idlebg commited on
Commit
e6ffdfb
1 Parent(s): 6fa7131

Adding `diffusers` weights of this model (#9)

Browse files

- Adding `diffusers` weights of this model (5773f9306295cfe8d8eb26ed818c768330de021c)

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 CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.10.2",
4
  "feature_extractor": [
5
- null,
6
- null
7
  ],
8
- "requires_safety_checker": null,
9
  "safety_checker": [
10
- null,
11
- null
12
  ],
13
  "scheduler": [
14
  "diffusers",
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.19.0.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",
safety_checker/config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 49406,
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": 49407,
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": "4.31.0",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "torch_dtype": "float16",
89
+ "transformers_version": null,
90
+ "vision_config": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_dropout": 0.0,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "exponential_decay_length_penalty": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "hidden_act": "quick_gelu",
112
+ "hidden_size": 1024,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "image_size": 224,
118
+ "initializer_factor": 1.0,
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 4096,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-05,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "min_length": 0,
131
+ "model_type": "clip_vision_model",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 16,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_channels": 3,
137
+ "num_hidden_layers": 24,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": null,
143
+ "patch_size": 14,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "projection_dim": 512,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "transformers_version": "4.31.0",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ }
168
+ }
safety_checker/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6
3
+ size 608016280
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664
safety_checker/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753acd54aa6d288d6c0ce9d51468eb28f495fcbaacf0edf755fa5fc7ce678cd9
3
+ size 1216062333
safety_checker/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b33b56681979059fda849651e85f3ddf994ddcd52615ccf4a71a32c055e40956
3
+ size 608101123
scheduler/scheduler_config.json CHANGED
@@ -1,14 +1,19 @@
1
  {
2
  "_class_name": "DDIMScheduler",
3
- "_diffusers_version": "0.10.2",
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
  }
 
1
  {
2
  "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.19.0.dev0",
4
  "beta_end": 0.012,
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": "epsilon",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
  "set_alpha_to_one": false,
 
15
  "steps_offset": 1,
16
+ "thresholding": false,
17
+ "timestep_spacing": "leading",
18
  "trained_betas": null
19
  }
text_encoder/config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "openai/clip-vit-large-patch14",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -19,7 +18,7 @@
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.26.0",
24
  "vocab_size": 49408
25
  }
 
1
  {
 
2
  "architectures": [
3
  "CLIPTextModel"
4
  ],
 
18
  "num_hidden_layers": 12,
19
  "pad_token_id": 1,
20
  "projection_dim": 768,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.31.0",
23
  "vocab_size": 49408
24
  }
text_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30080b68455ef5f23dbe219c2c4680f6a0405aecfc0261af26c456dee3db213c
3
+ size 246144152
text_encoder/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6982be4c31c7d50bf7f8bd76ba41c6347abd7ee73b40bba959455d7631b82af
3
- size 492265880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edab082b629b1c67b0f638fef1aa599f401afe734272b8e139fb9c967017eee7
3
+ size 492265168
text_encoder/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6afb38cf3363a11c9cc30324b2dfb25f19f9413253c257bc3dc25b8ca149014a
3
- size 492305335
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd47149072e14f2a0cf9062e292d88161f9c0ccdd65fd87f976bbfb35afd36b7
3
+ size 492306077
text_encoder/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2487cae512f9d24f727de026646b2eced98fe2d4cc950cf087ceea18e7215ef7
3
+ size 246186171
tokenizer/tokenizer_config.json CHANGED
@@ -8,6 +8,7 @@
8
  "rstrip": false,
9
  "single_word": false
10
  },
 
11
  "do_lower_case": true,
12
  "eos_token": {
13
  "__type": "AddedToken",
@@ -19,9 +20,7 @@
19
  },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
- "name_or_path": "runwayml/stable-diffusion-v1-5",
23
  "pad_token": "<|endoftext|>",
24
- "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
26
  "unk_token": {
27
  "__type": "AddedToken",
 
8
  "rstrip": false,
9
  "single_word": false
10
  },
11
+ "clean_up_tokenization_spaces": true,
12
  "do_lower_case": true,
13
  "eos_token": {
14
  "__type": "AddedToken",
 
20
  },
21
  "errors": "replace",
22
  "model_max_length": 77,
 
23
  "pad_token": "<|endoftext|>",
 
24
  "tokenizer_class": "CLIPTokenizer",
25
  "unk_token": {
26
  "__type": "AddedToken",
unet/config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.10.2",
4
  "act_fn": "silu",
 
 
 
5
  "attention_head_dim": 8,
6
  "block_out_channels": [
7
  320,
@@ -10,7 +13,12 @@
10
  1280
11
  ],
12
  "center_input_sample": false,
 
 
 
 
13
  "cross_attention_dim": 768,
 
14
  "down_block_types": [
15
  "CrossAttnDownBlock2D",
16
  "CrossAttnDownBlock2D",
@@ -19,23 +27,38 @@
19
  ],
20
  "downsample_padding": 1,
21
  "dual_cross_attention": false,
 
 
22
  "flip_sin_to_cos": true,
23
  "freq_shift": 0,
24
  "in_channels": 4,
25
  "layers_per_block": 2,
 
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": [
34
  "UpBlock2D",
35
  "CrossAttnUpBlock2D",
36
  "CrossAttnUpBlock2D",
37
  "CrossAttnUpBlock2D"
38
  ],
39
- "upcast_attention": false,
40
  "use_linear_projection": false
41
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.19.0.dev0",
4
  "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
  "attention_head_dim": 8,
9
  "block_out_channels": [
10
  320,
 
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": 768,
21
+ "cross_attention_norm": null,
22
  "down_block_types": [
23
  "CrossAttnDownBlock2D",
24
  "CrossAttnDownBlock2D",
 
27
  ],
28
  "downsample_padding": 1,
29
  "dual_cross_attention": false,
30
+ "encoder_hid_dim": null,
31
+ "encoder_hid_dim_type": null,
32
  "flip_sin_to_cos": true,
33
  "freq_shift": 0,
34
  "in_channels": 4,
35
  "layers_per_block": 2,
36
+ "mid_block_only_cross_attention": null,
37
  "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
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": 4,
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": "default",
49
+ "sample_size": 96,
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
  "up_block_types": [
57
  "UpBlock2D",
58
  "CrossAttnUpBlock2D",
59
  "CrossAttnUpBlock2D",
60
  "CrossAttnUpBlock2D"
61
  ],
62
+ "upcast_attention": null,
63
  "use_linear_projection": false
64
  }
unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec383404aada9e0bc372fb3cb5fb65105589fb0488037eaaf32e158f028d8b8
3
- size 3438354725
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b6c64102d8ae28bd8c9c3427028fba7c4d76a971b3ec1f6828917730428411
3
+ size 3438366373
unet/diffusion_pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a132ce41f90b7030e60bc3f61e9412ab1be4c1c0043d05152886243c7c6b888c
3
+ size 1719327893
unet/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1a6c4b8d65038de741048b0f4e6dbff49dfb736af57945aad1710966824f818
3
+ size 1719125304
vae/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.10.2",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
@@ -14,12 +14,14 @@
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": 256,
 
23
  "up_block_types": [
24
  "UpDecoderBlock2D",
25
  "UpDecoderBlock2D",
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.19.0.dev0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
 
14
  "DownEncoderBlock2D",
15
  "DownEncoderBlock2D"
16
  ],
17
+ "force_upcast": true,
18
  "in_channels": 3,
19
  "latent_channels": 4,
20
  "layers_per_block": 2,
21
  "norm_num_groups": 32,
22
  "out_channels": 3,
23
+ "sample_size": 768,
24
+ "scaling_factor": 0.18215,
25
  "up_block_types": [
26
  "UpDecoderBlock2D",
27
  "UpDecoderBlock2D",
vae/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f741464fc16ce3f501a0518eb848cf42a7bc2a54dcb27d12d5fadc62ddf6bfca
3
- size 334707217
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0b55734e819006e22f70eb6d8246fbf32f324d006cfe2ed9fd75d34a60d4ef
3
+ size 334712113
vae/diffusion_pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44915add42092106e70bffac475aae4283b5e8167a8a0c5f55ccc667ee4ebeb5
3
+ size 167405651
vae/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
3
+ size 167335342
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ede2dd4503db4d4ea13735155e88a976dbdf8f40a09b06cea6d4fd85dfca5d6d
3
- size 334643276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c01d878551cee9efec063c86e6b2fb923572353adb2e002f217766d516e78a7
3
+ size 334643268