sang-kyung commited on
Commit
024f7a3
1 Parent(s): 1e14451

End of training

Browse files
Files changed (34) hide show
  1. README.md +22 -0
  2. checkpoint-500/model_index.json +32 -0
  3. checkpoint-500/optimizer.bin +3 -0
  4. checkpoint-500/random_states_0.pkl +3 -0
  5. checkpoint-500/scaler.pt +3 -0
  6. checkpoint-500/scheduler.bin +3 -0
  7. checkpoint-500/text_encoder/config.json +25 -0
  8. checkpoint-500/text_encoder/pytorch_model.bin +3 -0
  9. checkpoint-500/unet/config.json +63 -0
  10. checkpoint-500/unet/diffusion_pytorch_model.bin +3 -0
  11. feature_extractor/preprocessor_config.json +28 -0
  12. logs/dreambooth/1687676646.8698778/events.out.tfevents.1687676646.alin20.3092872.1 +3 -0
  13. logs/dreambooth/1687676646.8728988/hparams.yml +58 -0
  14. logs/dreambooth/1687677365.7089162/events.out.tfevents.1687677365.alin20.3108130.1 +3 -0
  15. logs/dreambooth/1687677365.712464/hparams.yml +58 -0
  16. logs/dreambooth/1687678654.5114737/events.out.tfevents.1687678654.alin20.3128641.1 +3 -0
  17. logs/dreambooth/1687678654.5148494/hparams.yml +58 -0
  18. logs/dreambooth/events.out.tfevents.1687676646.alin20.3092872.0 +3 -0
  19. logs/dreambooth/events.out.tfevents.1687677365.alin20.3108130.0 +3 -0
  20. logs/dreambooth/events.out.tfevents.1687678654.alin20.3128641.0 +3 -0
  21. model_index.json +33 -0
  22. safety_checker/config.json +168 -0
  23. safety_checker/pytorch_model.bin +3 -0
  24. scheduler/scheduler_config.json +14 -0
  25. text_encoder/config.json +25 -0
  26. text_encoder/pytorch_model.bin +3 -0
  27. tokenizer/merges.txt +0 -0
  28. tokenizer/special_tokens_map.json +24 -0
  29. tokenizer/tokenizer_config.json +33 -0
  30. tokenizer/vocab.json +0 -0
  31. unet/config.json +63 -0
  32. unet/diffusion_pytorch_model.bin +3 -0
  33. vae/config.json +31 -0
  34. vae/diffusion_pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: CompVis/stable-diffusion-v1-4
5
+ instance_prompt: a photo of sks dog
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - dreambooth
12
+ inference: true
13
+ ---
14
+
15
+ # DreamBooth - sang-kyung/ckpt
16
+
17
+ This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/).
18
+ You can find some example images in the following.
19
+
20
+
21
+
22
+ DreamBooth for the text encoder was enabled: True.
checkpoint-500/model_index.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.2.2",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
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
+ }
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f5f99af10ff9df61e802b4e42ab42305d1b1ed4eef1acced444529573173c75
3
+ size 1972599009
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df2311bad4ef01be2e2fe04990925bba44b96737cd6fac19ea43d1a0001e093e
3
+ size 14727
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
3
+ size 557
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6be622d51c3bcf8a1991c02b9778f31d7e3a79a8b22e03e81a36e25205ef4c5b
3
+ size 563
checkpoint-500/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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": 512,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.2",
24
+ "vocab_size": 49408
25
+ }
checkpoint-500/text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c41a5f139c20be958617fcab1a378e67565712d23d3d4901c29bb979168751
3
+ size 492309793
checkpoint-500/unet/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 768,
21
+ "cross_attention_norm": null,
22
+ "down_block_types": [
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "DownBlock2D"
27
+ ],
28
+ "downsample_padding": 1,
29
+ "dual_cross_attention": false,
30
+ "encoder_hid_dim": null,
31
+ "encoder_hid_dim_type": null,
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 4,
35
+ "layers_per_block": 2,
36
+ "mid_block_only_cross_attention": null,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
39
+ "norm_eps": 1e-05,
40
+ "norm_num_groups": 32,
41
+ "num_attention_heads": null,
42
+ "num_class_embeds": null,
43
+ "only_cross_attention": false,
44
+ "out_channels": 4,
45
+ "projection_class_embeddings_input_dim": null,
46
+ "resnet_out_scale_factor": 1.0,
47
+ "resnet_skip_time_act": false,
48
+ "resnet_time_scale_shift": "default",
49
+ "sample_size": 64,
50
+ "time_cond_proj_dim": null,
51
+ "time_embedding_act_fn": null,
52
+ "time_embedding_dim": null,
53
+ "time_embedding_type": "positional",
54
+ "timestep_post_act": null,
55
+ "up_block_types": [
56
+ "UpBlock2D",
57
+ "CrossAttnUpBlock2D",
58
+ "CrossAttnUpBlock2D",
59
+ "CrossAttnUpBlock2D"
60
+ ],
61
+ "upcast_attention": false,
62
+ "use_linear_projection": false
63
+ }
checkpoint-500/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ac6d3e040bb43a998f3b576ea0e6a51894dfd410ad2aee28a3605b187f3d608
3
+ size 3438375973
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": "CLIPImageProcessor",
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
+ }
logs/dreambooth/1687676646.8698778/events.out.tfevents.1687676646.alin20.3092872.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93322b839486310914d2b5c0096a868f5201c61cf6608b23cad1c3287f1b2595
3
+ size 2709
logs/dreambooth/1687676646.8728988/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_labels_conditioning: null
11
+ class_prompt: null
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 1
15
+ gradient_checkpointing: false
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: ./dog
19
+ instance_prompt: a photo of sks dog
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 0
27
+ max_grad_norm: 1.0
28
+ max_train_steps: 400
29
+ mixed_precision: fp16
30
+ num_class_images: 100
31
+ num_train_epochs: 80
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: ./ckpt
35
+ pre_compute_text_embeddings: false
36
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
37
+ prior_generation_precision: null
38
+ prior_loss_weight: 1.0
39
+ push_to_hub: true
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ set_grads_to_none: false
48
+ skip_save_text_encoder: false
49
+ text_encoder_use_attention_mask: false
50
+ tokenizer_max_length: null
51
+ tokenizer_name: null
52
+ train_batch_size: 1
53
+ train_text_encoder: true
54
+ use_8bit_adam: false
55
+ validation_images: null
56
+ validation_prompt: null
57
+ validation_steps: 100
58
+ with_prior_preservation: false
logs/dreambooth/1687677365.7089162/events.out.tfevents.1687677365.alin20.3108130.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eef1bab1dce94743fd9b003416ab5482fcd1f430ae36f0f37be159217aa4ae91
3
+ size 2709
logs/dreambooth/1687677365.712464/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_labels_conditioning: null
11
+ class_prompt: null
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 2
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: ./dog
19
+ instance_prompt: a photo of sks dog
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 0
27
+ max_grad_norm: 1.0
28
+ max_train_steps: 800
29
+ mixed_precision: fp16
30
+ num_class_images: 100
31
+ num_train_epochs: 267
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: ./ckpt
35
+ pre_compute_text_embeddings: false
36
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
37
+ prior_generation_precision: null
38
+ prior_loss_weight: 1.0
39
+ push_to_hub: true
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ set_grads_to_none: false
48
+ skip_save_text_encoder: false
49
+ text_encoder_use_attention_mask: false
50
+ tokenizer_max_length: null
51
+ tokenizer_name: null
52
+ train_batch_size: 1
53
+ train_text_encoder: true
54
+ use_8bit_adam: true
55
+ validation_images: null
56
+ validation_prompt: null
57
+ validation_steps: 100
58
+ with_prior_preservation: false
logs/dreambooth/1687678654.5114737/events.out.tfevents.1687678654.alin20.3128641.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b2510523326dd5131f9fb081d350d1a1b58da797b74b2e5ef50cf97afc9a11
3
+ size 2709
logs/dreambooth/1687678654.5148494/hparams.yml ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_labels_conditioning: null
11
+ class_prompt: null
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 2
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: ./dog
19
+ instance_prompt: a photo of sks dog
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 0
27
+ max_grad_norm: 1.0
28
+ max_train_steps: 800
29
+ mixed_precision: fp16
30
+ num_class_images: 100
31
+ num_train_epochs: 267
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: ./ckpt
35
+ pre_compute_text_embeddings: false
36
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
37
+ prior_generation_precision: null
38
+ prior_loss_weight: 1.0
39
+ push_to_hub: true
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ set_grads_to_none: false
48
+ skip_save_text_encoder: false
49
+ text_encoder_use_attention_mask: false
50
+ tokenizer_max_length: null
51
+ tokenizer_name: null
52
+ train_batch_size: 1
53
+ train_text_encoder: true
54
+ use_8bit_adam: true
55
+ validation_images: null
56
+ validation_prompt: null
57
+ validation_steps: 100
58
+ with_prior_preservation: false
logs/dreambooth/events.out.tfevents.1687676646.alin20.3092872.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079f6e749042e45ea492db32397595de294e5458e699e2b83f3d214804b17a60
3
+ size 88
logs/dreambooth/events.out.tfevents.1687677365.alin20.3108130.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24f3aa507badda3f37ec3ad2ed6c1d47bcbafc4512b50001e8a4b9301309e56
3
+ size 111714
logs/dreambooth/events.out.tfevents.1687678654.alin20.3128641.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96554e4973246a73b4738b74186bcc3ffe10e6180af1a6bc2e421cf475cf837a
3
+ size 111714
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
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 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "59ec6bdf37d6279d3c0faf36e89ff1aa34f7ebf4",
3
+ "_name_or_path": "/home/sangkyung/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/59ec6bdf37d6279d3c0faf36e89ff1aa34f7ebf4/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": "4.30.2",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "torch_dtype": "float32",
89
+ "transformers_version": null,
90
+ "vision_config": {
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,
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_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,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": 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": "4.30.2",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ }
168
+ }
safety_checker/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
+ size 1216064769
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.18.0.dev0",
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
+ "trained_betas": null
14
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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": 512,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.2",
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 sha256:2954716ae368787488ef38ea85e32aae00ade167fb70c8c0e14b0ddf6baf989a
3
+ size 492309793
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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
+ 320,
11
+ 640,
12
+ 1280,
13
+ 1280
14
+ ],
15
+ "center_input_sample": false,
16
+ "class_embed_type": null,
17
+ "class_embeddings_concat": false,
18
+ "conv_in_kernel": 3,
19
+ "conv_out_kernel": 3,
20
+ "cross_attention_dim": 768,
21
+ "cross_attention_norm": null,
22
+ "down_block_types": [
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "DownBlock2D"
27
+ ],
28
+ "downsample_padding": 1,
29
+ "dual_cross_attention": false,
30
+ "encoder_hid_dim": null,
31
+ "encoder_hid_dim_type": null,
32
+ "flip_sin_to_cos": true,
33
+ "freq_shift": 0,
34
+ "in_channels": 4,
35
+ "layers_per_block": 2,
36
+ "mid_block_only_cross_attention": null,
37
+ "mid_block_scale_factor": 1,
38
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
39
+ "norm_eps": 1e-05,
40
+ "norm_num_groups": 32,
41
+ "num_attention_heads": null,
42
+ "num_class_embeds": null,
43
+ "only_cross_attention": false,
44
+ "out_channels": 4,
45
+ "projection_class_embeddings_input_dim": null,
46
+ "resnet_out_scale_factor": 1.0,
47
+ "resnet_skip_time_act": false,
48
+ "resnet_time_scale_shift": "default",
49
+ "sample_size": 64,
50
+ "time_cond_proj_dim": null,
51
+ "time_embedding_act_fn": null,
52
+ "time_embedding_dim": null,
53
+ "time_embedding_type": "positional",
54
+ "timestep_post_act": null,
55
+ "up_block_types": [
56
+ "UpBlock2D",
57
+ "CrossAttnUpBlock2D",
58
+ "CrossAttnUpBlock2D",
59
+ "CrossAttnUpBlock2D"
60
+ ],
61
+ "upcast_attention": false,
62
+ "use_linear_projection": false
63
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d22fb43e533c649bf1530c1f45421e3b9c644892140abc435ff35d2a550b5ef8
3
+ size 3438375973
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": "/home/sangkyung/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/59ec6bdf37d6279d3c0faf36e89ff1aa34f7ebf4/vae",
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
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c02e0c7c263a4c0630ca3a72380ff55b9e38e0ab41d64dff7bf620a58342bc75
3
+ size 334712113