Yeahia commited on
Commit
6d4d795
1 Parent(s): 98e2ecc

End of training

Browse files
Files changed (36) hide show
  1. README.md +17 -0
  2. feature_extractor/preprocessor_config.json +28 -0
  3. learned_embeds.safetensors +3 -0
  4. logs/textual_inversion/1694273189.2432952/events.out.tfevents.1694273189.uno.123988.1 +3 -0
  5. logs/textual_inversion/1694273189.244264/hparams.yml +47 -0
  6. logs/textual_inversion/1694273375.794672/events.out.tfevents.1694273375.uno.124321.1 +3 -0
  7. logs/textual_inversion/1694273375.795348/hparams.yml +47 -0
  8. logs/textual_inversion/1694273475.0678494/events.out.tfevents.1694273475.uno.124426.1 +3 -0
  9. logs/textual_inversion/1694273475.0685055/hparams.yml +47 -0
  10. logs/textual_inversion/1694274931.0763612/events.out.tfevents.1694274931.uno.124900.1 +3 -0
  11. logs/textual_inversion/1694274931.0770268/hparams.yml +47 -0
  12. logs/textual_inversion/1694276561.8736212/events.out.tfevents.1694276561.uno.125733.1 +3 -0
  13. logs/textual_inversion/1694276561.8743026/hparams.yml +47 -0
  14. logs/textual_inversion/1694277732.2635899/events.out.tfevents.1694277732.uno.125871.1 +3 -0
  15. logs/textual_inversion/1694277732.2642884/hparams.yml +47 -0
  16. logs/textual_inversion/events.out.tfevents.1694273189.uno.123988.0 +3 -0
  17. logs/textual_inversion/events.out.tfevents.1694273375.uno.124321.0 +3 -0
  18. logs/textual_inversion/events.out.tfevents.1694273475.uno.124426.0 +3 -0
  19. logs/textual_inversion/events.out.tfevents.1694274931.uno.124900.0 +3 -0
  20. logs/textual_inversion/events.out.tfevents.1694276561.uno.125733.0 +3 -0
  21. logs/textual_inversion/events.out.tfevents.1694277732.uno.125871.0 +3 -0
  22. model_index.json +34 -0
  23. safety_checker/config.json +28 -0
  24. safety_checker/model.safetensors +3 -0
  25. scheduler/scheduler_config.json +15 -0
  26. text_encoder/config.json +25 -0
  27. text_encoder/model.safetensors +3 -0
  28. tokenizer/added_tokens.json +3 -0
  29. tokenizer/merges.txt +0 -0
  30. tokenizer/special_tokens_map.json +24 -0
  31. tokenizer/tokenizer_config.json +33 -0
  32. tokenizer/vocab.json +0 -0
  33. unet/config.json +67 -0
  34. unet/diffusion_pytorch_model.safetensors +3 -0
  35. vae/config.json +32 -0
  36. vae/diffusion_pytorch_model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: runwayml/stable-diffusion-v1-5
5
+ tags:
6
+ - stable-diffusion
7
+ - stable-diffusion-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - textual_inversion
11
+ inference: true
12
+ ---
13
+
14
+ # Textual inversion text2image fine-tuning - Yeahia/textual_inversion_cat
15
+ These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
16
+
17
+
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
+ }
learned_embeds.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4c5023b2667e517feed29530339b2138f5270ec79d35259547e76ee6b7a159
3
+ size 3192
logs/textual_inversion/1694273189.2432952/events.out.tfevents.1694273189.uno.123988.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6c95b11581e54bcd7559b6e7c334259462bb38de0ee6f26aa247bdd66655f3
3
+ size 2342
logs/textual_inversion/1694273189.244264/hparams.yml ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ dataloader_num_workers: 0
10
+ enable_xformers_memory_efficient_attention: false
11
+ gradient_accumulation_steps: 4
12
+ gradient_checkpointing: false
13
+ hub_model_id: null
14
+ hub_token: null
15
+ initializer_token: toy
16
+ learnable_property: object
17
+ learning_rate: 0.002
18
+ local_rank: -1
19
+ logging_dir: logs
20
+ lr_num_cycles: 1
21
+ lr_scheduler: constant
22
+ lr_warmup_steps: 0
23
+ max_train_steps: 3000
24
+ mixed_precision: 'no'
25
+ no_safe_serialization: false
26
+ num_train_epochs: 24
27
+ num_validation_images: 4
28
+ num_vectors: 1
29
+ output_dir: textual_inversion_cat
30
+ placeholder_token: <cat-toy>
31
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
32
+ push_to_hub: true
33
+ repeats: 100
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ save_as_full_pipeline: false
39
+ save_steps: 500
40
+ scale_lr: true
41
+ seed: null
42
+ tokenizer_name: null
43
+ train_batch_size: 1
44
+ train_data_dir: /home/yeahia/test/images
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
logs/textual_inversion/1694273375.794672/events.out.tfevents.1694273375.uno.124321.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49f98345ae2611fffde166365387e5d45303777ec81b0c06643c91207324a5c5
3
+ size 2342
logs/textual_inversion/1694273375.795348/hparams.yml ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ dataloader_num_workers: 0
10
+ enable_xformers_memory_efficient_attention: false
11
+ gradient_accumulation_steps: 4
12
+ gradient_checkpointing: false
13
+ hub_model_id: null
14
+ hub_token: null
15
+ initializer_token: toy
16
+ learnable_property: object
17
+ learning_rate: 0.002
18
+ local_rank: -1
19
+ logging_dir: logs
20
+ lr_num_cycles: 1
21
+ lr_scheduler: constant
22
+ lr_warmup_steps: 0
23
+ max_train_steps: 300
24
+ mixed_precision: 'no'
25
+ no_safe_serialization: false
26
+ num_train_epochs: 3
27
+ num_validation_images: 4
28
+ num_vectors: 1
29
+ output_dir: textual_inversion_cat
30
+ placeholder_token: <cat-toy>
31
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
32
+ push_to_hub: false
33
+ repeats: 100
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ save_as_full_pipeline: false
39
+ save_steps: 500
40
+ scale_lr: true
41
+ seed: null
42
+ tokenizer_name: null
43
+ train_batch_size: 1
44
+ train_data_dir: /home/yeahia/test/images
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
logs/textual_inversion/1694273475.0678494/events.out.tfevents.1694273475.uno.124426.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879a6880451c469e5c40cbf26bcb656266cd1d15694ef7bb8134017546b95818
3
+ size 2342
logs/textual_inversion/1694273475.0685055/hparams.yml ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ dataloader_num_workers: 0
10
+ enable_xformers_memory_efficient_attention: false
11
+ gradient_accumulation_steps: 4
12
+ gradient_checkpointing: false
13
+ hub_model_id: null
14
+ hub_token: null
15
+ initializer_token: toy
16
+ learnable_property: object
17
+ learning_rate: 0.002
18
+ local_rank: -1
19
+ logging_dir: logs
20
+ lr_num_cycles: 1
21
+ lr_scheduler: constant
22
+ lr_warmup_steps: 0
23
+ max_train_steps: 30
24
+ mixed_precision: 'no'
25
+ no_safe_serialization: false
26
+ num_train_epochs: 1
27
+ num_validation_images: 4
28
+ num_vectors: 1
29
+ output_dir: textual_inversion_cat
30
+ placeholder_token: <cat-toy>
31
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
32
+ push_to_hub: false
33
+ repeats: 100
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ save_as_full_pipeline: false
39
+ save_steps: 500
40
+ scale_lr: true
41
+ seed: null
42
+ tokenizer_name: null
43
+ train_batch_size: 1
44
+ train_data_dir: /home/yeahia/test/images
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
logs/textual_inversion/1694274931.0763612/events.out.tfevents.1694274931.uno.124900.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5763a05bd43610821411b80aedf4cae610bf791c7f04aa412e000128261ab0a9
3
+ size 2351
logs/textual_inversion/1694274931.0770268/hparams.yml ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ dataloader_num_workers: 0
10
+ enable_xformers_memory_efficient_attention: false
11
+ gradient_accumulation_steps: 4
12
+ gradient_checkpointing: false
13
+ hub_model_id: null
14
+ hub_token: null
15
+ initializer_token: product
16
+ learnable_property: object
17
+ learning_rate: 0.002
18
+ local_rank: -1
19
+ logging_dir: logs
20
+ lr_num_cycles: 1
21
+ lr_scheduler: constant
22
+ lr_warmup_steps: 0
23
+ max_train_steps: 300
24
+ mixed_precision: 'no'
25
+ no_safe_serialization: false
26
+ num_train_epochs: 3
27
+ num_validation_images: 4
28
+ num_vectors: 1
29
+ output_dir: textual_inversion_cat
30
+ placeholder_token: <product-shot>
31
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
32
+ push_to_hub: false
33
+ repeats: 100
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ save_as_full_pipeline: false
39
+ save_steps: 500
40
+ scale_lr: true
41
+ seed: null
42
+ tokenizer_name: null
43
+ train_batch_size: 1
44
+ train_data_dir: /home/yeahia/test/images
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
logs/textual_inversion/1694276561.8736212/events.out.tfevents.1694276561.uno.125733.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f6eff372ef6106f2dc72ed875f171843a05b4bddf8c2f85516ab3f9f8e10f19
3
+ size 2351
logs/textual_inversion/1694276561.8743026/hparams.yml ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ dataloader_num_workers: 0
10
+ enable_xformers_memory_efficient_attention: false
11
+ gradient_accumulation_steps: 4
12
+ gradient_checkpointing: true
13
+ hub_model_id: null
14
+ hub_token: null
15
+ initializer_token: product
16
+ learnable_property: object
17
+ learning_rate: 0.002
18
+ local_rank: -1
19
+ logging_dir: logs
20
+ lr_num_cycles: 1
21
+ lr_scheduler: constant
22
+ lr_warmup_steps: 0
23
+ max_train_steps: 300
24
+ mixed_precision: 'no'
25
+ no_safe_serialization: false
26
+ num_train_epochs: 3
27
+ num_validation_images: 4
28
+ num_vectors: 1
29
+ output_dir: textual_inversion_cat
30
+ placeholder_token: <product-shot>
31
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
32
+ push_to_hub: false
33
+ repeats: 100
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ save_as_full_pipeline: false
39
+ save_steps: 500
40
+ scale_lr: true
41
+ seed: null
42
+ tokenizer_name: null
43
+ train_batch_size: 1
44
+ train_data_dir: /home/yeahia/test/images
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
logs/textual_inversion/1694277732.2635899/events.out.tfevents.1694277732.uno.125871.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e16653cb0f1efc02c3bdcb017ecd0ea953befe938b073b7454eb0678fa8ac9a
3
+ size 2351
logs/textual_inversion/1694277732.2642884/hparams.yml ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ dataloader_num_workers: 0
10
+ enable_xformers_memory_efficient_attention: false
11
+ gradient_accumulation_steps: 4
12
+ gradient_checkpointing: true
13
+ hub_model_id: null
14
+ hub_token: null
15
+ initializer_token: product
16
+ learnable_property: object
17
+ learning_rate: 0.002
18
+ local_rank: -1
19
+ logging_dir: logs
20
+ lr_num_cycles: 1
21
+ lr_scheduler: constant
22
+ lr_warmup_steps: 0
23
+ max_train_steps: 300
24
+ mixed_precision: 'no'
25
+ no_safe_serialization: false
26
+ num_train_epochs: 3
27
+ num_validation_images: 4
28
+ num_vectors: 1
29
+ output_dir: textual_inversion_cat
30
+ placeholder_token: <product-shot>
31
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
32
+ push_to_hub: true
33
+ repeats: 100
34
+ report_to: tensorboard
35
+ resolution: 512
36
+ resume_from_checkpoint: null
37
+ revision: null
38
+ save_as_full_pipeline: false
39
+ save_steps: 500
40
+ scale_lr: true
41
+ seed: null
42
+ tokenizer_name: null
43
+ train_batch_size: 1
44
+ train_data_dir: /home/yeahia/test/images
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
logs/textual_inversion/events.out.tfevents.1694273189.uno.123988.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe85d2d2e710b053f0a46768c74d6c4362ab0d16be8a43dbabe289a729777e05
3
+ size 4750
logs/textual_inversion/events.out.tfevents.1694273375.uno.124321.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b48100c136708e21ef4981f149d83f3cd15fc18d30773d44902cce5fd2fc04d
3
+ size 10408
logs/textual_inversion/events.out.tfevents.1694273475.uno.124426.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5f459bce011a769ca6a61d9142a5d01b7387e91cec923d95f83a0a078ecaa4
3
+ size 9916
logs/textual_inversion/events.out.tfevents.1694274931.uno.124900.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b017bf62c6257387d8d9ca38bc1166181ac3d0be3fccb8d666b6105cbeb4b233
3
+ size 99854
logs/textual_inversion/events.out.tfevents.1694276561.uno.125733.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d285da2abd1dcb132d2ee073b7ffe8931ff32a3571e2af08a15617d6d45a75
3
+ size 99854
logs/textual_inversion/events.out.tfevents.1694277732.uno.125871.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed90ecef2611701859d132b72be180752d733e04878ec809a3344a81697fd5ef
3
+ size 99854
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "requires_safety_checker": true,
10
+ "safety_checker": [
11
+ "stable_diffusion",
12
+ "StableDiffusionSafetyChecker"
13
+ ],
14
+ "scheduler": [
15
+ "diffusers",
16
+ "PNDMScheduler"
17
+ ],
18
+ "text_encoder": [
19
+ "transformers",
20
+ "CLIPTextModel"
21
+ ],
22
+ "tokenizer": [
23
+ "transformers",
24
+ "CLIPTokenizer"
25
+ ],
26
+ "unet": [
27
+ "diffusers",
28
+ "UNet2DConditionModel"
29
+ ],
30
+ "vae": [
31
+ "diffusers",
32
+ "AutoencoderKL"
33
+ ]
34
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/yeahia/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/1d0c4ebf6ff58a5caecab40fa1406526bca4b5b9/safety_checker",
3
+ "architectures": [
4
+ "StableDiffusionSafetyChecker"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "intermediate_size": 3072,
14
+ "model_type": "clip_text_model",
15
+ "num_attention_heads": 12
16
+ },
17
+ "torch_dtype": "float32",
18
+ "transformers_version": "4.34.0.dev0",
19
+ "vision_config": {
20
+ "dropout": 0.0,
21
+ "hidden_size": 1024,
22
+ "intermediate_size": 4096,
23
+ "model_type": "clip_vision_model",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "patch_size": 14
27
+ }
28
+ }
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.21.0.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
+ "timestep_spacing": "leading",
14
+ "trained_betas": null
15
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
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": "4.34.0.dev0",
24
+ "vocab_size": 49409
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42c91c07d7a87aaba4f52d0b6c66a935caa4c4c5b820bc648e3b8bfd17189a7
3
+ size 492268240
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<product-shot>": 49408
3
+ }
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 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
5
+ "act_fn": "silu",
6
+ "addition_embed_type": null,
7
+ "addition_embed_type_num_heads": 64,
8
+ "addition_time_embed_dim": null,
9
+ "attention_head_dim": 8,
10
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_attention_heads": null,
45
+ "num_class_embeds": null,
46
+ "only_cross_attention": false,
47
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "sample_size": 64,
53
+ "time_cond_proj_dim": null,
54
+ "time_embedding_act_fn": null,
55
+ "time_embedding_dim": null,
56
+ "time_embedding_type": "positional",
57
+ "timestep_post_act": null,
58
+ "transformer_layers_per_block": 1,
59
+ "up_block_types": [
60
+ "UpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D"
64
+ ],
65
+ "upcast_attention": false,
66
+ "use_linear_projection": false
67
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27cd69d4a0aa32105087a619f32a51bc087e133be93fe23da92f3c0bcc07d79
3
+ size 3438167536
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "_name_or_path": "runwayml/stable-diffusion-v1-5",
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
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "layers_per_block": 2,
22
+ "norm_num_groups": 32,
23
+ "out_channels": 3,
24
+ "sample_size": 512,
25
+ "scaling_factor": 0.18215,
26
+ "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ]
32
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d2b5932bb4151e54e694fd31ccf51fca908223c9485bd56cd0e1d83ad94c49
3
+ size 334643268