Add Diffusers weights

#9
by anzorq - opened
feature_extractor/preprocessor_config.json CHANGED
@@ -1,8 +1,12 @@
1
  {
2
- "crop_size": 224,
 
 
 
3
  "do_center_crop": true,
4
  "do_convert_rgb": true,
5
  "do_normalize": true,
 
6
  "do_resize": true,
7
  "feature_extractor_type": "CLIPFeatureExtractor",
8
  "image_mean": [
@@ -10,11 +14,15 @@
10
  0.4578275,
11
  0.40821073
12
  ],
 
13
  "image_std": [
14
  0.26862954,
15
  0.26130258,
16
  0.27577711
17
  ],
18
  "resample": 3,
19
- "size": 224
 
 
 
20
  }
 
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": [
 
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 CHANGED
@@ -1,13 +1,18 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.8.0.dev0",
4
  "feature_extractor": [
5
  "transformers",
6
- "CLIPFeatureExtractor"
 
 
 
 
 
7
  ],
8
  "scheduler": [
9
  "diffusers",
10
- "DDIMScheduler"
11
  ],
12
  "text_encoder": [
13
  "transformers",
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.9.0",
4
  "feature_extractor": [
5
  "transformers",
6
+ "CLIPImageProcessor"
7
+ ],
8
+ "requires_safety_checker": true,
9
+ "safety_checker": [
10
+ "stable_diffusion",
11
+ "StableDiffusionSafetyChecker"
12
  ],
13
  "scheduler": [
14
  "diffusers",
15
+ "PNDMScheduler"
16
  ],
17
  "text_encoder": [
18
  "transformers",
safety_checker/config.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
3
+ "_name_or_path": "CompVis/stable-diffusion-safety-checker",
4
+ "architectures": [
5
+ "StableDiffusionSafetyChecker"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "clip",
10
+ "projection_dim": 768,
11
+ "text_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_dropout": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "dropout": 0.0,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 77,
51
+ "min_length": 0,
52
+ "model_type": "clip_text_model",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "projection_dim": 512,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.25.0.dev0",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "text_config_dict": {
89
+ "hidden_size": 768,
90
+ "intermediate_size": 3072,
91
+ "num_attention_heads": 12,
92
+ "num_hidden_layers": 12
93
+ },
94
+ "torch_dtype": "float32",
95
+ "transformers_version": null,
96
+ "vision_config": {
97
+ "_name_or_path": "",
98
+ "add_cross_attention": false,
99
+ "architectures": null,
100
+ "attention_dropout": 0.0,
101
+ "bad_words_ids": null,
102
+ "begin_suppress_tokens": null,
103
+ "bos_token_id": null,
104
+ "chunk_size_feed_forward": 0,
105
+ "cross_attention_hidden_size": null,
106
+ "decoder_start_token_id": null,
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "dropout": 0.0,
110
+ "early_stopping": false,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "hidden_act": "quick_gelu",
118
+ "hidden_size": 1024,
119
+ "id2label": {
120
+ "0": "LABEL_0",
121
+ "1": "LABEL_1"
122
+ },
123
+ "image_size": 224,
124
+ "initializer_factor": 1.0,
125
+ "initializer_range": 0.02,
126
+ "intermediate_size": 4096,
127
+ "is_decoder": false,
128
+ "is_encoder_decoder": false,
129
+ "label2id": {
130
+ "LABEL_0": 0,
131
+ "LABEL_1": 1
132
+ },
133
+ "layer_norm_eps": 1e-05,
134
+ "length_penalty": 1.0,
135
+ "max_length": 20,
136
+ "min_length": 0,
137
+ "model_type": "clip_vision_model",
138
+ "no_repeat_ngram_size": 0,
139
+ "num_attention_heads": 16,
140
+ "num_beam_groups": 1,
141
+ "num_beams": 1,
142
+ "num_channels": 3,
143
+ "num_hidden_layers": 24,
144
+ "num_return_sequences": 1,
145
+ "output_attentions": false,
146
+ "output_hidden_states": false,
147
+ "output_scores": false,
148
+ "pad_token_id": null,
149
+ "patch_size": 14,
150
+ "prefix": null,
151
+ "problem_type": null,
152
+ "projection_dim": 512,
153
+ "pruned_heads": {},
154
+ "remove_invalid_values": false,
155
+ "repetition_penalty": 1.0,
156
+ "return_dict": true,
157
+ "return_dict_in_generate": false,
158
+ "sep_token_id": null,
159
+ "suppress_tokens": null,
160
+ "task_specific_params": null,
161
+ "temperature": 1.0,
162
+ "tf_legacy_loss": false,
163
+ "tie_encoder_decoder": false,
164
+ "tie_word_embeddings": true,
165
+ "tokenizer_class": null,
166
+ "top_k": 50,
167
+ "top_p": 1.0,
168
+ "torch_dtype": null,
169
+ "torchscript": false,
170
+ "transformers_version": "4.25.0.dev0",
171
+ "typical_p": 1.0,
172
+ "use_bfloat16": false
173
+ },
174
+ "vision_config_dict": {
175
+ "hidden_size": 1024,
176
+ "intermediate_size": 4096,
177
+ "num_attention_heads": 16,
178
+ "num_hidden_layers": 24,
179
+ "patch_size": 14
180
+ }
181
+ }
safety_checker/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
+ size 1216064769
scheduler/scheduler_config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_class_name": "DDIMScheduler",
3
- "_diffusers_version": "0.8.0.dev0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
7
- "clip_sample": false,
8
  "num_train_timesteps": 1000,
9
  "set_alpha_to_one": false,
 
10
  "steps_offset": 1,
11
  "trained_betas": null
12
  }
 
1
  {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.9.0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
 
7
  "num_train_timesteps": 1000,
8
  "set_alpha_to_one": false,
9
+ "skip_prk_steps": true,
10
  "steps_offset": 1,
11
  "trained_betas": null
12
  }
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "runwayml/stable-diffusion-v1-5",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -20,6 +20,6 @@
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.24.0",
24
  "vocab_size": 49408
25
  }
 
1
  {
2
+ "_name_or_path": "openai/clip-vit-large-patch14",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.25.0.dev0",
24
  "vocab_size": 49408
25
  }
text_encoder/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4690e6e394a693b4743aba98e1961689b2cede0a449707ea63f50e21123d39ae
3
- size 492308087
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7dd4a7aca273de9a428a44e30f5fc74371bf947fa59f67671fb0cf9307e85df
3
+ size 492307041
tokenizer/tokenizer_config.json CHANGED
@@ -19,7 +19,7 @@
19
  },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
- "name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/3beed0bcb34a3d281ce27bd8a6a1efbb68eada38/tokenizer",
23
  "pad_token": "<|endoftext|>",
24
  "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
 
19
  },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
+ "name_or_path": "openai/clip-vit-large-patch14",
23
  "pad_token": "<|endoftext|>",
24
  "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
unet/config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.8.0.dev0",
4
- "_name_or_path": "runwayml/stable-diffusion-v1-5",
5
  "act_fn": "silu",
6
  "attention_head_dim": 8,
7
  "block_out_channels": [
@@ -19,6 +18,7 @@
19
  "DownBlock2D"
20
  ],
21
  "downsample_padding": 1,
 
22
  "flip_sin_to_cos": true,
23
  "freq_shift": 0,
24
  "in_channels": 4,
@@ -26,6 +26,8 @@
26
  "mid_block_scale_factor": 1,
27
  "norm_eps": 1e-05,
28
  "norm_num_groups": 32,
 
 
29
  "out_channels": 4,
30
  "sample_size": 64,
31
  "up_block_types": [
@@ -33,5 +35,6 @@
33
  "CrossAttnUpBlock2D",
34
  "CrossAttnUpBlock2D",
35
  "CrossAttnUpBlock2D"
36
- ]
 
37
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.9.0",
 
4
  "act_fn": "silu",
5
  "attention_head_dim": 8,
6
  "block_out_channels": [
 
18
  "DownBlock2D"
19
  ],
20
  "downsample_padding": 1,
21
+ "dual_cross_attention": false,
22
  "flip_sin_to_cos": true,
23
  "freq_shift": 0,
24
  "in_channels": 4,
 
26
  "mid_block_scale_factor": 1,
27
  "norm_eps": 1e-05,
28
  "norm_num_groups": 32,
29
+ "num_class_embeds": null,
30
+ "only_cross_attention": false,
31
  "out_channels": 4,
32
  "sample_size": 64,
33
  "up_block_types": [
 
35
  "CrossAttnUpBlock2D",
36
  "CrossAttnUpBlock2D",
37
  "CrossAttnUpBlock2D"
38
+ ],
39
+ "use_linear_projection": false
40
  }
unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d32f017b0f6c544453e23316d18b1f9a0e94fbe54a37661de0be312febe63101
3
- size 3438364325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de30f96af7d8b31295fbe3775d478ffd91c02c4d7bde8842a88abc473b0a8f6
3
+ size 3438366373
vae/config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.8.0.dev0",
4
- "_name_or_path": "stabilityai/sd-vae-ft-mse",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.9.0",
 
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
vae/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
3
- size 334707217
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf4507d99b88db73f3916e2a20169fe74ada6b5582e9af56cfa80f5f3141765
3
+ size 334711857