Guizmus commited on
Commit
bca1152
1 Parent(s): b04f1b7

Add Diffusers weights

Browse files

Add Diffusers weights converted from checkpoint `BloodborneStyle-v1-1.ckpt` in revision b04f1b7d949ff6b34ee8e07a589868414a0f6bd9

model_index.json CHANGED
@@ -1,13 +1,17 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.7.0.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": "0.8.0.dev0",
4
  "feature_extractor": [
5
  "transformers",
6
  "CLIPFeatureExtractor"
7
  ],
8
+ "safety_checker": [
9
+ "stable_diffusion",
10
+ "StableDiffusionSafetyChecker"
11
+ ],
12
  "scheduler": [
13
  "diffusers",
14
+ "PNDMScheduler"
15
  ],
16
  "text_encoder": [
17
  "transformers",
safety_checker/config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
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
+ "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": "4.24.0",
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
+ "dropout": 0.0,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "quick_gelu",
117
+ "hidden_size": 1024,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "image_size": 224,
123
+ "initializer_factor": 1.0,
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 4096,
126
+ "is_decoder": false,
127
+ "is_encoder_decoder": false,
128
+ "label2id": {
129
+ "LABEL_0": 0,
130
+ "LABEL_1": 1
131
+ },
132
+ "layer_norm_eps": 1e-05,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "min_length": 0,
136
+ "model_type": "clip_vision_model",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 16,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_channels": 3,
142
+ "num_hidden_layers": 24,
143
+ "num_return_sequences": 1,
144
+ "output_attentions": false,
145
+ "output_hidden_states": false,
146
+ "output_scores": false,
147
+ "pad_token_id": null,
148
+ "patch_size": 14,
149
+ "prefix": null,
150
+ "problem_type": null,
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": "4.24.0",
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/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": "0.7.0.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": "0.8.0.dev0",
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": "F:/AI/Data/Outputs/Dreambooth/BloodborneStyle/v1-10k",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -19,7 +19,7 @@
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
- "torch_dtype": "float16",
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
  ],
 
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
+ "torch_dtype": "float32",
23
  "transformers_version": "4.24.0",
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 sha256:71c5b53caf2b8f820f23f1626fa35393c3e3f4035754f56de9a0921de823449e
3
- size 246188833
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3e806b1abd10573a77121eca26962cdf7053facea3350e24cd2d24d81ba902
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": "F:/AI/Data/Outputs/Dreambooth/BloodborneStyle/v1-10k\\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": "0.7.0.dev0",
4
- "_name_or_path": "F:/AI/Data/Outputs/Dreambooth/BloodborneStyle/v1-10k",
5
  "act_fn": "silu",
6
  "attention_head_dim": 8,
7
  "block_out_channels": [
@@ -27,7 +26,7 @@
27
  "norm_eps": 1e-05,
28
  "norm_num_groups": 32,
29
  "out_channels": 4,
30
- "sample_size": 64,
31
  "up_block_types": [
32
  "UpBlock2D",
33
  "CrossAttnUpBlock2D",
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.8.0.dev0",
 
4
  "act_fn": "silu",
5
  "attention_head_dim": 8,
6
  "block_out_channels": [
 
26
  "norm_eps": 1e-05,
27
  "norm_num_groups": 32,
28
  "out_channels": 4,
29
+ "sample_size": 32,
30
  "up_block_types": [
31
  "UpBlock2D",
32
  "CrossAttnUpBlock2D",
unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:201fd06a467146bd349af8b2f3431da9e36caa94bdbf024162f3efec25069115
3
- size 1719334053
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8efcdab051e54da4eeef68f7da639061751b9ddf2d70886c9b2851c9e40899b0
3
+ size 3438366373
vae/config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.7.0.dev0",
4
- "_name_or_path": "F:/AI/Data/Outputs/Dreambooth/BloodborneStyle/v1-10k",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
@@ -20,7 +19,7 @@
20
  "layers_per_block": 2,
21
  "norm_num_groups": 32,
22
  "out_channels": 3,
23
- "sample_size": 512,
24
  "up_block_types": [
25
  "UpDecoderBlock2D",
26
  "UpDecoderBlock2D",
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.8.0.dev0",
 
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
 
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",
vae/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
3
  size 334711857
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf4507d99b88db73f3916e2a20169fe74ada6b5582e9af56cfa80f5f3141765
3
  size 334711857