Hugging Face's logo

ayjays132
/
CustomImageGenerator

Text-to-Image
Diffusers
PyTorch
Safetensors
English
StableDiffusionPipeline
gpt2
image-generation
generative-model
multimodal
SOTA
Inference Endpoints
Model card Files Community
ayjays132 commited on
Commit
9881add
•
1 Parent(s): d4ebe48

Upload 24 files

Browse files
Files changed (4) hide show
  1. safety_checker/config.json +168 -167
  2. text_encoder/config.json +25 -24
  3. unet/config.json +68 -67
  4. vae/config.json +34 -33
safety_checker/config.json CHANGED
@@ -1,167 +1,168 @@
1
- {
2
- "_commit_hash": "133a221b8aa7292a167afc5127cb63fb5005638b",
3
- "architectures": [
4
- "StableDiffusionSafetyChecker"
5
- ],
6
- "initializer_factor": 1.0,
7
- "logit_scale_init_value": 2.6592,
8
- "model_type": "clip",
9
- "projection_dim": 768,
10
- "text_config": {
11
- "_name_or_path": "",
12
- "add_cross_attention": false,
13
- "architectures": null,
14
- "attention_dropout": 0.0,
15
- "bad_words_ids": null,
16
- "begin_suppress_tokens": null,
17
- "bos_token_id": 0,
18
- "chunk_size_feed_forward": 0,
19
- "cross_attention_hidden_size": null,
20
- "decoder_start_token_id": null,
21
- "diversity_penalty": 0.0,
22
- "do_sample": false,
23
- "dropout": 0.0,
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": "4.28.0.dev0",
83
- "typical_p": 1.0,
84
- "use_bfloat16": false,
85
- "vocab_size": 49408
86
- },
87
- "torch_dtype": "float32",
88
- "transformers_version": null,
89
- "vision_config": {
90
- "_name_or_path": "",
91
- "add_cross_attention": false,
92
- "architectures": null,
93
- "attention_dropout": 0.0,
94
- "bad_words_ids": null,
95
- "begin_suppress_tokens": null,
96
- "bos_token_id": null,
97
- "chunk_size_feed_forward": 0,
98
- "cross_attention_hidden_size": null,
99
- "decoder_start_token_id": null,
100
- "diversity_penalty": 0.0,
101
- "do_sample": false,
102
- "dropout": 0.0,
103
- "early_stopping": false,
104
- "encoder_no_repeat_ngram_size": 0,
105
- "eos_token_id": null,
106
- "exponential_decay_length_penalty": null,
107
- "finetuning_task": null,
108
- "forced_bos_token_id": null,
109
- "forced_eos_token_id": null,
110
- "hidden_act": "quick_gelu",
111
- "hidden_size": 1024,
112
- "id2label": {
113
- "0": "LABEL_0",
114
- "1": "LABEL_1"
115
- },
116
- "image_size": 224,
117
- "initializer_factor": 1.0,
118
- "initializer_range": 0.02,
119
- "intermediate_size": 4096,
120
- "is_decoder": false,
121
- "is_encoder_decoder": false,
122
- "label2id": {
123
- "LABEL_0": 0,
124
- "LABEL_1": 1
125
- },
126
- "layer_norm_eps": 1e-05,
127
- "length_penalty": 1.0,
128
- "max_length": 20,
129
- "min_length": 0,
130
- "model_type": "clip_vision_model",
131
- "no_repeat_ngram_size": 0,
132
- "num_attention_heads": 16,
133
- "num_beam_groups": 1,
134
- "num_beams": 1,
135
- "num_channels": 3,
136
- "num_hidden_layers": 24,
137
- "num_return_sequences": 1,
138
- "output_attentions": false,
139
- "output_hidden_states": false,
140
- "output_scores": false,
141
- "pad_token_id": null,
142
- "patch_size": 14,
143
- "prefix": null,
144
- "problem_type": null,
145
- "projection_dim": 512,
146
- "pruned_heads": {},
147
- "remove_invalid_values": false,
148
- "repetition_penalty": 1.0,
149
- "return_dict": true,
150
- "return_dict_in_generate": false,
151
- "sep_token_id": null,
152
- "suppress_tokens": null,
153
- "task_specific_params": null,
154
- "temperature": 1.0,
155
- "tf_legacy_loss": false,
156
- "tie_encoder_decoder": false,
157
- "tie_word_embeddings": true,
158
- "tokenizer_class": null,
159
- "top_k": 50,
160
- "top_p": 1.0,
161
- "torch_dtype": null,
162
- "torchscript": false,
163
- "transformers_version": "4.28.0.dev0",
164
- "typical_p": 1.0,
165
- "use_bfloat16": false
166
- }
167
- }
 
 
1
+ {
2
+ "_commit_hash": "133a221b8aa7292a167afc5127cb63fb5005638b",
3
+ "_name_or_path": "C:\\Users\\ayjay\\.cache\\huggingface\\hub\\models--CompVis--stable-diffusion-v1-4\\snapshots\\133a221b8aa7292a167afc5127cb63fb5005638b\\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": "4.28.0.dev0",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "torch_dtype": "float32",
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": "4.28.0.dev0",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ }
168
+ }
text_encoder/config.json CHANGED
@@ -1,24 +1,25 @@
1
- {
2
- "architectures": [
3
- "CLIPTextModel"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 0,
7
- "dropout": 0.0,
8
- "eos_token_id": 2,
9
- "hidden_act": "quick_gelu",
10
- "hidden_size": 768,
11
- "initializer_factor": 1.0,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-05,
15
- "max_position_embeddings": 77,
16
- "model_type": "clip_text_model",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 1,
20
- "projection_dim": 512,
21
- "torch_dtype": "float32",
22
- "transformers_version": "4.28.0.dev0",
23
- "vocab_size": 49408
24
- }
 
 
1
+ {
2
+ "_name_or_path": "C:\\Users\\ayjay\\.cache\\huggingface\\hub\\models--CompVis--stable-diffusion-v1-4\\snapshots\\133a221b8aa7292a167afc5127cb63fb5005638b\\text_encoder",
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": 512,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.28.0.dev0",
24
+ "vocab_size": 49408
25
+ }
unet/config.json CHANGED
@@ -1,67 +1,68 @@
1
- {
2
- "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.27.0",
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
- "attention_type": "default",
10
- "block_out_channels": [
11
- 320,
12
- 640,
13
- 1280,
14
- 1280
15
- ],
16
- "center_input_sample": false,
17
- "class_embed_type": null,
18
- "class_embeddings_concat": false,
19
- "conv_in_kernel": 3,
20
- "conv_out_kernel": 3,
21
- "cross_attention_dim": 768,
22
- "cross_attention_norm": null,
23
- "down_block_types": [
24
- "CrossAttnDownBlock2D",
25
- "CrossAttnDownBlock2D",
26
- "CrossAttnDownBlock2D",
27
- "DownBlock2D"
28
- ],
29
- "downsample_padding": 1,
30
- "dropout": 0.0,
31
- "dual_cross_attention": false,
32
- "encoder_hid_dim": null,
33
- "encoder_hid_dim_type": null,
34
- "flip_sin_to_cos": true,
35
- "freq_shift": 0,
36
- "in_channels": 4,
37
- "layers_per_block": 2,
38
- "mid_block_only_cross_attention": null,
39
- "mid_block_scale_factor": 1,
40
- "mid_block_type": "UNetMidBlock2DCrossAttn",
41
- "norm_eps": 1e-05,
42
- "norm_num_groups": 32,
43
- "num_attention_heads": null,
44
- "num_class_embeds": null,
45
- "only_cross_attention": false,
46
- "out_channels": 4,
47
- "projection_class_embeddings_input_dim": null,
48
- "resnet_out_scale_factor": 1.0,
49
- "resnet_skip_time_act": false,
50
- "resnet_time_scale_shift": "default",
51
- "reverse_transformer_layers_per_block": null,
52
- "sample_size": 64,
53
- "time_cond_proj_dim": null,
54
- "time_embedding_act_fn": null,
55
- "time_embedding_dim": null,
56
- "time_embedding_type": "positional",
57
- "timestep_post_act": null,
58
- "transformer_layers_per_block": 1,
59
- "up_block_types": [
60
- "UpBlock2D",
61
- "CrossAttnUpBlock2D",
62
- "CrossAttnUpBlock2D",
63
- "CrossAttnUpBlock2D"
64
- ],
65
- "upcast_attention": false,
66
- "use_linear_projection": false
67
- }
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.27.0",
4
+ "_name_or_path": "C:\\Users\\ayjay\\.cache\\huggingface\\hub\\models--CompVis--stable-diffusion-v1-4\\snapshots\\133a221b8aa7292a167afc5127cb63fb5005638b\\unet",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
vae/config.json CHANGED
@@ -1,33 +1,34 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.27.0",
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
- "force_upcast": true,
18
- "in_channels": 3,
19
- "latent_channels": 4,
20
- "latents_mean": null,
21
- "latents_std": null,
22
- "layers_per_block": 2,
23
- "norm_num_groups": 32,
24
- "out_channels": 3,
25
- "sample_size": 512,
26
- "scaling_factor": 0.18215,
27
- "up_block_types": [
28
- "UpDecoderBlock2D",
29
- "UpDecoderBlock2D",
30
- "UpDecoderBlock2D",
31
- "UpDecoderBlock2D"
32
- ]
33
- }
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.27.0",
4
+ "_name_or_path": "C:\\Users\\ayjay\\.cache\\huggingface\\hub\\models--CompVis--stable-diffusion-v1-4\\snapshots\\133a221b8aa7292a167afc5127cb63fb5005638b\\vae",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "latents_mean": null,
22
+ "latents_std": null,
23
+ "layers_per_block": 2,
24
+ "norm_num_groups": 32,
25
+ "out_channels": 3,
26
+ "sample_size": 512,
27
+ "scaling_factor": 0.18215,
28
+ "up_block_types": [
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D",
31
+ "UpDecoderBlock2D",
32
+ "UpDecoderBlock2D"
33
+ ]
34
+ }