Junhao233 commited on
Commit
0ea34b3
1 Parent(s): c3f4d04
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPImageProcessor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
model_index.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "TextToVideoIFInterpPipeline",
3
+ "_diffusers_version": "0.19.3",
4
+ "_name_or_path": "show-1-interpolation",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "scheduler": [
10
+ "diffusers",
11
+ "DPMSolverMultistepScheduler"
12
+ ],
13
+ "text_encoder": [
14
+ "transformers",
15
+ "T5EncoderModel"
16
+ ],
17
+ "tokenizer": [
18
+ "transformers",
19
+ "T5Tokenizer"
20
+ ],
21
+ "unet": [
22
+ "showone.models.unet_3d_condition",
23
+ "UNet3DConditionModel"
24
+ ]
25
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DPMSolverMultistepScheduler",
3
+ "_diffusers_version": "0.19.3",
4
+ "algorithm_type": "dpmsolver++",
5
+ "beta_end": 0.02,
6
+ "beta_schedule": "squaredcos_cap_v2",
7
+ "beta_start": 0.0001,
8
+ "clip_sample": true,
9
+ "clip_sample_range": 1.0,
10
+ "dynamic_thresholding_ratio": 0.95,
11
+ "lambda_min_clipped": -5.1,
12
+ "lower_order_final": true,
13
+ "num_train_timesteps": 1000,
14
+ "prediction_type": "epsilon",
15
+ "sample_max_value": 1.5,
16
+ "solver_order": 2,
17
+ "solver_type": "midpoint",
18
+ "steps_offset": 0,
19
+ "thresholding": true,
20
+ "timestep_spacing": "linspace",
21
+ "trained_betas": null,
22
+ "use_karras_sigmas": false,
23
+ "variance_type": "learned_range"
24
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/efs/home/jarvis/models/IF-I-L-v1.0/text_encoder",
3
+ "architectures": [
4
+ "T5EncoderModel"
5
+ ],
6
+ "d_ff": 10240,
7
+ "d_kv": 64,
8
+ "d_model": 4096,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "num_decoder_layers": 24,
20
+ "num_heads": 64,
21
+ "num_layers": 24,
22
+ "output_past": true,
23
+ "pad_token_id": 0,
24
+ "relative_attention_max_distance": 128,
25
+ "relative_attention_num_buckets": 32,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.29.1",
29
+ "use_cache": true,
30
+ "vocab_size": 32128
31
+ }
text_encoder/pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08a84d346b5f7c04036082364c0b4e74a754e62ea546de5bcf9949206b0b9719
3
+ size 9725939183
text_encoder/pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abdda89634be180596b30a7c369ab01ea09a9b18a603f9581f83ac8a4b85fbe2
3
+ size 1812025029
text_encoder/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,227 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11801079808
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
19
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
20
+ "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
23
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
24
+ "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
25
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
26
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
27
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
28
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
29
+ "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
30
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
31
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
32
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
33
+ "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
34
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
35
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
36
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
37
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
38
+ "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
40
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
41
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
42
+ "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
44
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
45
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
46
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
47
+ "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
48
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
49
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
50
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
51
+ "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
52
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
53
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
54
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
55
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
56
+ "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
58
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
59
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
60
+ "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
61
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
62
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
63
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
64
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
65
+ "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
66
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
67
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
68
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
69
+ "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
70
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
71
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
72
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
73
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
74
+ "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
76
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
77
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
78
+ "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
79
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
80
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
81
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
82
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
83
+ "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
84
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
85
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
86
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
87
+ "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
88
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
89
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
90
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
91
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
92
+ "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
94
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
95
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
96
+ "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
97
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
98
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
99
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
100
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
101
+ "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
102
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
103
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
104
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
105
+ "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
106
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
107
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
108
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
109
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
110
+ "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
111
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
112
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
113
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
114
+ "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
115
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
116
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
117
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
118
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
119
+ "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
120
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
121
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
122
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
123
+ "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
124
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
125
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
126
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
127
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
128
+ "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
129
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
130
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
131
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
132
+ "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
133
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
134
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
135
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
136
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
137
+ "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
138
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
139
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
140
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
141
+ "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
142
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
143
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
144
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
145
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
146
+ "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
147
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
148
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
149
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
150
+ "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
151
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
152
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
153
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
154
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
155
+ "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
156
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
157
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
158
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
159
+ "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
160
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
161
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
162
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
163
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
164
+ "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
165
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
166
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
167
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
168
+ "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
169
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
170
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
171
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
172
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
173
+ "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
174
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
175
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
176
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
177
+ "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
178
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
179
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
180
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
181
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
182
+ "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
183
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
184
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
185
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
186
+ "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
187
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
188
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
189
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
190
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
191
+ "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
192
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
193
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
194
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
195
+ "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
196
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
197
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
198
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
199
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
200
+ "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
201
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
202
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
203
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
204
+ "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
205
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
206
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
207
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
208
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
209
+ "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
210
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
211
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
212
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
213
+ "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
214
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
215
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
216
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
217
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
218
+ "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
219
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
220
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
221
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
222
+ "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
223
+ "encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
224
+ "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
225
+ "shared.weight": "pytorch_model-00001-of-00002.bin"
226
+ }
227
+ }
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
tokenizer/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
unet/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet3DConditionModel",
3
+ "_diffusers_version": "0.19.3",
4
+ "act_fn": "gelu",
5
+ "addition_embed_type": "text",
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
+ "attention_head_dim": 64,
9
+ "block_out_channels": [
10
+ 320,
11
+ 640,
12
+ 960,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 1280,
21
+ "cross_attention_norm": "group_norm",
22
+ "down_block_types": [
23
+ "ResnetDownsampleBlock3D",
24
+ "SimpleCrossAttnDownBlock3D",
25
+ "SimpleCrossAttnDownBlock3D",
26
+ "SimpleCrossAttnDownBlock3D"
27
+ ],
28
+ "downsample_padding": 1,
29
+ "dual_cross_attention": false,
30
+ "encoder_hid_dim": 4096,
31
+ "encoder_hid_dim_type": "text_proj",
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 7,
35
+ "layers_per_block": 3,
36
+ "mid_block_only_cross_attention": null,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock3DSimpleCrossAttn",
39
+ "norm_eps": 1e-05,
40
+ "norm_num_groups": 32,
41
+ "num_attention_heads": null,
42
+ "num_class_embeds": null,
43
+ "only_cross_attention": false,
44
+ "out_channels": 6,
45
+ "projection_class_embeddings_input_dim": null,
46
+ "resnet_out_scale_factor": 1.0,
47
+ "resnet_skip_time_act": false,
48
+ "resnet_time_scale_shift": "scale_shift",
49
+ "sample_size": 64,
50
+ "time_cond_proj_dim": null,
51
+ "time_embedding_act_fn": null,
52
+ "time_embedding_dim": null,
53
+ "time_embedding_type": "positional",
54
+ "timestep_post_act": null,
55
+ "transformer_layers_per_block": 1,
56
+ "transfromer_in_opt": false,
57
+ "up_block_types": [
58
+ "SimpleCrossAttnUpBlock3D",
59
+ "SimpleCrossAttnUpBlock3D",
60
+ "SimpleCrossAttnUpBlock3D",
61
+ "ResnetUpsampleBlock3D"
62
+ ],
63
+ "upcast_attention": false,
64
+ "use_linear_projection": false
65
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d673e9c15f0d46df802afc6dd60ac147e5363ed5e17c7b58211e3f793acc2a
3
+ size 3454460358