amankishore commited on
Commit
024ed1d
1 Parent(s): fc5661b

Upgrade to SD2

Browse files
feature_extractor/preprocessor_config.json DELETED
@@ -1,20 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
logs/dreambooth/1669598855.001458/events.out.tfevents.1669598855.instance-4.5954.1 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:24cf85eb46a8790c3a8364f90cde2c364ec5c73c1e1f0ae96225c112f5d81fa3
3
- size 1923
 
 
 
 
logs/dreambooth/1669598855.018298/hparams.yml DELETED
@@ -1,37 +0,0 @@
1
- adam_beta1: 0.9
2
- adam_beta2: 0.999
3
- adam_epsilon: 1.0e-08
4
- adam_weight_decay: 0.01
5
- center_crop: false
6
- class_data_dir: null
7
- class_prompt: null
8
- gradient_accumulation_steps: 1
9
- gradient_checkpointing: true
10
- hub_model_id: null
11
- hub_token: null
12
- instance_data_dir: /home/diffusers/examples/dreambooth/datasets/3-lowpoly/living_room/class
13
- instance_prompt: a photo of lowpoly_living_room
14
- learning_rate: 2.0e-06
15
- local_rank: -1
16
- logging_dir: logs
17
- lr_scheduler: constant
18
- lr_warmup_steps: 0
19
- max_grad_norm: 1.0
20
- max_train_steps: 2000
21
- mixed_precision: null
22
- num_class_images: 100
23
- num_train_epochs: 223
24
- output_dir: /home/diffusers/examples/dreambooth/datasets/3-lowpoly/living_room/model
25
- pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
26
- prior_loss_weight: 1.0
27
- push_to_hub: false
28
- resolution: 512
29
- revision: null
30
- sample_batch_size: 4
31
- scale_lr: false
32
- seed: null
33
- tokenizer_name: null
34
- train_batch_size: 1
35
- train_text_encoder: true
36
- use_8bit_adam: true
37
- with_prior_preservation: false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
logs/dreambooth/events.out.tfevents.1669598854.instance-4.5954.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4b465676c57c03d4c6bbc45ea82ee5a840c95e7b8acf588adeab50e29f7b1d6
3
- size 167786
 
 
 
 
model_index.json CHANGED
@@ -2,13 +2,13 @@
2
  "_class_name": "StableDiffusionPipeline",
3
  "_diffusers_version": "0.9.0",
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",
 
2
  "_class_name": "StableDiffusionPipeline",
3
  "_diffusers_version": "0.9.0",
4
  "feature_extractor": [
5
+ null,
6
+ null
7
  ],
8
+ "requires_safety_checker": false,
9
  "safety_checker": [
10
+ null,
11
+ null
12
  ],
13
  "scheduler": [
14
  "diffusers",
output.png CHANGED

Git LFS Details

  • SHA256: f5c589af1a99f35b7f1b662a4ab89a2e33827423ba2b82c71c48e20c226cad26
  • Pointer size: 132 Bytes
  • Size of remote file: 2.59 MB

Git LFS Details

  • SHA256: d04d1cc13bc9889074e60b37609a5cb2c92df61663fd83ae1c47a097ee4db269
  • Pointer size: 132 Bytes
  • Size of remote file: 2.64 MB
safety_checker/config.json DELETED
@@ -1,179 +0,0 @@
1
- {
2
- "_commit_hash": "63534535d4730d5976c5c647a7f2adaea1102f5b",
3
- "_name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/63534535d4730d5976c5c647a7f2adaea1102f5b/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 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
- size 1216064769
 
 
 
 
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "runwayml/stable-diffusion-v1-5",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -7,18 +7,18 @@
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": "4.24.0",
24
  "vocab_size": 49408
 
1
  {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2-base",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
7
  "bos_token_id": 0,
8
  "dropout": 0.0,
9
  "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
  "initializer_factor": 1.0,
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
  "layer_norm_eps": 1e-05,
16
  "max_position_embeddings": 77,
17
  "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
  "pad_token_id": 1,
21
+ "projection_dim": 512,
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.24.0",
24
  "vocab_size": 49408
text_encoder/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9697d910de3a19d60c2b8ba27a600443177edb43abf3d513f7638b8facf93640
3
- size 492309793
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d61d4f33f3c90c3b96c477aaa4f3cb2c767809f18f27d29e52c471275e59bfa
3
+ size 1361679905
tokenizer/special_tokens_map.json CHANGED
@@ -13,7 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "!",
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
tokenizer/tokenizer_config.json CHANGED
@@ -19,7 +19,7 @@
19
  },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
- "name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/63534535d4730d5976c5c647a7f2adaea1102f5b/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": "/root/.cache/huggingface/diffusers/models--stabilityai--stable-diffusion-2-base/snapshots/abda38f7c548237cae935d6182ae56acd5a02ed8/tokenizer",
23
  "pad_token": "<|endoftext|>",
24
  "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
unet/config.json CHANGED
@@ -1,9 +1,14 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.9.0",
4
- "_name_or_path": "runwayml/stable-diffusion-v1-5",
5
  "act_fn": "silu",
6
- "attention_head_dim": 8,
 
 
 
 
 
7
  "block_out_channels": [
8
  320,
9
  640,
@@ -11,7 +16,7 @@
11
  1280
12
  ],
13
  "center_input_sample": false,
14
- "cross_attention_dim": 768,
15
  "down_block_types": [
16
  "CrossAttnDownBlock2D",
17
  "CrossAttnDownBlock2D",
@@ -37,5 +42,5 @@
37
  "CrossAttnUpBlock2D",
38
  "CrossAttnUpBlock2D"
39
  ],
40
- "use_linear_projection": false
41
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.9.0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-base",
5
  "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
  "block_out_channels": [
13
  320,
14
  640,
 
16
  1280
17
  ],
18
  "center_input_sample": false,
19
+ "cross_attention_dim": 1024,
20
  "down_block_types": [
21
  "CrossAttnDownBlock2D",
22
  "CrossAttnDownBlock2D",
 
42
  "CrossAttnUpBlock2D",
43
  "CrossAttnUpBlock2D"
44
  ],
45
+ "use_linear_projection": true
46
  }
unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c91d52946c3b2ea6110748fdb02f076768f7fce419377cab010b99469dc5f38
3
- size 3438375973
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1c00b93b60561e392b4bca9af675ed296ef86a741693d5f9e812ecf78cccf9
3
+ size 3463934693
vae/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.9.0",
4
- "_name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/63534535d4730d5976c5c647a7f2adaea1102f5b/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.9.0",
4
+ "_name_or_path": "/root/.cache/huggingface/diffusers/models--stabilityai--stable-diffusion-2-base/snapshots/abda38f7c548237cae935d6182ae56acd5a02ed8/vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
vae/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af27ea858349760ebe3311953e0bfe8d6fd257dc9537ae0b2b938c262132a2c6
3
  size 334711857
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
3
  size 334711857