birdbong commited on
Commit
8e953e3
1 Parent(s): 9cd4afd

Adding `diffusers` weights of this model

Browse files

This PR adds fp32 and fp16 weights in PyTorch and safetensors format to SG161222/Realistic_Vision_V5.1_noVAE

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
@@ -1,33 +1,33 @@
1
  {
2
- "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.16.1",
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",
15
- "DEISMultistepScheduler"
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
- }
 
1
  {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.18.0.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
+ "DPMSolverMultistepScheduler"
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 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 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": "4.30.2",
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": "4.30.2",
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 sha256:08902f19b1cfebd7c989f152fc0507bef6898c706a91d666509383122324b511
3
+ size 608018440
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11cfe53105625af8c00faac32a430626641cce686454f3c39d837f14397d858b
3
+ size 1215981832
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
safety_checker/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ba87205445ad5def13e54919b038dcfb7321ec1c3f4b12487d4fba6036125f
3
+ size 608103564
scheduler/scheduler_config.json CHANGED
@@ -1,21 +1,26 @@
1
  {
2
- "_class_name": "DEISMultistepScheduler",
3
- "_diffusers_version": "0.16.1",
4
- "algorithm_type": "deis",
5
  "beta_end": 0.012,
6
  "beta_schedule": "scaled_linear",
7
  "beta_start": 0.00085,
8
  "clip_sample": false,
9
  "clip_sample_range": 1.0,
10
  "dynamic_thresholding_ratio": 0.995,
 
11
  "lower_order_final": true,
12
  "num_train_timesteps": 1000,
13
  "prediction_type": "epsilon",
 
14
  "sample_max_value": 1.0,
15
  "set_alpha_to_one": false,
16
  "solver_order": 2,
17
- "solver_type": "logrho",
18
  "steps_offset": 1,
19
  "thresholding": false,
20
- "trained_betas": null
 
 
 
21
  }
 
1
  {
2
+ "_class_name": "DPMSolverMultistepScheduler",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "algorithm_type": "dpmsolver++",
5
  "beta_end": 0.012,
6
  "beta_schedule": "scaled_linear",
7
  "beta_start": 0.00085,
8
  "clip_sample": false,
9
  "clip_sample_range": 1.0,
10
  "dynamic_thresholding_ratio": 0.995,
11
+ "lambda_min_clipped": -Infinity,
12
  "lower_order_final": true,
13
  "num_train_timesteps": 1000,
14
  "prediction_type": "epsilon",
15
+ "rescale_betas_zero_snr": false,
16
  "sample_max_value": 1.0,
17
  "set_alpha_to_one": false,
18
  "solver_order": 2,
19
+ "solver_type": "midpoint",
20
  "steps_offset": 1,
21
  "thresholding": false,
22
+ "timestep_spacing": "leading",
23
+ "trained_betas": null,
24
+ "use_karras_sigmas": false,
25
+ "variance_type": null
26
  }
text_encoder/config.json CHANGED
@@ -19,7 +19,7 @@
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
- "torch_dtype": "float32",
23
  "transformers_version": "4.30.2",
24
  "vocab_size": 49408
25
  }
 
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
+ "torch_dtype": "float16",
23
  "transformers_version": "4.30.2",
24
  "vocab_size": 49408
25
  }
text_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f5d11650d8df9a619757843e91d504de300f6da75cdb66b66faab80bf98b96b
3
+ size 246144864
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da801e72753c118abf383cee2b59d5ddeb212fe344cc5a36bac22ab664a05b2
3
+ size 492307041
text_encoder/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0460d52f1487cc73ce279b0cc89fd8ef7316ed2e2eb947eefac12ea885d4a8
3
+ size 246187076
unet/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.16.1",
4
  "act_fn": "silu",
5
  "addition_embed_type": null,
6
  "addition_embed_type_num_heads": 64,
@@ -27,6 +27,7 @@
27
  "downsample_padding": 1,
28
  "dual_cross_attention": false,
29
  "encoder_hid_dim": null,
 
30
  "flip_sin_to_cos": true,
31
  "freq_shift": 0,
32
  "in_channels": 4,
@@ -36,6 +37,7 @@
36
  "mid_block_type": "UNetMidBlock2DCrossAttn",
37
  "norm_eps": 1e-05,
38
  "norm_num_groups": 32,
 
39
  "num_class_embeds": null,
40
  "only_cross_attention": false,
41
  "out_channels": 4,
@@ -55,6 +57,6 @@
55
  "CrossAttnUpBlock2D",
56
  "CrossAttnUpBlock2D"
57
  ],
58
- "upcast_attention": false,
59
  "use_linear_projection": false
60
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.0.dev0",
4
  "act_fn": "silu",
5
  "addition_embed_type": null,
6
  "addition_embed_type_num_heads": 64,
 
27
  "downsample_padding": 1,
28
  "dual_cross_attention": false,
29
  "encoder_hid_dim": null,
30
+ "encoder_hid_dim_type": null,
31
  "flip_sin_to_cos": true,
32
  "freq_shift": 0,
33
  "in_channels": 4,
 
37
  "mid_block_type": "UNetMidBlock2DCrossAttn",
38
  "norm_eps": 1e-05,
39
  "norm_num_groups": 32,
40
+ "num_attention_heads": null,
41
  "num_class_embeds": null,
42
  "only_cross_attention": false,
43
  "out_channels": 4,
 
57
  "CrossAttnUpBlock2D",
58
  "CrossAttnUpBlock2D"
59
  ],
60
+ "upcast_attention": null,
61
  "use_linear_projection": false
62
  }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef2d71d90c97c9d0c98a68b5e07b8a7b859f27753509d7cc1bd2e3949343a1c
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 sha256:695ad3ab97841a6640c588caf88ed3ab231ab56efe51691d78efdf87d7b93452
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:c150f632d0c2338a50224504fa238f716cf50fb680897b0330563d2ff7bbf0e7
3
+ size 1719125304
vae/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.16.1",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.18.0.dev0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:251086e7c7793410070d11a421db3886a7b2a7ff27cdea006a67a4cd76a7a899
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 sha256:6183e4464d298b5aa971849ea031f233aaf16b0a31b6ffbc3754605e85a1b8f1
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 sha256:249bd6adf5e03a78cfbc21c689b08f9e285fa49fa81f2cf9ff175c6272a2740a
3
+ size 167335342
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68a430f8a51413e80ecec6c13fff4b6b63e57600a2ec661a016a14fd1037fa4b
3
- size 334643276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a6170968f284b6c0c111e2611c806a04102e2a48790ebd1d490ca78040d2bb
3
+ size 334643268