Hugging Face's logo

xfh
/
test_sd_pokemon_model

Text-to-Image
Diffusers
TensorBoard
StableDiffusionPipeline
Inference Endpoints
Model card Files Metrics Community
3
xfh commited on
Commit
2b86b07
·
1 Parent(s): a23f43f

init

Browse files
Files changed (39) hide show
  1. feature_extractor/preprocessor_config.json +20 -0
  2. logs/text2image-fine-tune/1669436263.344843/events.out.tfevents.1669436263.xfh01.2764.1 +3 -0
  3. logs/text2image-fine-tune/1669436263.3456168/hparams.yml +36 -0
  4. logs/text2image-fine-tune/1669436790.3681219/events.out.tfevents.1669436790.xfh01.3486.1 +3 -0
  5. logs/text2image-fine-tune/1669436790.3686771/hparams.yml +36 -0
  6. logs/text2image-fine-tune/1669440696.9996736/events.out.tfevents.1669440696.xfh01.2226.1 +3 -0
  7. logs/text2image-fine-tune/1669440697.0002701/hparams.yml +36 -0
  8. logs/text2image-fine-tune/1669440772.90456/events.out.tfevents.1669440772.xfh01.2316.1 +3 -0
  9. logs/text2image-fine-tune/1669440772.9051244/hparams.yml +36 -0
  10. logs/text2image-fine-tune/1669442377.6729236/events.out.tfevents.1669442377.xfh01.2570.1 +3 -0
  11. logs/text2image-fine-tune/1669442377.6745534/hparams.yml +36 -0
  12. logs/text2image-fine-tune/1669470687.0407345/events.out.tfevents.1669470687.xfh01.26508.1 +3 -0
  13. logs/text2image-fine-tune/1669470687.0412807/hparams.yml +36 -0
  14. logs/text2image-fine-tune/1669470786.8168669/events.out.tfevents.1669470786.xfh01.26603.1 +3 -0
  15. logs/text2image-fine-tune/1669470786.8176863/hparams.yml +36 -0
  16. logs/text2image-fine-tune/1669470893.5055661/events.out.tfevents.1669470893.xfh01.26694.1 +3 -0
  17. logs/text2image-fine-tune/1669470893.5140162/hparams.yml +36 -0
  18. logs/text2image-fine-tune/events.out.tfevents.1669436263.xfh01.2764.0 +3 -0
  19. logs/text2image-fine-tune/events.out.tfevents.1669436790.xfh01.3486.0 +3 -0
  20. logs/text2image-fine-tune/events.out.tfevents.1669440696.xfh01.2226.0 +3 -0
  21. logs/text2image-fine-tune/events.out.tfevents.1669440772.xfh01.2316.0 +3 -0
  22. logs/text2image-fine-tune/events.out.tfevents.1669442377.xfh01.2570.0 +3 -0
  23. logs/text2image-fine-tune/events.out.tfevents.1669470687.xfh01.26508.0 +3 -0
  24. logs/text2image-fine-tune/events.out.tfevents.1669470786.xfh01.26603.0 +3 -0
  25. logs/text2image-fine-tune/events.out.tfevents.1669470893.xfh01.26694.0 +3 -0
  26. model_index.json +32 -0
  27. safety_checker/config.json +179 -0
  28. safety_checker/pytorch_model.bin +3 -0
  29. scheduler/scheduler_config.json +12 -0
  30. text_encoder/config.json +24 -0
  31. text_encoder/pytorch_model.bin +3 -0
  32. tokenizer/merges.txt +0 -0
  33. tokenizer/special_tokens_map.json +24 -0
  34. tokenizer/tokenizer_config.json +34 -0
  35. tokenizer/vocab.json +0 -0
  36. unet/config.json +37 -0
  37. unet/diffusion_pytorch_model.bin +3 -0
  38. vae/config.json +30 -0
  39. vae/diffusion_pytorch_model.bin +3 -0
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
+ }
logs/text2image-fine-tune/1669436263.344843/events.out.tfevents.1669436263.xfh01.2764.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3717807fca140efa478a446bd10dd99223d03f41538a4a0a5d10ab904b2d939
3
+ size 1665
logs/text2image-fine-tune/1669436263.3456168/hparams.yml ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ cache_dir: null
6
+ caption_column: text
7
+ center_crop: true
8
+ dataset_config_name: null
9
+ dataset_name: lambdalabs/pokemon-blip-captions
10
+ gradient_accumulation_steps: 4
11
+ gradient_checkpointing: true
12
+ hub_model_id: null
13
+ hub_token: null
14
+ image_column: image
15
+ learning_rate: 1.0e-05
16
+ local_rank: 0
17
+ logging_dir: logs
18
+ lr_scheduler: constant
19
+ lr_warmup_steps: 0
20
+ max_grad_norm: 1.0
21
+ max_train_samples: null
22
+ max_train_steps: 15000
23
+ mixed_precision: null
24
+ num_train_epochs: 143
25
+ output_dir: sd-pokemon-model
26
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
27
+ push_to_hub: false
28
+ random_flip: true
29
+ report_to: tensorboard
30
+ resolution: 512
31
+ scale_lr: false
32
+ seed: null
33
+ train_batch_size: 1
34
+ train_data_dir: null
35
+ use_8bit_adam: false
36
+ use_ema: true
logs/text2image-fine-tune/1669436790.3681219/events.out.tfevents.1669436790.xfh01.3486.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d180cdb62284da21d0307aaeedb8008e31bafb739c370bde2feefe2d029dfdc5
3
+ size 1665
logs/text2image-fine-tune/1669436790.3686771/hparams.yml ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ cache_dir: null
6
+ caption_column: text
7
+ center_crop: true
8
+ dataset_config_name: null
9
+ dataset_name: lambdalabs/pokemon-blip-captions
10
+ gradient_accumulation_steps: 4
11
+ gradient_checkpointing: true
12
+ hub_model_id: null
13
+ hub_token: null
14
+ image_column: image
15
+ learning_rate: 1.0e-05
16
+ local_rank: 0
17
+ logging_dir: logs
18
+ lr_scheduler: constant
19
+ lr_warmup_steps: 0
20
+ max_grad_norm: 1.0
21
+ max_train_samples: null
22
+ max_train_steps: 15000
23
+ mixed_precision: null
24
+ num_train_epochs: 72
25
+ output_dir: sd-pokemon-model
26
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
27
+ push_to_hub: false
28
+ random_flip: true
29
+ report_to: tensorboard
30
+ resolution: 512
31
+ scale_lr: false
32
+ seed: null
33
+ train_batch_size: 1
34
+ train_data_dir: null
35
+ use_8bit_adam: false
36
+ use_ema: true
logs/text2image-fine-tune/1669440696.9996736/events.out.tfevents.1669440696.xfh01.2226.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20be0c04660f95105d1b82e97f3954455e0b949ff9702f0cb030168b0d710b22
3
+ size 1665
logs/text2image-fine-tune/1669440697.0002701/hparams.yml ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ cache_dir: null
6
+ caption_column: text
7
+ center_crop: true
8
+ dataset_config_name: null
9
+ dataset_name: lambdalabs/pokemon-blip-captions
10
+ gradient_accumulation_steps: 4
11
+ gradient_checkpointing: true
12
+ hub_model_id: null
13
+ hub_token: null
14
+ image_column: image
15
+ learning_rate: 1.0e-05
16
+ local_rank: 0
17
+ logging_dir: logs
18
+ lr_scheduler: constant
19
+ lr_warmup_steps: 0
20
+ max_grad_norm: 1.0
21
+ max_train_samples: null
22
+ max_train_steps: 15000
23
+ mixed_precision: null
24
+ num_train_epochs: 72
25
+ output_dir: sd-pokemon-model
26
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
27
+ push_to_hub: false
28
+ random_flip: true
29
+ report_to: tensorboard
30
+ resolution: 512
31
+ scale_lr: false
32
+ seed: null
33
+ train_batch_size: 1
34
+ train_data_dir: null
35
+ use_8bit_adam: false
36
+ use_ema: true
logs/text2image-fine-tune/1669440772.90456/events.out.tfevents.1669440772.xfh01.2316.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd48e3efdfed3bff350a52f39494a43e3018f5baf716ea663c5d6061616531d
3
+ size 1665
logs/text2image-fine-tune/1669440772.9051244/hparams.yml ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ cache_dir: null
6
+ caption_column: text
7
+ center_crop: true
8
+ dataset_config_name: null
9
+ dataset_name: lambdalabs/pokemon-blip-captions
10
+ gradient_accumulation_steps: 4
11
+ gradient_checkpointing: true
12
+ hub_model_id: null
13
+ hub_token: null
14
+ image_column: image
15
+ learning_rate: 1.0e-05
16
+ local_rank: 0
17
+ logging_dir: logs
18
+ lr_scheduler: constant
19
+ lr_warmup_steps: 0
20
+ max_grad_norm: 1.0
21
+ max_train_samples: null
22
+ max_train_steps: 15000
23
+ mixed_precision: null
24
+ num_train_epochs: 72
25
+ output_dir: sd-pokemon-model
26
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
27
+ push_to_hub: false
28
+ random_flip: true
29
+ report_to: tensorboard
30
+ resolution: 512
31
+ scale_lr: false
32
+ seed: null
33
+ train_batch_size: 1
34
+ train_data_dir: null
35
+ use_8bit_adam: false
36
+ use_ema: true
logs/text2image-fine-tune/1669442377.6729236/events.out.tfevents.1669442377.xfh01.2570.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acbc998fe6f9961fccde10d34b9e68c3f5bb7d516257d34c5cd102d4b691da1d
3
+ size 1665
logs/text2image-fine-tune/1669442377.6745534/hparams.yml ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ cache_dir: null
6
+ caption_column: text
7
+ center_crop: true
8
+ dataset_config_name: null
9
+ dataset_name: lambdalabs/pokemon-blip-captions
10
+ gradient_accumulation_steps: 4
11
+ gradient_checkpointing: true
12
+ hub_model_id: null
13
+ hub_token: null
14
+ image_column: image
15
+ learning_rate: 1.0e-05
16
+ local_rank: 0
17
+ logging_dir: logs
18
+ lr_scheduler: constant
19
+ lr_warmup_steps: 0
20
+ max_grad_norm: 1.0
21
+ max_train_samples: null
22
+ max_train_steps: 5000
23
+ mixed_precision: null
24
+ num_train_epochs: 72
25
+ output_dir: sd-pokemon-model
26
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
27
+ push_to_hub: false
28
+ random_flip: true
29
+ report_to: tensorboard
30
+ resolution: 512
31
+ scale_lr: false
32
+ seed: null
33
+ train_batch_size: 3
34
+ train_data_dir: null
35
+ use_8bit_adam: false
36
+ use_ema: true
logs/text2image-fine-tune/1669470687.0407345/events.out.tfevents.1669470687.xfh01.26508.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bbd1eda1a11cbe5c92739da8bae88fd63a7abd80488433481bbc32b61d0151e
3
+ size 1665
logs/text2image-fine-tune/1669470687.0412807/hparams.yml ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ cache_dir: null
6
+ caption_column: text
7
+ center_crop: true
8
+ dataset_config_name: null
9
+ dataset_name: lambdalabs/pokemon-blip-captions
10
+ gradient_accumulation_steps: 4
11
+ gradient_checkpointing: true
12
+ hub_model_id: null
13
+ hub_token: null
14
+ image_column: image
15
+ learning_rate: 1.0e-05
16
+ local_rank: 0
17
+ logging_dir: logs
18
+ lr_scheduler: constant
19
+ lr_warmup_steps: 0
20
+ max_grad_norm: 1.0
21
+ max_train_samples: null
22
+ max_train_steps: 5000
23
+ mixed_precision: null
24
+ num_train_epochs: 24
25
+ output_dir: sd-pokemon-model
26
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
27
+ push_to_hub: false
28
+ random_flip: true
29
+ report_to: tensorboard
30
+ resolution: 512
31
+ scale_lr: false
32
+ seed: null
33
+ train_batch_size: 1
34
+ train_data_dir: null
35
+ use_8bit_adam: false
36
+ use_ema: true
logs/text2image-fine-tune/1669470786.8168669/events.out.tfevents.1669470786.xfh01.26603.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f628a681215ad03ffc99ac83f5e8a667a6111514ef78c7915d0aa3070cc0ea1
3
+ size 1665
logs/text2image-fine-tune/1669470786.8176863/hparams.yml ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ cache_dir: null
6
+ caption_column: text
7
+ center_crop: true
8
+ dataset_config_name: null
9
+ dataset_name: lambdalabs/pokemon-blip-captions
10
+ gradient_accumulation_steps: 4
11
+ gradient_checkpointing: true
12
+ hub_model_id: null
13
+ hub_token: null
14
+ image_column: image
15
+ learning_rate: 1.0e-05
16
+ local_rank: 0
17
+ logging_dir: logs
18
+ lr_scheduler: constant
19
+ lr_warmup_steps: 0
20
+ max_grad_norm: 1.0
21
+ max_train_samples: null
22
+ max_train_steps: 5000
23
+ mixed_precision: null
24
+ num_train_epochs: 24
25
+ output_dir: sd-pokemon-model
26
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
27
+ push_to_hub: false
28
+ random_flip: true
29
+ report_to: tensorboard
30
+ resolution: 512
31
+ scale_lr: false
32
+ seed: null
33
+ train_batch_size: 1
34
+ train_data_dir: null
35
+ use_8bit_adam: false
36
+ use_ema: true
logs/text2image-fine-tune/1669470893.5055661/events.out.tfevents.1669470893.xfh01.26694.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649263dfbcb511566975de168f53724f862d26c14d400251b605678b84881742
3
+ size 1665
logs/text2image-fine-tune/1669470893.5140162/hparams.yml ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ cache_dir: null
6
+ caption_column: text
7
+ center_crop: true
8
+ dataset_config_name: null
9
+ dataset_name: lambdalabs/pokemon-blip-captions
10
+ gradient_accumulation_steps: 4
11
+ gradient_checkpointing: true
12
+ hub_model_id: null
13
+ hub_token: null
14
+ image_column: image
15
+ learning_rate: 1.0e-05
16
+ local_rank: 0
17
+ logging_dir: logs
18
+ lr_scheduler: constant
19
+ lr_warmup_steps: 0
20
+ max_grad_norm: 1.0
21
+ max_train_samples: null
22
+ max_train_steps: 5000
23
+ mixed_precision: null
24
+ num_train_epochs: 24
25
+ output_dir: sd-pokemon-model
26
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
27
+ push_to_hub: false
28
+ random_flip: true
29
+ report_to: tensorboard
30
+ resolution: 512
31
+ scale_lr: false
32
+ seed: null
33
+ train_batch_size: 1
34
+ train_data_dir: null
35
+ use_8bit_adam: false
36
+ use_ema: true
logs/text2image-fine-tune/events.out.tfevents.1669436263.xfh01.2764.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451850bdc7bf296d0cd53f2bb88401731c84ec5725e9f096ac65b93e521979e8
3
+ size 2200
logs/text2image-fine-tune/events.out.tfevents.1669436790.xfh01.3486.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4186fd7020bc2c62281af720848ddd1ce1371b4e3cfc6533cb58973ebef9770d
3
+ size 3064
logs/text2image-fine-tune/events.out.tfevents.1669440696.xfh01.2226.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:941247b47786d80172842309d77365af12a391e55328a09c3e3b1e34dee2174f
3
+ size 472
logs/text2image-fine-tune/events.out.tfevents.1669440772.xfh01.2316.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4c82f692732f60599749b7318172ec0ac479593df29807cfd94e6787bd85e6
3
+ size 14417
logs/text2image-fine-tune/events.out.tfevents.1669442377.xfh01.2570.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca1f19757d3de54d9f6e77cd85ce9e931c67113519fc70a731a2b5146fdc8a6
3
+ size 92131
logs/text2image-fine-tune/events.out.tfevents.1669470687.xfh01.26508.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2f97bf2db4dfd62383067294478d6d1374e23ac609fcbde68d90fdab830e0e
3
+ size 40
logs/text2image-fine-tune/events.out.tfevents.1669470786.xfh01.26603.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3efafb5ea051a1780380a020f9e249ab37d3a93f24629269768ee0787b66ad08
3
+ size 472
logs/text2image-fine-tune/events.out.tfevents.1669470893.xfh01.26694.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf09aafe171c3b5f40dfe96904194c38ece76d6e50c5a818512c56d3698bdec5
3
+ size 244913
model_index.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.4.1",
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 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sep_token_id": null,
71
+ "suppress_tokens": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": null,
81
+ "torchscript": false,
82
+ "transformers_version": "4.24.0",
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "vocab_size": 49408
86
+ },
87
+ "text_config_dict": {
88
+ "hidden_size": 768,
89
+ "intermediate_size": 3072,
90
+ "num_attention_heads": 12,
91
+ "num_hidden_layers": 12
92
+ },
93
+ "torch_dtype": "float32",
94
+ "transformers_version": null,
95
+ "vision_config": {
96
+ "_name_or_path": "",
97
+ "add_cross_attention": false,
98
+ "architectures": null,
99
+ "attention_dropout": 0.0,
100
+ "bad_words_ids": null,
101
+ "begin_suppress_tokens": null,
102
+ "bos_token_id": null,
103
+ "chunk_size_feed_forward": 0,
104
+ "cross_attention_hidden_size": null,
105
+ "decoder_start_token_id": null,
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "dropout": 0.0,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "quick_gelu",
117
+ "hidden_size": 1024,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "image_size": 224,
123
+ "initializer_factor": 1.0,
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 4096,
126
+ "is_decoder": false,
127
+ "is_encoder_decoder": false,
128
+ "label2id": {
129
+ "LABEL_0": 0,
130
+ "LABEL_1": 1
131
+ },
132
+ "layer_norm_eps": 1e-05,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "min_length": 0,
136
+ "model_type": "clip_vision_model",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 16,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_channels": 3,
142
+ "num_hidden_layers": 24,
143
+ "num_return_sequences": 1,
144
+ "output_attentions": false,
145
+ "output_hidden_states": false,
146
+ "output_scores": false,
147
+ "pad_token_id": null,
148
+ "patch_size": 14,
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "pruned_heads": {},
152
+ "remove_invalid_values": false,
153
+ "repetition_penalty": 1.0,
154
+ "return_dict": true,
155
+ "return_dict_in_generate": false,
156
+ "sep_token_id": null,
157
+ "suppress_tokens": null,
158
+ "task_specific_params": null,
159
+ "temperature": 1.0,
160
+ "tf_legacy_loss": false,
161
+ "tie_encoder_decoder": false,
162
+ "tie_word_embeddings": true,
163
+ "tokenizer_class": null,
164
+ "top_k": 50,
165
+ "top_p": 1.0,
166
+ "torch_dtype": null,
167
+ "torchscript": false,
168
+ "transformers_version": "4.24.0",
169
+ "typical_p": 1.0,
170
+ "use_bfloat16": false
171
+ },
172
+ "vision_config_dict": {
173
+ "hidden_size": 1024,
174
+ "intermediate_size": 4096,
175
+ "num_attention_heads": 16,
176
+ "num_hidden_layers": 24,
177
+ "patch_size": 14
178
+ }
179
+ }
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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.4.1",
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 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.24.0",
23
+ "vocab_size": 49408
24
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a20d724dacc3f94e73753462567b578a6395b725e17b4ddaeddf0dd3bc148729
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "CompVis/stable-diffusion-v1-4",
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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.4.1",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "center_input_sample": false,
14
+ "cross_attention_dim": 768,
15
+ "down_block_types": [
16
+ "CrossAttnDownBlock2D",
17
+ "CrossAttnDownBlock2D",
18
+ "CrossAttnDownBlock2D",
19
+ "DownBlock2D"
20
+ ],
21
+ "downsample_padding": 1,
22
+ "flip_sin_to_cos": true,
23
+ "freq_shift": 0,
24
+ "in_channels": 4,
25
+ "layers_per_block": 2,
26
+ "mid_block_scale_factor": 1,
27
+ "norm_eps": 1e-05,
28
+ "norm_num_groups": 32,
29
+ "out_channels": 4,
30
+ "sample_size": 64,
31
+ "up_block_types": [
32
+ "UpBlock2D",
33
+ "CrossAttnUpBlock2D",
34
+ "CrossAttnUpBlock2D",
35
+ "CrossAttnUpBlock2D"
36
+ ]
37
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0149bbdb5ebe4a2cdbe3e87e6f88bdb36c4f20b327cb4bcbd539a6c0968540
3
+ size 3438230427
vae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.4.1",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d17aa398e021a2600c4a8b570060056a069a1b7b6f8ace78ffa52fff69395d
3
+ size 334715313