JosefJilek commited on
Commit
9298603
1 Parent(s): e2171f8

Diffusers - V0.5.3

Browse files
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": "CLIPFeatureExtractor",
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
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",
19
+ "CLIPTextModel"
20
+ ],
21
+ "tokenizer": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": 2,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "quick_gelu",
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_factor": 1.0,
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "is_decoder": false,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "layer_norm_eps": 1e-05,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 77,
50
+ "min_length": 0,
51
+ "model_type": "clip_text_model",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 12,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_hidden_layers": 12,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "pad_token_id": 1,
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "projection_dim": 512,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sep_token_id": null,
71
+ "suppress_tokens": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.27.0.dev0",
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "vocab_size": 49408
86
+ },
87
+ "text_config_dict": {
88
+ "hidden_size": 768,
89
+ "intermediate_size": 3072,
90
+ "num_attention_heads": 12,
91
+ "num_hidden_layers": 12
92
+ },
93
+ "torch_dtype": "float32",
94
+ "transformers_version": null,
95
+ "vision_config": {
96
+ "_name_or_path": "",
97
+ "add_cross_attention": false,
98
+ "architectures": null,
99
+ "attention_dropout": 0.0,
100
+ "bad_words_ids": null,
101
+ "begin_suppress_tokens": null,
102
+ "bos_token_id": null,
103
+ "chunk_size_feed_forward": 0,
104
+ "cross_attention_hidden_size": null,
105
+ "decoder_start_token_id": null,
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "early_stopping": false,
109
+ "encoder_no_repeat_ngram_size": 0,
110
+ "eos_token_id": null,
111
+ "exponential_decay_length_penalty": null,
112
+ "finetuning_task": null,
113
+ "forced_bos_token_id": null,
114
+ "forced_eos_token_id": null,
115
+ "hidden_act": "quick_gelu",
116
+ "hidden_size": 1024,
117
+ "id2label": {
118
+ "0": "LABEL_0",
119
+ "1": "LABEL_1"
120
+ },
121
+ "image_size": 224,
122
+ "initializer_factor": 1.0,
123
+ "initializer_range": 0.02,
124
+ "intermediate_size": 4096,
125
+ "is_decoder": false,
126
+ "is_encoder_decoder": false,
127
+ "label2id": {
128
+ "LABEL_0": 0,
129
+ "LABEL_1": 1
130
+ },
131
+ "layer_norm_eps": 1e-05,
132
+ "length_penalty": 1.0,
133
+ "max_length": 20,
134
+ "min_length": 0,
135
+ "model_type": "clip_vision_model",
136
+ "no_repeat_ngram_size": 0,
137
+ "num_attention_heads": 16,
138
+ "num_beam_groups": 1,
139
+ "num_beams": 1,
140
+ "num_channels": 3,
141
+ "num_hidden_layers": 24,
142
+ "num_return_sequences": 1,
143
+ "output_attentions": false,
144
+ "output_hidden_states": false,
145
+ "output_scores": false,
146
+ "pad_token_id": null,
147
+ "patch_size": 14,
148
+ "prefix": null,
149
+ "problem_type": null,
150
+ "projection_dim": 512,
151
+ "pruned_heads": {},
152
+ "remove_invalid_values": false,
153
+ "repetition_penalty": 1.0,
154
+ "return_dict": true,
155
+ "return_dict_in_generate": false,
156
+ "sep_token_id": null,
157
+ "suppress_tokens": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tf_legacy_loss": false,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "transformers_version": "4.27.0.dev0",
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false
171
+ },
172
+ "vision_config_dict": {
173
+ "hidden_size": 1024,
174
+ "intermediate_size": 4096,
175
+ "num_attention_heads": 16,
176
+ "num_hidden_layers": 24,
177
+ "patch_size": 14
178
+ }
179
+ }
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6a233ff6fd5ccb9f76fd99618d73369c52dd3d8222376384d0e601911089e8
3
+ size 1215981830
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.15.0.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
+ "prediction_type": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-large-patch14",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 768,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.27.0.dev0",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b384ea4ab4a5dcdeb81323e8dcb562bdc1284208b754412ed3ab166b770d8a
3
+ size 492265874
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "pad_token": "<|endoftext|>",
23
+ "special_tokens_map_file": "./special_tokens_map.json",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "act_fn": "silu",
5
+ "attention_head_dim": 8,
6
+ "block_out_channels": [
7
+ 320,
8
+ 640,
9
+ 1280,
10
+ 1280
11
+ ],
12
+ "center_input_sample": false,
13
+ "class_embed_type": null,
14
+ "conv_in_kernel": 3,
15
+ "conv_out_kernel": 3,
16
+ "cross_attention_dim": 768,
17
+ "down_block_types": [
18
+ "CrossAttnDownBlock2D",
19
+ "CrossAttnDownBlock2D",
20
+ "CrossAttnDownBlock2D",
21
+ "DownBlock2D"
22
+ ],
23
+ "downsample_padding": 1,
24
+ "dual_cross_attention": false,
25
+ "flip_sin_to_cos": true,
26
+ "freq_shift": 0,
27
+ "in_channels": 4,
28
+ "layers_per_block": 2,
29
+ "mid_block_scale_factor": 1,
30
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
31
+ "norm_eps": 1e-05,
32
+ "norm_num_groups": 32,
33
+ "num_class_embeds": null,
34
+ "only_cross_attention": false,
35
+ "out_channels": 4,
36
+ "projection_class_embeddings_input_dim": null,
37
+ "resnet_time_scale_shift": "default",
38
+ "sample_size": 64,
39
+ "time_cond_proj_dim": null,
40
+ "time_embedding_type": "positional",
41
+ "timestep_post_act": null,
42
+ "up_block_types": [
43
+ "UpBlock2D",
44
+ "CrossAttnUpBlock2D",
45
+ "CrossAttnUpBlock2D",
46
+ "CrossAttnUpBlock2D"
47
+ ],
48
+ "upcast_attention": false,
49
+ "use_linear_projection": false
50
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:687b260e68bf6827c6ace07dfc96ed54352d35effe0aa08df48acad0c4cc9e86
3
+ size 3438167540
vae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.15.0.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
+ "in_channels": 3,
18
+ "latent_channels": 4,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 3,
22
+ "sample_size": 512,
23
+ "scaling_factor": 0.18215,
24
+ "up_block_types": [
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D"
29
+ ]
30
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16aadd9501c371b6ef94257a01596e461b13637fd984588175821c77c5a74df
3
+ size 334643276