patrickvonplaten commited on
Commit
f488742
1 Parent(s): 024a207

add diffusers 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 ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.6.0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
7
+ ],
8
+ "safety_checker": [
9
+ "stable_diffusion",
10
+ "StableDiffusionSafetyChecker"
11
+ ],
12
+ "scheduler": [
13
+ "diffusers",
14
+ "PNDMScheduler"
15
+ ],
16
+ "text_encoder": [
17
+ "transformers",
18
+ "CLIPTextModel"
19
+ ],
20
+ "tokenizer": [
21
+ "transformers",
22
+ "CLIPTokenizer"
23
+ ],
24
+ "unet": [
25
+ "diffusers",
26
+ "UNet2DConditionModel"
27
+ ],
28
+ "vae": [
29
+ "diffusers",
30
+ "AutoencoderKL"
31
+ ]
32
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
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
+ "bos_token_id": 0,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "dropout": 0.0,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": 2,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "quick_gelu",
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_factor": 1.0,
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "is_decoder": false,
41
+ "is_encoder_decoder": false,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1
45
+ },
46
+ "layer_norm_eps": 1e-05,
47
+ "length_penalty": 1.0,
48
+ "max_length": 20,
49
+ "max_position_embeddings": 77,
50
+ "min_length": 0,
51
+ "model_type": "clip_text_model",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 12,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_hidden_layers": 12,
57
+ "num_return_sequences": 1,
58
+ "output_attentions": false,
59
+ "output_hidden_states": false,
60
+ "output_scores": false,
61
+ "pad_token_id": 1,
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "task_specific_params": null,
71
+ "temperature": 1.0,
72
+ "tf_legacy_loss": false,
73
+ "tie_encoder_decoder": false,
74
+ "tie_word_embeddings": true,
75
+ "tokenizer_class": null,
76
+ "top_k": 50,
77
+ "top_p": 1.0,
78
+ "torch_dtype": null,
79
+ "torchscript": false,
80
+ "transformers_version": "4.22.0.dev0",
81
+ "typical_p": 1.0,
82
+ "use_bfloat16": false,
83
+ "vocab_size": 49408
84
+ },
85
+ "text_config_dict": {
86
+ "hidden_size": 768,
87
+ "intermediate_size": 3072,
88
+ "num_attention_heads": 12,
89
+ "num_hidden_layers": 12
90
+ },
91
+ "torch_dtype": "float32",
92
+ "transformers_version": null,
93
+ "vision_config": {
94
+ "_name_or_path": "",
95
+ "add_cross_attention": false,
96
+ "architectures": null,
97
+ "attention_dropout": 0.0,
98
+ "bad_words_ids": null,
99
+ "bos_token_id": null,
100
+ "chunk_size_feed_forward": 0,
101
+ "cross_attention_hidden_size": null,
102
+ "decoder_start_token_id": null,
103
+ "diversity_penalty": 0.0,
104
+ "do_sample": false,
105
+ "dropout": 0.0,
106
+ "early_stopping": false,
107
+ "encoder_no_repeat_ngram_size": 0,
108
+ "eos_token_id": null,
109
+ "exponential_decay_length_penalty": null,
110
+ "finetuning_task": null,
111
+ "forced_bos_token_id": null,
112
+ "forced_eos_token_id": null,
113
+ "hidden_act": "quick_gelu",
114
+ "hidden_size": 1024,
115
+ "id2label": {
116
+ "0": "LABEL_0",
117
+ "1": "LABEL_1"
118
+ },
119
+ "image_size": 224,
120
+ "initializer_factor": 1.0,
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 4096,
123
+ "is_decoder": false,
124
+ "is_encoder_decoder": false,
125
+ "label2id": {
126
+ "LABEL_0": 0,
127
+ "LABEL_1": 1
128
+ },
129
+ "layer_norm_eps": 1e-05,
130
+ "length_penalty": 1.0,
131
+ "max_length": 20,
132
+ "min_length": 0,
133
+ "model_type": "clip_vision_model",
134
+ "no_repeat_ngram_size": 0,
135
+ "num_attention_heads": 16,
136
+ "num_beam_groups": 1,
137
+ "num_beams": 1,
138
+ "num_channels": 3,
139
+ "num_hidden_layers": 24,
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": 14,
146
+ "prefix": null,
147
+ "problem_type": null,
148
+ "pruned_heads": {},
149
+ "remove_invalid_values": false,
150
+ "repetition_penalty": 1.0,
151
+ "return_dict": true,
152
+ "return_dict_in_generate": false,
153
+ "sep_token_id": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "transformers_version": "4.22.0.dev0",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ },
168
+ "vision_config_dict": {
169
+ "hidden_size": 1024,
170
+ "intermediate_size": 4096,
171
+ "num_attention_heads": 16,
172
+ "num_hidden_layers": 24,
173
+ "patch_size": 14
174
+ }
175
+ }
safety_checker/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:193490b58ef62739077262e833bf091c66c29488058681ac25cf7df3d8190974
3
+ size 1216061799
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.6.0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "num_train_timesteps": 1000,
8
+ "set_alpha_to_one": false,
9
+ "skip_prk_steps": true,
10
+ "steps_offset": 1,
11
+ "trained_betas": null
12
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.22.0.dev0",
24
+ "vocab_size": 49408
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770a47a9ffdcfda0b05506a7888ed714d06131d60267e6cf52765d61cf59fd67
3
+ size 492305335
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": "<|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 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": "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 ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.6.0",
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": 4,
24
+ "layers_per_block": 2,
25
+ "mid_block_scale_factor": 1,
26
+ "norm_eps": 1e-05,
27
+ "norm_num_groups": 32,
28
+ "out_channels": 4,
29
+ "sample_size": 32,
30
+ "up_block_types": [
31
+ "UpBlock2D",
32
+ "CrossAttnUpBlock2D",
33
+ "CrossAttnUpBlock2D",
34
+ "CrossAttnUpBlock2D"
35
+ ]
36
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7da0e21ba7ea50637bee26e81c220844defdf01aafca02b2c42ecdadb813de4
3
+ size 3438354725
v1-inference.yaml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ base_learning_rate: 1.0e-04
3
+ target: ldm.models.diffusion.ddpm.LatentDiffusion
4
+ params:
5
+ linear_start: 0.00085
6
+ linear_end: 0.0120
7
+ num_timesteps_cond: 1
8
+ log_every_t: 200
9
+ timesteps: 1000
10
+ first_stage_key: "jpg"
11
+ cond_stage_key: "txt"
12
+ image_size: 64
13
+ channels: 4
14
+ cond_stage_trainable: false # Note: different from the one we trained before
15
+ conditioning_key: crossattn
16
+ monitor: val/loss_simple_ema
17
+ scale_factor: 0.18215
18
+ use_ema: False
19
+
20
+ scheduler_config: # 10000 warmup steps
21
+ target: ldm.lr_scheduler.LambdaLinearScheduler
22
+ params:
23
+ warm_up_steps: [ 10000 ]
24
+ cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
25
+ f_start: [ 1.e-6 ]
26
+ f_max: [ 1. ]
27
+ f_min: [ 1. ]
28
+
29
+ unet_config:
30
+ target: ldm.modules.diffusionmodules.openaimodel.UNetModel
31
+ params:
32
+ image_size: 32 # unused
33
+ in_channels: 4
34
+ out_channels: 4
35
+ model_channels: 320
36
+ attention_resolutions: [ 4, 2, 1 ]
37
+ num_res_blocks: 2
38
+ channel_mult: [ 1, 2, 4, 4 ]
39
+ num_heads: 8
40
+ use_spatial_transformer: True
41
+ transformer_depth: 1
42
+ context_dim: 768
43
+ use_checkpoint: True
44
+ legacy: False
45
+
46
+ first_stage_config:
47
+ target: ldm.models.autoencoder.AutoencoderKL
48
+ params:
49
+ embed_dim: 4
50
+ monitor: val/rec_loss
51
+ ddconfig:
52
+ double_z: true
53
+ z_channels: 4
54
+ resolution: 256
55
+ in_channels: 3
56
+ out_ch: 3
57
+ ch: 128
58
+ ch_mult:
59
+ - 1
60
+ - 2
61
+ - 4
62
+ - 4
63
+ num_res_blocks: 2
64
+ attn_resolutions: []
65
+ dropout: 0.0
66
+ lossconfig:
67
+ target: torch.nn.Identity
68
+
69
+ cond_stage_config:
70
+ target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
vae/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.6.0",
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": 256,
23
+ "up_block_types": [
24
+ "UpDecoderBlock2D",
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D"
28
+ ]
29
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b134cded8eb78b184aefb8805b6b572f36fa77b255c483665dda931fa0130c5
3
+ size 334707217