saltacc commited on
Commit
552da11
1 Parent(s): 4d84adb
checkpoints/wd-1-5-beta2-aesthetic-fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96fc8b5de4ea310ac42680dc122485ba3a3cb029913052c9d09a92fea877ce57
3
+ size 2580068692
checkpoints/wd-1-5-beta2-aesthetic-fp16.yaml ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False # we set this to false because this is an inference only config
20
+
21
+ unet_config:
22
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
23
+ params:
24
+ use_checkpoint: True
25
+ use_fp16: True
26
+ image_size: 32 # unused
27
+ in_channels: 4
28
+ out_channels: 4
29
+ model_channels: 320
30
+ attention_resolutions: [ 4, 2, 1 ]
31
+ num_res_blocks: 2
32
+ channel_mult: [ 1, 2, 4, 4 ]
33
+ num_head_channels: 64 # need to fix for flash-attn
34
+ use_spatial_transformer: True
35
+ use_linear_in_transformer: True
36
+ transformer_depth: 1
37
+ context_dim: 1024
38
+ legacy: False
39
+
40
+ first_stage_config:
41
+ target: ldm.models.autoencoder.AutoencoderKL
42
+ params:
43
+ embed_dim: 4
44
+ monitor: val/rec_loss
45
+ ddconfig:
46
+ #attn_type: "vanilla-xformers"
47
+ double_z: true
48
+ z_channels: 4
49
+ resolution: 256
50
+ in_channels: 3
51
+ out_ch: 3
52
+ ch: 128
53
+ ch_mult:
54
+ - 1
55
+ - 2
56
+ - 4
57
+ - 4
58
+ num_res_blocks: 2
59
+ attn_resolutions: []
60
+ dropout: 0.0
61
+ lossconfig:
62
+ target: torch.nn.Identity
63
+
64
+ cond_stage_config:
65
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
66
+ params:
67
+ freeze: True
68
+ layer: "penultimate"
checkpoints/wd-1-5-beta2-aesthetic-fp32.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711cd95c77dc04e4f76a40c06b4c8fce64c1c4373c7d461a9121cb624afe6dcd
3
+ size 5159974886
checkpoints/wd-1-5-beta2-aesthetic-fp32.yaml ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False # we set this to false because this is an inference only config
20
+
21
+ unet_config:
22
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
23
+ params:
24
+ use_checkpoint: True
25
+ use_fp16: True
26
+ image_size: 32 # unused
27
+ in_channels: 4
28
+ out_channels: 4
29
+ model_channels: 320
30
+ attention_resolutions: [ 4, 2, 1 ]
31
+ num_res_blocks: 2
32
+ channel_mult: [ 1, 2, 4, 4 ]
33
+ num_head_channels: 64 # need to fix for flash-attn
34
+ use_spatial_transformer: True
35
+ use_linear_in_transformer: True
36
+ transformer_depth: 1
37
+ context_dim: 1024
38
+ legacy: False
39
+
40
+ first_stage_config:
41
+ target: ldm.models.autoencoder.AutoencoderKL
42
+ params:
43
+ embed_dim: 4
44
+ monitor: val/rec_loss
45
+ ddconfig:
46
+ #attn_type: "vanilla-xformers"
47
+ double_z: true
48
+ z_channels: 4
49
+ resolution: 256
50
+ in_channels: 3
51
+ out_ch: 3
52
+ ch: 128
53
+ ch_mult:
54
+ - 1
55
+ - 2
56
+ - 4
57
+ - 4
58
+ num_res_blocks: 2
59
+ attn_resolutions: []
60
+ dropout: 0.0
61
+ lossconfig:
62
+ target: torch.nn.Identity
63
+
64
+ cond_stage_config:
65
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
66
+ params:
67
+ freeze: True
68
+ layer: "penultimate"
checkpoints/wd-1-5-beta2-fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf1855f4d12824b96d9350ad325ac709a488a1b6fb417f0f6f87f85f4b5e1ee
3
+ size 2580068692
checkpoints/wd-1-5-beta2-fp16.yaml ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False # we set this to false because this is an inference only config
20
+
21
+ unet_config:
22
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
23
+ params:
24
+ use_checkpoint: True
25
+ use_fp16: True
26
+ image_size: 32 # unused
27
+ in_channels: 4
28
+ out_channels: 4
29
+ model_channels: 320
30
+ attention_resolutions: [ 4, 2, 1 ]
31
+ num_res_blocks: 2
32
+ channel_mult: [ 1, 2, 4, 4 ]
33
+ num_head_channels: 64 # need to fix for flash-attn
34
+ use_spatial_transformer: True
35
+ use_linear_in_transformer: True
36
+ transformer_depth: 1
37
+ context_dim: 1024
38
+ legacy: False
39
+
40
+ first_stage_config:
41
+ target: ldm.models.autoencoder.AutoencoderKL
42
+ params:
43
+ embed_dim: 4
44
+ monitor: val/rec_loss
45
+ ddconfig:
46
+ #attn_type: "vanilla-xformers"
47
+ double_z: true
48
+ z_channels: 4
49
+ resolution: 256
50
+ in_channels: 3
51
+ out_ch: 3
52
+ ch: 128
53
+ ch_mult:
54
+ - 1
55
+ - 2
56
+ - 4
57
+ - 4
58
+ num_res_blocks: 2
59
+ attn_resolutions: []
60
+ dropout: 0.0
61
+ lossconfig:
62
+ target: torch.nn.Identity
63
+
64
+ cond_stage_config:
65
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
66
+ params:
67
+ freeze: True
68
+ layer: "penultimate"
checkpoints/wd-1-5-beta2-fp32.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764f93581d80b46011039bb388e899f17f7869fce7e7928b060e9a5574bd8f84
3
+ size 5159974886
checkpoints/wd-1-5-beta2-fp32.yaml ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-4
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ parameterization: "v"
6
+ linear_start: 0.00085
7
+ linear_end: 0.0120
8
+ num_timesteps_cond: 1
9
+ log_every_t: 200
10
+ timesteps: 1000
11
+ first_stage_key: "jpg"
12
+ cond_stage_key: "txt"
13
+ image_size: 64
14
+ channels: 4
15
+ cond_stage_trainable: false
16
+ conditioning_key: crossattn
17
+ monitor: val/loss_simple_ema
18
+ scale_factor: 0.18215
19
+ use_ema: False # we set this to false because this is an inference only config
20
+
21
+ unet_config:
22
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
23
+ params:
24
+ use_checkpoint: True
25
+ use_fp16: True
26
+ image_size: 32 # unused
27
+ in_channels: 4
28
+ out_channels: 4
29
+ model_channels: 320
30
+ attention_resolutions: [ 4, 2, 1 ]
31
+ num_res_blocks: 2
32
+ channel_mult: [ 1, 2, 4, 4 ]
33
+ num_head_channels: 64 # need to fix for flash-attn
34
+ use_spatial_transformer: True
35
+ use_linear_in_transformer: True
36
+ transformer_depth: 1
37
+ context_dim: 1024
38
+ legacy: False
39
+
40
+ first_stage_config:
41
+ target: ldm.models.autoencoder.AutoencoderKL
42
+ params:
43
+ embed_dim: 4
44
+ monitor: val/rec_loss
45
+ ddconfig:
46
+ #attn_type: "vanilla-xformers"
47
+ double_z: true
48
+ z_channels: 4
49
+ resolution: 256
50
+ in_channels: 3
51
+ out_ch: 3
52
+ ch: 128
53
+ ch_mult:
54
+ - 1
55
+ - 2
56
+ - 4
57
+ - 4
58
+ num_res_blocks: 2
59
+ attn_resolutions: []
60
+ dropout: 0.0
61
+ lossconfig:
62
+ target: torch.nn.Identity
63
+
64
+ cond_stage_config:
65
+ target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
66
+ params:
67
+ freeze: True
68
+ layer: "penultimate"
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.12.1",
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 ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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",
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",
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/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4666d0f9b718a6ed165ce95b8aac0d3d78031b8906fdc88ca8e735af5261788c
3
+ size 1215981833
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.12.1",
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": "v_prediction",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/sd-finetune-data/cafe-output/wd-15-official-step-2-2023-02-03-18-08/step_120000",
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": "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": "4.26.0",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cce6febb0b6d876ee5eb24af35e27e764eb4f9b1d0b7c026c8c3333d4cfc916c
3
+ size 1361597018
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "!",
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 ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "/mnt/sd-finetune-data/cafe-output/wd-15-official-step-2-2023-02-03-18-08/step_120000",
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 ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.12.1",
4
+ "_name_or_path": "/mnt/sd-finetune-data/cafe-output/wd-15-official-step-2-2023-02-03-18-08/step_120000",
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,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "cross_attention_dim": 1024,
21
+ "down_block_types": [
22
+ "CrossAttnDownBlock2D",
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "DownBlock2D"
26
+ ],
27
+ "downsample_padding": 1,
28
+ "dual_cross_attention": false,
29
+ "flip_sin_to_cos": true,
30
+ "freq_shift": 0,
31
+ "in_channels": 4,
32
+ "layers_per_block": 2,
33
+ "mid_block_scale_factor": 1,
34
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
35
+ "norm_eps": 1e-05,
36
+ "norm_num_groups": 32,
37
+ "num_class_embeds": null,
38
+ "only_cross_attention": false,
39
+ "out_channels": 4,
40
+ "resnet_time_scale_shift": "default",
41
+ "sample_size": 96,
42
+ "up_block_types": [
43
+ "UpBlock2D",
44
+ "CrossAttnUpBlock2D",
45
+ "CrossAttnUpBlock2D",
46
+ "CrossAttnUpBlock2D"
47
+ ],
48
+ "upcast_attention": true,
49
+ "use_linear_projection": true
50
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05101bc4e37285316a455022dc331e2118a01a17baf0b346f322730f5c4c945b
3
+ size 3463726467
vae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.12.1",
4
+ "_name_or_path": "/mnt/sd-finetune-data/cafe/cafe-tools/vae-v2/vae-v2",
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
+ "up_block_types": [
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D"
29
+ ]
30
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ba2a6f13818912597aabe11b15e3cb20c4b80fbb28c469284687b2c5758d474
3
+ size 334643245