1280, bias=False)
(to_k): Linear(in_features=1280, out_features=1280, bias=False)
(to_v): Linear(in_features=1280, out_features=1280, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=1280, out_features=1280, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm2): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
(attn2): Attention(
(to_q): Linear(in_features=1280, out_features=1280, bias=False)
(to_k): Linear(in_features=2048, out_features=1280, bias=False)
(to_v): Linear(in_features=2048, out_features=1280, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=1280, out_features=1280, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm3): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
(ff): FeedForward(
(net): ModuleList(
(0): GEGLU(
(proj): Linear(in_features=1280, out_features=10240, bias=True)
)
(1): Dropout(p=0.0, inplace=False)
(2): Linear(in_features=5120, out_features=1280, bias=True)
)
)
)
)
(proj_out): Linear(in_features=1280, out_features=1280, bias=True)
)
)
(resnets): ModuleList(
(0-1): 2 x ResnetBlock2D(
(norm1): GroupNorm(32, 2560, eps=1e-05, affine=True)
(conv1): Conv2d(2560, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=1280, bias=True)
(norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(2560, 1280, kernel_size=(1, 1), stride=(1, 1))
)
(2): ResnetBlock2D(
(norm1): GroupNorm(32, 1920, eps=1e-05, affine=True)
(conv1): Conv2d(1920, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=1280, bias=True)
(norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(1920, 1280, kernel_size=(1, 1), stride=(1, 1))
)
)
(upsamplers): ModuleList(
(0): Upsample2D(
(conv): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
)
(1): CrossAttnUpBlock2D(
(attentions): ModuleList(
(0-2): 3 x Transformer2DModel(
(norm): GroupNorm(32, 640, eps=1e-06, affine=True)
(proj_in): Linear(in_features=640, out_features=640, bias=True)
(transformer_blocks): ModuleList(
(0-1): 2 x BasicTransformerBlock(
(norm1): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
(attn1): Attention(
(to_q): Linear(in_features=640, out_features=640, bias=False)
(to_k): Linear(in_features=640, out_features=640, bias=False)
(to_v): Linear(in_features=640, out_features=640, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=640, out_features=640, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm2): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
(attn2): Attention(
(to_q): Linear(in_features=640, out_features=640, bias=False)
(to_k): Linear(in_features=2048, out_features=640, bias=False)
(to_v): Linear(in_features=2048, out_features=640, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=640, out_features=640, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm3): LayerNorm((640,), eps=1e-05, elementwise_affine=True)
(ff): FeedForward(
(net): ModuleList(
(0): GEGLU(
(proj): Linear(in_features=640, out_features=5120, bias=True)
)
(1): Dropout(p=0.0, inplace=False)
(2): Linear(in_features=2560, out_features=640, bias=True)
)
)
)
)
(proj_out): Linear(in_features=640, out_features=640, bias=True)
)
)
(resnets): ModuleList(
(0): ResnetBlock2D(
(norm1): GroupNorm(32, 1920, eps=1e-05, affine=True)
(conv1): Conv2d(1920, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=640, bias=True)
(norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(1920, 640, kernel_size=(1, 1), stride=(1, 1))
)
(1): ResnetBlock2D(
(norm1): GroupNorm(32, 1280, eps=1e-05, affine=True)
(conv1): Conv2d(1280, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=640, bias=True)
(norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(1280, 640, kernel_size=(1, 1), stride=(1, 1))
)
(2): ResnetBlock2D(
(norm1): GroupNorm(32, 960, eps=1e-05, affine=True)
(conv1): Conv2d(960, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=640, bias=True)
(norm2): GroupNorm(32, 640, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(960, 640, kernel_size=(1, 1), stride=(1, 1))
)
)
(upsamplers): ModuleList(
(0): Upsample2D(
(conv): Conv2d(640, 640, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
)
)
(2): UpBlock2D(
(resnets): ModuleList(
(0): ResnetBlock2D(
(norm1): GroupNorm(32, 960, eps=1e-05, affine=True)
(conv1): Conv2d(960, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=320, bias=True)
(norm2): GroupNorm(32, 320, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(960, 320, kernel_size=(1, 1), stride=(1, 1))
)
(1-2): 2 x ResnetBlock2D(
(norm1): GroupNorm(32, 640, eps=1e-05, affine=True)
(conv1): Conv2d(640, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=320, bias=True)
(norm2): GroupNorm(32, 320, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(320, 320, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
(conv_shortcut): Conv2d(640, 320, kernel_size=(1, 1), stride=(1, 1))
)
)
)
)
(mid_block): UNetMidBlock2DCrossAttn(
(attentions): ModuleList(
(0): Transformer2DModel(
(norm): GroupNorm(32, 1280, eps=1e-06, affine=True)
(proj_in): Linear(in_features=1280, out_features=1280, bias=True)
(transformer_blocks): ModuleList(
(0-9): 10 x BasicTransformerBlock(
(norm1): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
(attn1): Attention(
(to_q): Linear(in_features=1280, out_features=1280, bias=False)
(to_k): Linear(in_features=1280, out_features=1280, bias=False)
(to_v): Linear(in_features=1280, out_features=1280, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=1280, out_features=1280, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm2): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
(attn2): Attention(
(to_q): Linear(in_features=1280, out_features=1280, bias=False)
(to_k): Linear(in_features=2048, out_features=1280, bias=False)
(to_v): Linear(in_features=2048, out_features=1280, bias=False)
(to_out): ModuleList(
(0): Linear(in_features=1280, out_features=1280, bias=True)
(1): Dropout(p=0.0, inplace=False)
)
)
(norm3): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
(ff): FeedForward(
(net): ModuleList(
(0): GEGLU(
(proj): Linear(in_features=1280, out_features=10240, bias=True)
)
(1): Dropout(p=0.0, inplace=False)
(2): Linear(in_features=5120, out_features=1280, bias=True)
)
)
)
)
(proj_out): Linear(in_features=1280, out_features=1280, bias=True)
)
)
(resnets): ModuleList(
(0-1): 2 x ResnetBlock2D(
(norm1): GroupNorm(32, 1280, eps=1e-05, affine=True)
(conv1): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(time_emb_proj): Linear(in_features=1280, out_features=1280, bias=True)
(norm2): GroupNorm(32, 1280, eps=1e-05, affine=True)
(dropout): Dropout(p=0.0, inplace=False)
(conv2): Conv2d(1280, 1280, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(nonlinearity): SiLU()
)
)
)
(conv_norm_out): GroupNorm(32, 320, eps=1e-05, affine=True)
(conv_act): SiLU()
(conv_out): Conv2d(320, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)