CSAle commited on
Commit
e5a62fe
1 Parent(s): 374f675

Upload with huggingface_hub

Browse files
Files changed (36) hide show
  1. feature_extractor/preprocessor_config.json +28 -0
  2. logs/text2image-fine-tune/1675983956.2002516/events.out.tfevents.1675983956.Neptune.12604.1 +3 -0
  3. logs/text2image-fine-tune/1675983956.2015917/hparams.yml +43 -0
  4. logs/text2image-fine-tune/1675984078.25978/events.out.tfevents.1675984078.Neptune.12755.1 +3 -0
  5. logs/text2image-fine-tune/1675984078.2612956/hparams.yml +43 -0
  6. logs/text2image-fine-tune/1675984340.6063933/events.out.tfevents.1675984340.Neptune.12845.1 +3 -0
  7. logs/text2image-fine-tune/1675984340.607931/hparams.yml +43 -0
  8. logs/text2image-fine-tune/1675984443.5766144/events.out.tfevents.1675984443.Neptune.13316.1 +3 -0
  9. logs/text2image-fine-tune/1675984443.5777953/hparams.yml +43 -0
  10. logs/text2image-fine-tune/1675984934.977128/events.out.tfevents.1675984934.Neptune.13767.1 +3 -0
  11. logs/text2image-fine-tune/1675984934.9782863/hparams.yml +43 -0
  12. logs/text2image-fine-tune/1675990270.8678262/events.out.tfevents.1675990270.Neptune.16485.1 +3 -0
  13. logs/text2image-fine-tune/1675990270.8693988/hparams.yml +43 -0
  14. logs/text2image-fine-tune/1675990314.0638402/events.out.tfevents.1675990314.Neptune.16660.1 +3 -0
  15. logs/text2image-fine-tune/1675990314.065287/hparams.yml +43 -0
  16. logs/text2image-fine-tune/events.out.tfevents.1675983956.Neptune.12604.0 +3 -0
  17. logs/text2image-fine-tune/events.out.tfevents.1675984078.Neptune.12755.0 +3 -0
  18. logs/text2image-fine-tune/events.out.tfevents.1675984340.Neptune.12845.0 +3 -0
  19. logs/text2image-fine-tune/events.out.tfevents.1675984443.Neptune.13316.0 +3 -0
  20. logs/text2image-fine-tune/events.out.tfevents.1675984934.Neptune.13767.0 +3 -0
  21. logs/text2image-fine-tune/events.out.tfevents.1675990270.Neptune.16485.0 +3 -0
  22. logs/text2image-fine-tune/events.out.tfevents.1675990314.Neptune.16660.0 +3 -0
  23. model_index.json +33 -0
  24. safety_checker/config.json +181 -0
  25. safety_checker/pytorch_model.bin +3 -0
  26. scheduler/scheduler_config.json +14 -0
  27. text_encoder/config.json +25 -0
  28. text_encoder/pytorch_model.bin +3 -0
  29. tokenizer/merges.txt +0 -0
  30. tokenizer/special_tokens_map.json +24 -0
  31. tokenizer/tokenizer_config.json +34 -0
  32. tokenizer/vocab.json +0 -0
  33. unet/config.json +55 -0
  34. unet/diffusion_pytorch_model.bin +3 -0
  35. vae/config.json +31 -0
  36. vae/diffusion_pytorch_model.bin +3 -0
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
+ }
logs/text2image-fine-tune/1675983956.2002516/events.out.tfevents.1675983956.Neptune.12604.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27250932a82b174ecce7e5ffd8926737d3b93c84bafeb5fbb28716f4e906a1a
3
+ size 1929
logs/text2image-fine-tune/1675983956.2015917/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: CSAle/DilbertDiffusionDataset
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 7500
30
+ output_dir: dilbert-model
31
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: null
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/1675984078.25978/events.out.tfevents.1675984078.Neptune.12755.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09fc8d1c92671be16f436bedfd6687f0893176eb3cab0b7b134ec75d73afc022
3
+ size 1929
logs/text2image-fine-tune/1675984078.2612956/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: CSAle/DilbertDiffusionDataset
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 7500
30
+ output_dir: dilbert-model
31
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: null
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/1675984340.6063933/events.out.tfevents.1675984340.Neptune.12845.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5843bd50497074eb44039c3eb06467854376dc92aa659947ee35086683d3bd76
3
+ size 1929
logs/text2image-fine-tune/1675984340.607931/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: CSAle/DilbertDiffusionDataset
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 7500
30
+ output_dir: dilbert-model
31
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-2
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: null
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/1675984443.5766144/events.out.tfevents.1675984443.Neptune.13316.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1906a4623251aeafabe7789555a492bd350d9316d74aeeaf16bf95643a421d5
3
+ size 1929
logs/text2image-fine-tune/1675984443.5777953/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: CSAle/DilbertDiffusionDataset
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 15000
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 7500
30
+ output_dir: dilbert-model
31
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-2
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: null
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/1675984934.977128/events.out.tfevents.1675984934.Neptune.13767.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f6425a101c47e84ce47808f4ad6d639030947b697974a4d9f30ca5d9fc63da
3
+ size 1929
logs/text2image-fine-tune/1675984934.9782863/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: CSAle/DilbertDiffusionDataset
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 400
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 200
30
+ output_dir: dilbert-model
31
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-2
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: null
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/1675990270.8678262/events.out.tfevents.1675990270.Neptune.16485.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da77cc522a2611a491142667ebd9c357b73e976c5ee4ab97854060d01cdeeac
3
+ size 1937
logs/text2image-fine-tune/1675990270.8693988/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: CSAle/DilbertDiffusionDataset
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 400
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 200
30
+ output_dir: dilbert-model
31
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: null
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/1675990314.0638402/events.out.tfevents.1675990314.Neptune.16660.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e03d4a11a3a5e0aaee23d820c967bebbcfd099268c89622563c0adbf83a2f0
3
+ size 1937
logs/text2image-fine-tune/1675990314.065287/hparams.yml ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ dataloader_num_workers: 0
11
+ dataset_config_name: null
12
+ dataset_name: CSAle/DilbertDiffusionDataset
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 4
15
+ gradient_checkpointing: true
16
+ hub_model_id: null
17
+ hub_token: null
18
+ image_column: image
19
+ learning_rate: 1.0e-05
20
+ local_rank: -1
21
+ logging_dir: logs
22
+ lr_scheduler: constant
23
+ lr_warmup_steps: 0
24
+ max_grad_norm: 1.0
25
+ max_train_samples: null
26
+ max_train_steps: 400
27
+ mixed_precision: null
28
+ non_ema_revision: null
29
+ num_train_epochs: 200
30
+ output_dir: dilbert-model
31
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1-base
32
+ push_to_hub: false
33
+ random_flip: true
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ scale_lr: false
39
+ seed: null
40
+ train_batch_size: 1
41
+ train_data_dir: null
42
+ use_8bit_adam: false
43
+ use_ema: true
logs/text2image-fine-tune/events.out.tfevents.1675983956.Neptune.12604.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4c13252fa47692688f5b234bf739813afc72137d9a9af093b43e9b90ad61eb
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1675984078.Neptune.12755.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bad1a74c7f4efc00a407fdd343619707c4545e02ff57316c0768843a70b6bec
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1675984340.Neptune.12845.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de84dbc60c2f9afc0ac0b1f2905c89131e119a38ca64681e966753d61094de9
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1675984443.Neptune.13316.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60055212db76ad166a2107be0c4dc8f7178bbba0fe708a09058d0687c134a666
3
+ size 16475
logs/text2image-fine-tune/events.out.tfevents.1675984934.Neptune.13767.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ab1a44b643ad47014c43f384c01d587f1495947070794662b67c973799a35e
3
+ size 19513
logs/text2image-fine-tune/events.out.tfevents.1675990270.Neptune.16485.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f5769aa6ba2bdf4228ed5379f6d9cf86bce211002b77a19cd58512ca070566
3
+ size 40
logs/text2image-fine-tune/events.out.tfevents.1675990314.Neptune.16660.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1952b41bba1693d9dc8abd89e327f077bdb758a4f9e595cf090329b7139278c4
3
+ size 19513
model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.13.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
7
+ ],
8
+ "requires_safety_checker": false,
9
+ "safety_checker": [
10
+ null,
11
+ null
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": "19fc41b79b00453e5a1e9620ebd991bb19b62991",
3
+ "_name_or_path": "/home/chris/.cache/huggingface/diffusers/models--CompVis--stable-diffusion-v1-2/snapshots/19fc41b79b00453e5a1e9620ebd991bb19b62991/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": "4.26.1",
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": "4.26.1",
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/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": "0.13.0.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": "stabilityai/stable-diffusion-2-1-base",
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": "float16",
23
+ "transformers_version": "4.26.1",
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:f2a06cf32cf585d03b55fef302142a5321b761ec440113925f64f4ceaffc7730
3
+ size 680904225
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": "/home/chris/.cache/huggingface/diffusers/models--stabilityai--stable-diffusion-2-1-base/snapshots/88bb1a46821197d1ac0cb54d1d09fb6e70b171bc/tokenizer",
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.13.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-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,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 4,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "resnet_time_scale_shift": "default",
43
+ "sample_size": 64,
44
+ "time_cond_proj_dim": null,
45
+ "time_embedding_type": "positional",
46
+ "timestep_post_act": null,
47
+ "up_block_types": [
48
+ "UpBlock2D",
49
+ "CrossAttnUpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D"
52
+ ],
53
+ "upcast_attention": false,
54
+ "use_linear_projection": true
55
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33875e1ef6b9a90d6957574d2256f724474a08c527fc4bb91b9cf1e1f2c16e11
3
+ size 3463934693
vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.13.0.dev0",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
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": 768,
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 sha256:11bc15ceb385823b4adb68bd5bdd7568d0c706c3de5ea9ebcb0b807092fc9030
3
+ size 167407601