xingchaoliu commited on
Commit
ecd0380
1 Parent(s): c433b69
README.md DELETED
@@ -1,5 +0,0 @@
1
- ---
2
- license: other
3
- license_name: tencent-hunyuan-community
4
- license_link: https://huggingface.co/Tencent-Hunyuan/HunyuanDiT/blob/main/LICENSE.txt
5
- ---
 
 
 
 
 
 
model_index.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "HunyuanDiTPipeline",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "Tencent-Hunyuan/HunyuanDiT-Diffusers",
5
+ "feature_extractor": [
6
+ null,
7
+ null
8
+ ],
9
+ "requires_safety_checker": true,
10
+ "safety_checker": [
11
+ null,
12
+ null
13
+ ],
14
+ "scheduler": [
15
+ "diffusers",
16
+ "DDPMScheduler"
17
+ ],
18
+ "text_encoder": [
19
+ "transformers",
20
+ "BertModel"
21
+ ],
22
+ "text_encoder_2": [
23
+ "transformers",
24
+ "T5EncoderModel"
25
+ ],
26
+ "tokenizer": [
27
+ "transformers",
28
+ "BertTokenizer"
29
+ ],
30
+ "tokenizer_2": [
31
+ "transformers",
32
+ "T5Tokenizer"
33
+ ],
34
+ "transformer": [
35
+ "diffusers",
36
+ "HunyuanDiT2DModel"
37
+ ],
38
+ "vae": [
39
+ "diffusers",
40
+ "AutoencoderKL"
41
+ ]
42
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDPMScheduler",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "beta_end": 0.02,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "v_prediction",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "skip_prk_steps": true,
16
+ "steps_offset": 1,
17
+ "thresholding": false,
18
+ "timestep_spacing": "leading",
19
+ "trained_betas": null,
20
+ "variance_type": "fixed_small"
21
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "pooler_fc_size": 768,
23
+ "pooler_num_attention_heads": 12,
24
+ "pooler_num_fc_layers": 3,
25
+ "pooler_size_per_head": 128,
26
+ "pooler_type": "first_token_transform",
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.41.1",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 47020
33
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c6348af2cb4d5852fe51102ce39605903dbe7925c005cf8995506cc21ea914
3
+ size 1408188288
text_encoder_2/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5EncoderModel"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 5120,
7
+ "d_kv": 64,
8
+ "d_model": 2048,
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": 32,
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
+ "tokenizer_class": "T5Tokenizer",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.41.1",
30
+ "use_cache": true,
31
+ "vocab_size": 250112
32
+ }
text_encoder_2/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c0c539ab8e8fba3877cc94bc483e427f74c525f817a809b028ebc8d96d75a94
3
+ size 4993585936
text_encoder_2/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b49976cb1fe40da28a600d783f4686024c97eb01f224c54305cce55ddcd8a5e
3
+ size 1686275552
text_encoder_2/model.safetensors.index.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6679834624
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
19
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
20
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
21
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
23
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
24
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
25
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
26
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
27
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
28
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
29
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
30
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
31
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
32
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
33
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
34
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
35
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
36
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
37
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
38
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
39
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
40
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
41
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
42
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
43
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
44
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
45
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
46
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
47
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
48
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
49
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
50
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
51
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
52
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
53
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
54
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
55
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
56
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
57
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
58
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
59
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
60
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
61
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
62
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
63
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
64
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
65
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
66
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
67
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
68
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
69
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
70
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
71
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
72
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
73
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
74
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
75
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
76
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
77
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
78
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
79
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
80
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
81
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
82
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
83
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
84
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
85
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
86
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
87
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
88
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
89
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
90
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
91
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
92
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
93
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
94
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
95
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
96
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
97
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
98
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
99
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
100
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
101
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
102
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
103
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
104
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
105
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
106
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
107
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
108
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
109
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
110
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
111
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
112
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
113
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
114
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
115
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
116
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
117
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
118
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
119
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
120
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
121
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
122
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
123
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
124
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
125
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
126
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
127
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
128
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
129
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
130
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
131
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
132
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
133
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
134
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
135
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
136
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
137
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
138
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
139
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
140
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
141
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
142
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
143
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
144
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
145
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
146
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
147
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
148
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
149
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
150
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
151
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
152
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
153
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
154
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
155
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
156
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
157
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
158
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
159
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
160
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
161
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
162
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
163
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
164
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
165
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
166
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
167
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
168
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
169
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
170
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
171
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
172
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
173
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
174
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
175
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
176
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
177
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
178
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
179
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
180
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
181
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
182
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
183
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
184
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
185
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
186
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
187
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
188
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
189
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
190
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
191
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
192
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
193
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
194
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
195
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
196
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
197
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
198
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
199
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
200
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
201
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
202
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
203
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
204
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
205
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
206
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
207
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
208
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
209
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
210
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
211
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
212
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
213
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
214
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
215
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
216
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
217
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
218
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
219
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
220
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
221
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
222
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
223
+ "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
224
+ "shared.weight": "model-00001-of-00002.safetensors"
225
+ }
226
+ }
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 77,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_2/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer_2/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer_2/tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [],
30
+ "clean_up_tokenization_spaces": true,
31
+ "eos_token": "</s>",
32
+ "extra_ids": 0,
33
+ "legacy": true,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<pad>",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "T5Tokenizer",
38
+ "unk_token": "<unk>"
39
+ }
transformer/config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "HunyuanDiT2DModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "activation_fn": "gelu-approximate",
5
+ "attention_head_dim": 88,
6
+ "cross_attention_dim": 1024,
7
+ "cross_attention_dim_t5": 2048,
8
+ "hidden_size": 1408,
9
+ "in_channels": 4,
10
+ "learn_sigma": true,
11
+ "mlp_ratio": 4.3637,
12
+ "norm_type": "layer_norm",
13
+ "num_attention_heads": 16,
14
+ "num_layers": 40,
15
+ "patch_size": 2,
16
+ "pooled_projection_dim": 1024,
17
+ "sample_size": 128,
18
+ "text_len": 77,
19
+ "text_len_t5": 256,
20
+ "use_style_cond_and_image_meta_size": false
21
+ }
transformer/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af0239f15b91e424160581963873466b0eb673993b952a16e5a54ae18d521a1c
3
+ size 5999962656
vae/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "act_fn": "silu",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 512,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "DownEncoderBlock2D",
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D"
16
+ ],
17
+ "force_upcast": false,
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "latents_mean": null,
21
+ "latents_std": null,
22
+ "layers_per_block": 2,
23
+ "norm_num_groups": 32,
24
+ "out_channels": 3,
25
+ "sample_size": 512,
26
+ "scaling_factor": 0.13025,
27
+ "shift_factor": null,
28
+ "up_block_types": [
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D",
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D"
33
+ ],
34
+ "use_post_quant_conv": true,
35
+ "use_quant_conv": true
36
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a14dc6fe8d71c83576f135a87c61a16561c9c080abba418d2cc976ee034f88
3
+ size 334643268