mprzymus commited on
Commit
0fe0f7f
1 Parent(s): 366f2c7

End of training

Browse files
model_index.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.17.0",
 
4
  "feature_extractor": [
5
  "transformers",
6
  "CLIPImageProcessor"
@@ -12,7 +13,7 @@
12
  ],
13
  "scheduler": [
14
  "diffusers",
15
- "DDIMScheduler"
16
  ],
17
  "text_encoder": [
18
  "transformers",
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.19.3",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPImageProcessor"
 
13
  ],
14
  "scheduler": [
15
  "diffusers",
16
+ "PNDMScheduler"
17
  ],
18
  "text_encoder": [
19
  "transformers",
safety_checker/config.json CHANGED
@@ -1,44 +1,43 @@
1
  {
2
- "_commit_hash": "3ee6c9f225f088ad5d35b624b6514b091e6a4849",
3
- "_name_or_path": "/root/.cache/huggingface/hub/models--hf-internal-testing--tiny-stable-diffusion-pipe/snapshots/3ee6c9f225f088ad5d35b624b6514b091e6a4849/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": 64,
11
  "text_config": {
12
  "_name_or_path": "",
13
  "add_cross_attention": false,
14
  "architectures": null,
15
- "attention_dropout": 0.1,
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": 0.1,
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
- "gradient_checkpointing": false,
33
  "hidden_act": "quick_gelu",
34
- "hidden_size": 32,
35
  "id2label": {
36
  "0": "LABEL_0",
37
  "1": "LABEL_1"
38
  },
39
  "initializer_factor": 1.0,
40
  "initializer_range": 0.02,
41
- "intermediate_size": 37,
42
  "is_decoder": false,
43
  "is_encoder_decoder": false,
44
  "label2id": {
@@ -48,14 +47,14 @@
48
  "layer_norm_eps": 1e-05,
49
  "length_penalty": 1.0,
50
  "max_length": 20,
51
- "max_position_embeddings": 512,
52
  "min_length": 0,
53
  "model_type": "clip_text_model",
54
  "no_repeat_ngram_size": 0,
55
- "num_attention_heads": 4,
56
  "num_beam_groups": 1,
57
  "num_beams": 1,
58
- "num_hidden_layers": 5,
59
  "num_return_sequences": 1,
60
  "output_attentions": false,
61
  "output_hidden_states": false,
@@ -81,10 +80,10 @@
81
  "top_p": 1.0,
82
  "torch_dtype": null,
83
  "torchscript": false,
84
- "transformers_version": "4.30.1",
85
  "typical_p": 1.0,
86
  "use_bfloat16": false,
87
- "vocab_size": 99
88
  },
89
  "torch_dtype": "float32",
90
  "transformers_version": null,
@@ -92,7 +91,7 @@
92
  "_name_or_path": "",
93
  "add_cross_attention": false,
94
  "architectures": null,
95
- "attention_dropout": 0.1,
96
  "bad_words_ids": null,
97
  "begin_suppress_tokens": null,
98
  "bos_token_id": null,
@@ -101,7 +100,7 @@
101
  "decoder_start_token_id": null,
102
  "diversity_penalty": 0.0,
103
  "do_sample": false,
104
- "dropout": 0.1,
105
  "early_stopping": false,
106
  "encoder_no_repeat_ngram_size": 0,
107
  "eos_token_id": null,
@@ -109,17 +108,16 @@
109
  "finetuning_task": null,
110
  "forced_bos_token_id": null,
111
  "forced_eos_token_id": null,
112
- "gradient_checkpointing": false,
113
  "hidden_act": "quick_gelu",
114
- "hidden_size": 32,
115
  "id2label": {
116
  "0": "LABEL_0",
117
  "1": "LABEL_1"
118
  },
119
- "image_size": 30,
120
  "initializer_factor": 1.0,
121
  "initializer_range": 0.02,
122
- "intermediate_size": 37,
123
  "is_decoder": false,
124
  "is_encoder_decoder": false,
125
  "label2id": {
@@ -132,17 +130,17 @@
132
  "min_length": 0,
133
  "model_type": "clip_vision_model",
134
  "no_repeat_ngram_size": 0,
135
- "num_attention_heads": 4,
136
  "num_beam_groups": 1,
137
  "num_beams": 1,
138
  "num_channels": 3,
139
- "num_hidden_layers": 5,
140
  "num_return_sequences": 1,
141
  "output_attentions": false,
142
  "output_hidden_states": false,
143
  "output_scores": false,
144
  "pad_token_id": null,
145
- "patch_size": 2,
146
  "prefix": null,
147
  "problem_type": null,
148
  "projection_dim": 512,
@@ -163,9 +161,8 @@
163
  "top_p": 1.0,
164
  "torch_dtype": null,
165
  "torchscript": false,
166
- "transformers_version": "4.30.1",
167
  "typical_p": 1.0,
168
  "use_bfloat16": false
169
- },
170
- "vocab_size": 1000
171
- }
 
1
  {
2
+ "_commit_hash": "c9ab35ff5f2c362e9e22fbafe278077e196057f0",
3
+ "_name_or_path": "/root/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/c9ab35ff5f2c362e9e22fbafe278077e196057f0/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": 49406,
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": 49407,
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": {
 
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,
 
80
  "top_p": 1.0,
81
  "torch_dtype": null,
82
  "torchscript": false,
83
+ "transformers_version": "4.31.0",
84
  "typical_p": 1.0,
85
  "use_bfloat16": false,
86
+ "vocab_size": 49408
87
  },
88
  "torch_dtype": "float32",
89
  "transformers_version": null,
 
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,
 
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,
 
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": {
 
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,
 
161
  "top_p": 1.0,
162
  "torch_dtype": null,
163
  "torchscript": false,
164
+ "transformers_version": "4.31.0",
165
  "typical_p": 1.0,
166
  "use_bfloat16": false
167
+ }
168
+ }
 
safety_checker/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87e0b3cc2e4ec88899f2db084a69f0f62d55d1621c919450482539b33ee6b2b8
3
- size 213000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753acd54aa6d288d6c0ce9d51468eb28f495fcbaacf0edf755fa5fc7ce678cd9
3
+ size 1216062333
scheduler/scheduler_config.json CHANGED
@@ -1,19 +1,15 @@
1
  {
2
- "_class_name": "DDIMScheduler",
3
- "_diffusers_version": "0.17.0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
7
  "clip_sample": false,
8
- "clip_sample_range": 1.0,
9
- "dynamic_thresholding_ratio": 0.995,
10
  "num_train_timesteps": 1000,
11
  "prediction_type": "epsilon",
12
- "rescale_betas_zero_snr": false,
13
- "sample_max_value": 1.0,
14
- "set_alpha_to_one": true,
15
  "steps_offset": 1,
16
- "thresholding": false,
17
  "timestep_spacing": "leading",
18
  "trained_betas": null
19
- }
 
1
  {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.19.3",
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
  "timestep_spacing": "leading",
14
  "trained_betas": null
15
+ }
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "hf-internal-testing/tiny-stable-diffusion-pipe",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -8,18 +8,18 @@
8
  "dropout": 0.0,
9
  "eos_token_id": 2,
10
  "hidden_act": "quick_gelu",
11
- "hidden_size": 32,
12
  "initializer_factor": 1.0,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 37,
15
  "layer_norm_eps": 1e-05,
16
  "max_position_embeddings": 77,
17
  "model_type": "clip_text_model",
18
- "num_attention_heads": 4,
19
- "num_hidden_layers": 5,
20
  "pad_token_id": 1,
21
- "projection_dim": 512,
22
  "torch_dtype": "float16",
23
- "transformers_version": "4.30.1",
24
- "vocab_size": 1000
25
  }
 
1
  {
2
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
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": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "vocab_size": 49408
25
  }
text_encoder/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b465fe593757bc41341575313d740c7b2ee9285e8b4a57bcb610cde5926d73a
3
- size 166000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b020851da42091416889fa03bf3e527e9bc8a7f0b1164147ce06536a5c22494c
3
+ size 246187869
tokenizer/merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer/vocab.json CHANGED
The diff for this file is too large to render. See raw diff
 
unet/config.json CHANGED
@@ -1,28 +1,32 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.17.0",
4
- "_name_or_path": "hf-internal-testing/tiny-stable-diffusion-pipe",
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
- 32,
11
- 64
 
 
12
  ],
13
  "center_input_sample": false,
14
  "class_embed_type": null,
15
  "class_embeddings_concat": false,
16
  "conv_in_kernel": 3,
17
  "conv_out_kernel": 3,
18
- "cross_attention_dim": 32,
19
  "cross_attention_norm": null,
20
  "down_block_types": [
21
- "DownBlock2D",
22
- "CrossAttnDownBlock2D"
 
 
23
  ],
24
  "downsample_padding": 1,
25
- "dropout": 0.0,
26
  "dual_cross_attention": false,
27
  "encoder_hid_dim": null,
28
  "encoder_hid_dim_type": null,
@@ -35,6 +39,7 @@
35
  "mid_block_type": "UNetMidBlock2DCrossAttn",
36
  "norm_eps": 1e-05,
37
  "norm_num_groups": 32,
 
38
  "num_class_embeds": null,
39
  "only_cross_attention": false,
40
  "out_channels": 4,
@@ -42,15 +47,18 @@
42
  "resnet_out_scale_factor": 1.0,
43
  "resnet_skip_time_act": false,
44
  "resnet_time_scale_shift": "default",
45
- "sample_size": 32,
46
  "time_cond_proj_dim": null,
47
  "time_embedding_act_fn": null,
48
  "time_embedding_dim": null,
49
  "time_embedding_type": "positional",
50
  "timestep_post_act": null,
 
51
  "up_block_types": [
 
52
  "CrossAttnUpBlock2D",
53
- "UpBlock2D"
 
54
  ],
55
  "upcast_attention": false,
56
  "use_linear_projection": false
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.19.3",
4
+ "_name_or_path": "drive/MyDrive/mgr/diffusion/new_data/checkpoint-36022",
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
  "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
  "dual_cross_attention": false,
31
  "encoder_hid_dim": null,
32
  "encoder_hid_dim_type": null,
 
39
  "mid_block_type": "UNetMidBlock2DCrossAttn",
40
  "norm_eps": 1e-05,
41
  "norm_num_groups": 32,
42
+ "num_attention_heads": null,
43
  "num_class_embeds": null,
44
  "only_cross_attention": false,
45
  "out_channels": 4,
 
47
  "resnet_out_scale_factor": 1.0,
48
  "resnet_skip_time_act": false,
49
  "resnet_time_scale_shift": "default",
50
+ "sample_size": 64,
51
  "time_cond_proj_dim": null,
52
  "time_embedding_act_fn": null,
53
  "time_embedding_dim": null,
54
  "time_embedding_type": "positional",
55
  "timestep_post_act": null,
56
+ "transformer_layers_per_block": 1,
57
  "up_block_types": [
58
+ "UpBlock2D",
59
  "CrossAttnUpBlock2D",
60
+ "CrossAttnUpBlock2D",
61
+ "CrossAttnUpBlock2D"
62
  ],
63
  "upcast_attention": false,
64
  "use_linear_projection": false
unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af538a6fa271655b41e60e056e43ffb99168478945de84a237622764b78c9a58
3
- size 5834433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c5540b0085d0329557df89c733b9d1b47e33e69b16fa2e740830e97dfc302e
3
+ size 3438375973
vae/config.json CHANGED
@@ -1,24 +1,31 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.17.0",
4
- "_name_or_path": "hf-internal-testing/tiny-stable-diffusion-pipe",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
- 32,
8
- 64
 
 
9
  ],
10
  "down_block_types": [
 
 
11
  "DownEncoderBlock2D",
12
  "DownEncoderBlock2D"
13
  ],
 
14
  "in_channels": 3,
15
  "latent_channels": 4,
16
- "layers_per_block": 1,
17
  "norm_num_groups": 32,
18
  "out_channels": 3,
19
- "sample_size": 32,
20
  "scaling_factor": 0.18215,
21
  "up_block_types": [
 
 
22
  "UpDecoderBlock2D",
23
  "UpDecoderBlock2D"
24
  ]
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.19.3",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
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
+ "layers_per_block": 2,
22
  "norm_num_groups": 32,
23
  "out_channels": 3,
24
+ "sample_size": 512,
25
  "scaling_factor": 0.18215,
26
  "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
  "UpDecoderBlock2D",
30
  "UpDecoderBlock2D"
31
  ]
vae/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:312beec1128406b4b3f0524ff15fe06e21a19759f36a835f8bd919ec741e52f4
3
- size 1365993
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa8c1b74b3e2781e4347b9b350203597674d8860a4338b46431de760c3a5dd22
3
+ size 167407857