upload diffusers model

#1
by burnerbaby - opened
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": "0.12.0.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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
safety_checker/config.json DELETED
@@ -1,181 +0,0 @@
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": "4.26.0.dev0",
84
- "typical_p": 1.0,
85
- "use_bfloat16": false,
86
- "vocab_size": 49408
87
- },
88
- "text_config_dict": {
89
- "hidden_size": 768,
90
- "intermediate_size": 3072,
91
- "num_attention_heads": 12,
92
- "num_hidden_layers": 12
93
- },
94
- "torch_dtype": "float32",
95
- "transformers_version": null,
96
- "vision_config": {
97
- "_name_or_path": "",
98
- "add_cross_attention": false,
99
- "architectures": null,
100
- "attention_dropout": 0.0,
101
- "bad_words_ids": null,
102
- "begin_suppress_tokens": null,
103
- "bos_token_id": null,
104
- "chunk_size_feed_forward": 0,
105
- "cross_attention_hidden_size": null,
106
- "decoder_start_token_id": null,
107
- "diversity_penalty": 0.0,
108
- "do_sample": false,
109
- "dropout": 0.0,
110
- "early_stopping": false,
111
- "encoder_no_repeat_ngram_size": 0,
112
- "eos_token_id": null,
113
- "exponential_decay_length_penalty": null,
114
- "finetuning_task": null,
115
- "forced_bos_token_id": null,
116
- "forced_eos_token_id": null,
117
- "hidden_act": "quick_gelu",
118
- "hidden_size": 1024,
119
- "id2label": {
120
- "0": "LABEL_0",
121
- "1": "LABEL_1"
122
- },
123
- "image_size": 224,
124
- "initializer_factor": 1.0,
125
- "initializer_range": 0.02,
126
- "intermediate_size": 4096,
127
- "is_decoder": false,
128
- "is_encoder_decoder": false,
129
- "label2id": {
130
- "LABEL_0": 0,
131
- "LABEL_1": 1
132
- },
133
- "layer_norm_eps": 1e-05,
134
- "length_penalty": 1.0,
135
- "max_length": 20,
136
- "min_length": 0,
137
- "model_type": "clip_vision_model",
138
- "no_repeat_ngram_size": 0,
139
- "num_attention_heads": 16,
140
- "num_beam_groups": 1,
141
- "num_beams": 1,
142
- "num_channels": 3,
143
- "num_hidden_layers": 24,
144
- "num_return_sequences": 1,
145
- "output_attentions": false,
146
- "output_hidden_states": false,
147
- "output_scores": false,
148
- "pad_token_id": null,
149
- "patch_size": 14,
150
- "prefix": null,
151
- "problem_type": null,
152
- "projection_dim": 512,
153
- "pruned_heads": {},
154
- "remove_invalid_values": false,
155
- "repetition_penalty": 1.0,
156
- "return_dict": true,
157
- "return_dict_in_generate": false,
158
- "sep_token_id": null,
159
- "suppress_tokens": null,
160
- "task_specific_params": null,
161
- "temperature": 1.0,
162
- "tf_legacy_loss": false,
163
- "tie_encoder_decoder": false,
164
- "tie_word_embeddings": true,
165
- "tokenizer_class": null,
166
- "top_k": 50,
167
- "top_p": 1.0,
168
- "torch_dtype": null,
169
- "torchscript": false,
170
- "transformers_version": "4.26.0.dev0",
171
- "typical_p": 1.0,
172
- "use_bfloat16": false
173
- },
174
- "vision_config_dict": {
175
- "hidden_size": 1024,
176
- "intermediate_size": 4096,
177
- "num_attention_heads": 16,
178
- "num_hidden_layers": 24,
179
- "patch_size": 14
180
- }
181
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
safety_checker/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
- size 1216064769
 
 
 
 
scheduler/scheduler_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "_class_name": "PNDMScheduler",
3
- "_diffusers_version": "0.12.0.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": "openai/clip-vit-large-patch14",
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": 768,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.26.0.dev0",
24
- "vocab_size": 49408
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
text_encoder/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f69cec2968928240a248554dd6eb6d88e6e11b690c8bdcecb57427d5f0fc8fd
3
- size 492307041
 
 
 
 
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
@@ -1,34 +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
- "do_lower_case": true,
12
- "eos_token": {
13
- "__type": "AddedToken",
14
- "content": "<|endoftext|>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false
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",
26
- "unk_token": {
27
- "__type": "AddedToken",
28
- "content": "<|endoftext|>",
29
- "lstrip": false,
30
- "normalized": true,
31
- "rstrip": false,
32
- "single_word": false
33
- }
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
unet/config.json DELETED
@@ -1,44 +0,0 @@
1
- {
2
- "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.12.0.dev0",
4
- "act_fn": "silu",
5
- "attention_head_dim": 8,
6
- "block_out_channels": [
7
- 320,
8
- 640,
9
- 1280,
10
- 1280
11
- ],
12
- "center_input_sample": false,
13
- "class_embed_type": null,
14
- "cross_attention_dim": 768,
15
- "down_block_types": [
16
- "CrossAttnDownBlock2D",
17
- "CrossAttnDownBlock2D",
18
- "CrossAttnDownBlock2D",
19
- "DownBlock2D"
20
- ],
21
- "downsample_padding": 1,
22
- "dual_cross_attention": false,
23
- "flip_sin_to_cos": true,
24
- "freq_shift": 0,
25
- "in_channels": 4,
26
- "layers_per_block": 2,
27
- "mid_block_scale_factor": 1,
28
- "mid_block_type": "UNetMidBlock2DCrossAttn",
29
- "norm_eps": 1e-05,
30
- "norm_num_groups": 32,
31
- "num_class_embeds": null,
32
- "only_cross_attention": false,
33
- "out_channels": 4,
34
- "resnet_time_scale_shift": "default",
35
- "sample_size": 64,
36
- "up_block_types": [
37
- "UpBlock2D",
38
- "CrossAttnUpBlock2D",
39
- "CrossAttnUpBlock2D",
40
- "CrossAttnUpBlock2D"
41
- ],
42
- "upcast_attention": false,
43
- "use_linear_projection": false
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
unet/diffusion_pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0807cf17fa0f1f85cc34f91192cbb8430ca1e730556c0a3b83b4a096b07cec9f
3
- size 3438366373
 
 
 
 
vae/config.json DELETED
@@ -1,29 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.12.0.dev0",
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
- "in_channels": 3,
18
- "latent_channels": 4,
19
- "layers_per_block": 2,
20
- "norm_num_groups": 32,
21
- "out_channels": 3,
22
- "sample_size": 512,
23
- "up_block_types": [
24
- "UpDecoderBlock2D",
25
- "UpDecoderBlock2D",
26
- "UpDecoderBlock2D",
27
- "UpDecoderBlock2D"
28
- ]
29
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vae/diffusion_pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:202db1d3d9ee176c88ee4ca933877e102516f12538bee3e5395ef454ed4b8f58
3
- size 334711857