ninja commited on
Commit
ae012c9
1 Parent(s): d46a91b

Initial commit

Browse files
feature_extractor/preprocessor_config.json DELETED
@@ -1,28 +0,0 @@
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 DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.17.0.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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
text_encoder/pytorch_model.bin → pytorch_lora_weights.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a34f30098988d85dc0fb0fc272a842ebcf552e2ebc6ce4adbcf3695d08e8a90
3
- size 246188833
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aaf69cde4ca3ac8415aa237349c3319490d06234c3df5ec70c2222fcd2efb6e
3
+ size 3287771
safety_checker/config.json DELETED
@@ -1,168 +0,0 @@
1
- {
2
- "_commit_hash": "249dd2d739844dea6a0bc7fc27b3c1d014720b28",
3
- "_name_or_path": "/root/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/249dd2d739844dea6a0bc7fc27b3c1d014720b28/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": "4.28.1",
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": "4.28.1",
165
- "typical_p": 1.0,
166
- "use_bfloat16": false
167
- }
168
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
safety_checker/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0456a803da90fddb9afd66f0d023667f99a91cdb080a274c23ecc336010763bf
3
- size 608107073
 
 
 
 
scheduler/scheduler_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "_class_name": "PNDMScheduler",
3
- "_diffusers_version": "0.17.0.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 DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "_name_or_path": "/root/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/249dd2d739844dea6a0bc7fc27b3c1d014720b28/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": "float16",
23
- "transformers_version": "4.28.1",
24
- "vocab_size": 49408
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
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 DELETED
@@ -1,33 +0,0 @@
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
- "clean_up_tokenization_spaces": true,
12
- "do_lower_case": true,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "<|endoftext|>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "errors": "replace",
22
- "model_max_length": 77,
23
- "pad_token": "<|endoftext|>",
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 DELETED
The diff for this file is too large to render. See raw diff
 
unet/config.json DELETED
@@ -1,61 +0,0 @@
1
- {
2
- "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.17.0.dev0",
4
- "_name_or_path": "/root/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/249dd2d739844dea6a0bc7fc27b3c1d014720b28/unet",
5
- "act_fn": "silu",
6
- "addition_embed_type": null,
7
- "addition_embed_type_num_heads": 64,
8
- "attention_head_dim": 8,
9
- "block_out_channels": [
10
- 320,
11
- 640,
12
- 1280,
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",
25
- "CrossAttnDownBlock2D",
26
- "DownBlock2D"
27
- ],
28
- "downsample_padding": 1,
29
- "dual_cross_attention": false,
30
- "encoder_hid_dim": null,
31
- "flip_sin_to_cos": true,
32
- "freq_shift": 0,
33
- "in_channels": 4,
34
- "layers_per_block": 2,
35
- "mid_block_only_cross_attention": null,
36
- "mid_block_scale_factor": 1,
37
- "mid_block_type": "UNetMidBlock2DCrossAttn",
38
- "norm_eps": 1e-05,
39
- "norm_num_groups": 32,
40
- "num_class_embeds": null,
41
- "only_cross_attention": false,
42
- "out_channels": 4,
43
- "projection_class_embeddings_input_dim": null,
44
- "resnet_out_scale_factor": 1.0,
45
- "resnet_skip_time_act": false,
46
- "resnet_time_scale_shift": "default",
47
- "sample_size": 64,
48
- "time_cond_proj_dim": null,
49
- "time_embedding_act_fn": null,
50
- "time_embedding_dim": null,
51
- "time_embedding_type": "positional",
52
- "timestep_post_act": null,
53
- "up_block_types": [
54
- "UpBlock2D",
55
- "CrossAttnUpBlock2D",
56
- "CrossAttnUpBlock2D",
57
- "CrossAttnUpBlock2D"
58
- ],
59
- "upcast_attention": false,
60
- "use_linear_projection": false
61
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
unet/diffusion_pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:285dbacc32c2ffc020f957780b4e6586452c276b7b324514baf355664c94bf73
3
- size 1721069349
 
 
 
 
vae/config.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.17.0.dev0",
4
- "_name_or_path": "/root/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/249dd2d739844dea6a0bc7fc27b3c1d014720b28/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
- "in_channels": 3,
19
- "latent_channels": 4,
20
- "layers_per_block": 2,
21
- "norm_num_groups": 32,
22
- "out_channels": 3,
23
- "sample_size": 512,
24
- "scaling_factor": 0.18215,
25
- "up_block_types": [
26
- "UpDecoderBlock2D",
27
- "UpDecoderBlock2D",
28
- "UpDecoderBlock2D",
29
- "UpDecoderBlock2D"
30
- ]
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vae/diffusion_pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3524731ccb7c457ec5481e252c774463677e51ef4df7fccb6f88534b632acf92
3
- size 167407601