Aflalo commited on
Commit
b0f2d5f
1 Parent(s): f2bedf9

updated ckpts - ema weights

Browse files
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 224,
3
+ "do_center_crop": true,
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_resize": true,
7
+ "feature_extractor_type": "CLIPFeatureExtractor",
8
+ "image_mean": [
9
+ 0.48145466,
10
+ 0.4578275,
11
+ 0.40821073
12
+ ],
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "resample": 3,
19
+ "size": 224
20
+ }
model_index.json CHANGED
@@ -1,10 +1,11 @@
1
  {
2
- "_class_name": "StableDiffusionUpscalePipeline",
3
  "_diffusers_version": "0.9.0.dev0",
4
  "low_res_scheduler": [
5
  "diffusers",
6
  "DDPMScheduler"
7
  ],
 
8
  "max_noise_level": 350,
9
  "scheduler": [
10
  "diffusers",
 
1
  {
2
+ "_class_name": "StableDiffusionUpscaleLDM3DPipeline",
3
  "_diffusers_version": "0.9.0.dev0",
4
  "low_res_scheduler": [
5
  "diffusers",
6
  "DDPMScheduler"
7
  ],
8
+
9
  "max_noise_level": 350,
10
  "scheduler": [
11
  "diffusers",
safety_checker/config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./safety_module",
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
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "dropout": 0.0,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_act": "quick_gelu",
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_factor": 1.0,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": false,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 77,
49
+ "min_length": 0,
50
+ "model_type": "clip_text_model",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 1,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "transformers_version": "4.21.0.dev0",
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false,
81
+ "vocab_size": 49408
82
+ },
83
+ "text_config_dict": {
84
+ "hidden_size": 768,
85
+ "intermediate_size": 3072,
86
+ "num_attention_heads": 12,
87
+ "num_hidden_layers": 12
88
+ },
89
+ "torch_dtype": "float32",
90
+ "transformers_version": null,
91
+ "vision_config": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_dropout": 0.0,
96
+ "bad_words_ids": 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_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
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "task_specific_params": null,
152
+ "temperature": 1.0,
153
+ "tie_encoder_decoder": false,
154
+ "tie_word_embeddings": true,
155
+ "tokenizer_class": null,
156
+ "top_k": 50,
157
+ "top_p": 1.0,
158
+ "torch_dtype": null,
159
+ "torchscript": false,
160
+ "transformers_version": "4.21.0.dev0",
161
+ "typical_p": 1.0,
162
+ "use_bfloat16": false
163
+ },
164
+ "vision_config_dict": {
165
+ "hidden_size": 1024,
166
+ "intermediate_size": 4096,
167
+ "num_attention_heads": 16,
168
+ "num_hidden_layers": 24,
169
+ "patch_size": 14
170
+ }
171
+ }
unet/diffusion_pytorch_model.bin → safety_checker/model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd94f081b9077d017ed99d0b96c0b8b5a38742cdcb61302e4472a6f9d98ad6b4
3
- size 3443497527
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d6a233ff6fd5ccb9f76fd99618d73369c52dd3d8222376384d0e601911089e8
3
+ size 1215981830
unet/diffusion_pytorch_model_ema.bin → safety_checker/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:063889377720289a5f8b9cdb8c31cdd18b29c2e9b98186ff849e6b54101d4b0e
3
- size 3443500283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770a47a9ffdcfda0b05506a7888ed714d06131d60267e6cf52765d61cf59fd67
3
+ size 492305335
unet/.ipynb_checkpoints/config-checkpoint.json DELETED
@@ -1,46 +0,0 @@
1
- {
2
- "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.8.0",
4
- "_name_or_path": "hf-models/stable-diffusion-x4-upscaler/unet",
5
- "act_fn": "silu",
6
- "attention_head_dim": 8,
7
- "block_out_channels": [
8
- 256,
9
- 512,
10
- 512,
11
- 1024
12
- ],
13
- "center_input_sample": false,
14
- "cross_attention_dim": 1024,
15
- "down_block_types": [
16
- "DownBlock2D",
17
- "CrossAttnDownBlock2D",
18
- "CrossAttnDownBlock2D",
19
- "CrossAttnDownBlock2D"
20
- ],
21
- "downsample_padding": 1,
22
- "dual_cross_attention": false,
23
- "flip_sin_to_cos": true,
24
- "freq_shift": 0,
25
- "in_channels": 7,
26
- "layers_per_block": 2,
27
- "mid_block_scale_factor": 1,
28
- "norm_eps": 1e-05,
29
- "norm_num_groups": 32,
30
- "num_class_embeds": 1000,
31
- "only_cross_attention": [
32
- true,
33
- true,
34
- true,
35
- false
36
- ],
37
- "out_channels": 4,
38
- "sample_size": 128,
39
- "up_block_types": [
40
- "CrossAttnUpBlock2D",
41
- "CrossAttnUpBlock2D",
42
- "CrossAttnUpBlock2D",
43
- "UpBlock2D"
44
- ],
45
- "use_linear_projection": true
46
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
unet/config.json CHANGED
@@ -1,46 +1,37 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.9.0.dev0",
4
- "_name_or_path": "hf-models/stable-diffusion-x4-upscaler/unet",
5
  "act_fn": "silu",
6
  "attention_head_dim": 8,
7
  "block_out_channels": [
8
- 256,
9
- 512,
10
- 512,
11
- 1024
12
  ],
13
  "center_input_sample": false,
14
- "cross_attention_dim": 1024,
15
  "down_block_types": [
16
- "DownBlock2D",
17
  "CrossAttnDownBlock2D",
18
  "CrossAttnDownBlock2D",
19
- "CrossAttnDownBlock2D"
 
20
  ],
21
  "downsample_padding": 1,
22
- "dual_cross_attention": false,
23
  "flip_sin_to_cos": true,
24
  "freq_shift": 0,
25
  "in_channels": 8,
 
26
  "layers_per_block": 2,
27
  "mid_block_scale_factor": 1,
28
  "norm_eps": 1e-05,
29
  "norm_num_groups": 32,
30
- "num_class_embeds": 1000,
31
- "only_cross_attention": [
32
- true,
33
- true,
34
- true,
35
- false
36
- ],
37
  "out_channels": 4,
38
- "sample_size": 128,
39
  "up_block_types": [
 
40
  "CrossAttnUpBlock2D",
41
  "CrossAttnUpBlock2D",
42
- "CrossAttnUpBlock2D",
43
- "UpBlock2D"
44
- ],
45
- "use_linear_projection": true
46
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.2.2",
 
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
+ "cross_attention_dim": 768,
14
  "down_block_types": [
 
15
  "CrossAttnDownBlock2D",
16
  "CrossAttnDownBlock2D",
17
+ "CrossAttnDownBlock2D",
18
+ "DownBlock2D"
19
  ],
20
  "downsample_padding": 1,
 
21
  "flip_sin_to_cos": true,
22
  "freq_shift": 0,
23
  "in_channels": 8,
24
+ "num_class_embeds":1000,
25
  "layers_per_block": 2,
26
  "mid_block_scale_factor": 1,
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",
34
  "CrossAttnUpBlock2D",
35
+ "CrossAttnUpBlock2D"
36
+ ]
 
 
37
  }
unet/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:009c228d871942d23a6d0b946d311225bdede48aec47ad61ed61a22c94f5ef78
3
- size 3443333824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875f4a72e6ebdb147bb40bdb46524de35ea59303b0a4d4a1fda1d398f4a0c945
3
+ size 3443333744
vae/model_index.json ADDED
File without changes