Dytorch commited on
Commit
4f444ec
1 Parent(s): 72bc524

End of training

Browse files
Files changed (50) hide show
  1. README.md +17 -0
  2. checkpoint-1000/optimizer.bin +3 -0
  3. checkpoint-1000/pytorch_model.bin +3 -0
  4. checkpoint-1000/random_states_0.pkl +3 -0
  5. checkpoint-1000/scheduler.bin +3 -0
  6. checkpoint-1500/optimizer.bin +3 -0
  7. checkpoint-1500/pytorch_model.bin +3 -0
  8. checkpoint-1500/random_states_0.pkl +3 -0
  9. checkpoint-1500/scheduler.bin +3 -0
  10. checkpoint-2000/optimizer.bin +3 -0
  11. checkpoint-2000/pytorch_model.bin +3 -0
  12. checkpoint-2000/random_states_0.pkl +3 -0
  13. checkpoint-2000/scheduler.bin +3 -0
  14. checkpoint-500/optimizer.bin +3 -0
  15. checkpoint-500/pytorch_model.bin +3 -0
  16. checkpoint-500/random_states_0.pkl +3 -0
  17. checkpoint-500/scheduler.bin +3 -0
  18. feature_extractor/preprocessor_config.json +28 -0
  19. learned_embeds-steps-1000.bin +3 -0
  20. learned_embeds-steps-1500.bin +3 -0
  21. learned_embeds-steps-2000.bin +3 -0
  22. learned_embeds-steps-500.bin +3 -0
  23. learned_embeds.bin +3 -0
  24. logs/textual_inversion/1691549012.4338174/events.out.tfevents.1691549012.ai-3060-2.56428.1 +3 -0
  25. logs/textual_inversion/1691549012.434793/hparams.yml +46 -0
  26. logs/textual_inversion/1691633406.08271/events.out.tfevents.1691633406.ai-3060-2.17226.1 +3 -0
  27. logs/textual_inversion/1691633406.0835783/hparams.yml +46 -0
  28. logs/textual_inversion/1691633504.8266742/events.out.tfevents.1691633504.ai-3060-2.17544.1 +3 -0
  29. logs/textual_inversion/1691633504.827518/hparams.yml +46 -0
  30. logs/textual_inversion/1691648687.813039/events.out.tfevents.1691648687.ai-3060-2.80723.1 +3 -0
  31. logs/textual_inversion/1691648687.8139715/hparams.yml +46 -0
  32. logs/textual_inversion/events.out.tfevents.1691549012.ai-3060-2.56428.0 +3 -0
  33. logs/textual_inversion/events.out.tfevents.1691633406.ai-3060-2.17226.0 +3 -0
  34. logs/textual_inversion/events.out.tfevents.1691633504.ai-3060-2.17544.0 +3 -0
  35. logs/textual_inversion/events.out.tfevents.1691648687.ai-3060-2.80723.0 +3 -0
  36. model_index.json +34 -0
  37. safety_checker/config.json +181 -0
  38. safety_checker/pytorch_model.bin +3 -0
  39. scheduler/scheduler_config.json +15 -0
  40. text_encoder/config.json +25 -0
  41. text_encoder/pytorch_model.bin +3 -0
  42. tokenizer/added_tokens.json +3 -0
  43. tokenizer/merges.txt +0 -0
  44. tokenizer/special_tokens_map.json +24 -0
  45. tokenizer/tokenizer_config.json +34 -0
  46. tokenizer/vocab.json +0 -0
  47. unet/config.json +65 -0
  48. unet/diffusion_pytorch_model.bin +3 -0
  49. vae/config.json +32 -0
  50. vae/diffusion_pytorch_model.bin +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 - Dytorch/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
+
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9baefe8c25d0a87b5f7d465ee4f6d1034ba929ed57e62bbd9ce19b3b480e5ab
3
+ size 303570477
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31245467bcd51dc758a9b32cb766d6f3a35f745b028727f95c5cd15d53b971df
3
+ size 492322337
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4be0c5427b1da06674d207b1a2015d90b604b2ae899dd020b96078807c902d5
3
+ size 14663
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb19b948b33a080098712534e53a991114e50367c7efbe3f9b4d0cec03eb540
3
+ size 563
checkpoint-1500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55856c7cb5479034d2e684456d2c5ff5b931432b34d070fe8549332425b34803
3
+ size 303570477
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee697e5efc014d88d686cf696a1bafc7cecd04dbc110252ac269714f656d9d48
3
+ size 492322337
checkpoint-1500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b3b7b946da748897dd26b962c50e5cfdc7f9de755dad5297fa53a8a2bdd244
3
+ size 14727
checkpoint-1500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7abf0b3af2013b920618166f35e17d899fce776df72f2c2a64c13989f4b8a6a8
3
+ size 563
checkpoint-2000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:921244b176e4efd8725b2e77d829b61fde16f8f847fea85a2c67b04103de5815
3
+ size 303570477
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dd3a6ce619ad61bb6c8b2bb648f9cccc899c4b3a6dff8d17426940c7bf7e96f
3
+ size 492322337
checkpoint-2000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd5f3713da86f1249d926156842284f7a30ff7ca47a53cdc7f66b36d2c01683
3
+ size 14663
checkpoint-2000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce55ada40659c32ea01f44d7732f0406a6c9004376f7e5579de396b3481cc2d
3
+ size 563
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5beda14d91685970dc689c31ac07d3cf9cca23233a45dce20def33c34e23e3
3
+ size 303570477
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f27dd63534147239172966c69cffad1ff8cec7aedf6ec3c89bfaf0fce5549903
3
+ size 492322337
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df2c5702b59d582502d22cc153fe93c82def445333abd866f9b194a13324bad2
3
+ size 14663
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478ff7b9adcb1fba8f74abd29e0dfb41133888ecf608d07ea8ae2143e019d098
3
+ size 563
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-steps-1000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839b7a3b250a500e5076f96c9601efd7bf2798cd88099721a18d79d20f5181fd
3
+ size 4001
learned_embeds-steps-1500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09aa3b1e9a93ce6e4192b9dcabbfedd442a2ebf4d19d2f484cc37baa64d90517
3
+ size 4001
learned_embeds-steps-2000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43d3fb8bb0b9291b9f1dbe1346d6cf939b14cfeb6dfaca8a7cc013773721d99
3
+ size 4001
learned_embeds-steps-500.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57d183d80172445d65231575dd8fbc43ddbea1d5ab06e4f2679f8ca9a028779
3
+ size 3998
learned_embeds.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb7d552fbdf944edc09f96ed524fea71449251a2c78b43badc5c4e2c5e14d48b
3
+ size 3840
logs/textual_inversion/1691549012.4338174/events.out.tfevents.1691549012.ai-3060-2.56428.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60846c2d840cfe3a6e75f0b7b9b0701973aa89385fbdf4b266447e812d6081d
3
+ size 2260
logs/textual_inversion/1691549012.434793/hparams.yml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ num_train_epochs: 20
26
+ num_validation_images: 4
27
+ num_vectors: 1
28
+ output_dir: textual_inversion_cat
29
+ placeholder_token: <cat-toy>
30
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
31
+ push_to_hub: true
32
+ repeats: 100
33
+ report_to: tensorboard
34
+ resolution: 512
35
+ resume_from_checkpoint: null
36
+ revision: null
37
+ save_as_full_pipeline: false
38
+ save_steps: 500
39
+ scale_lr: true
40
+ seed: null
41
+ tokenizer_name: null
42
+ train_batch_size: 1
43
+ train_data_dir: ./cat
44
+ validation_epochs: null
45
+ validation_prompt: null
46
+ validation_steps: 100
logs/textual_inversion/1691633406.08271/events.out.tfevents.1691633406.ai-3060-2.17226.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae7bc84b9fa8f28580fb0a9e94721a4e21711dacd46a9a16b0920ca0cd5977ba
3
+ size 2260
logs/textual_inversion/1691633406.0835783/hparams.yml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ num_train_epochs: 20
26
+ num_validation_images: 4
27
+ num_vectors: 1
28
+ output_dir: textual_inversion_cat
29
+ placeholder_token: <cat-toy>
30
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
31
+ push_to_hub: true
32
+ repeats: 100
33
+ report_to: tensorboard
34
+ resolution: 512
35
+ resume_from_checkpoint: null
36
+ revision: null
37
+ save_as_full_pipeline: false
38
+ save_steps: 500
39
+ scale_lr: true
40
+ seed: null
41
+ tokenizer_name: null
42
+ train_batch_size: 1
43
+ train_data_dir: ./cat
44
+ validation_epochs: null
45
+ validation_prompt: null
46
+ validation_steps: 100
logs/textual_inversion/1691633504.8266742/events.out.tfevents.1691633504.ai-3060-2.17544.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb195368f1d8a51d8c8de42fab368b231fad9555393ea3a563fe54f43483a03
3
+ size 2260
logs/textual_inversion/1691633504.827518/hparams.yml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ num_train_epochs: 2
26
+ num_validation_images: 4
27
+ num_vectors: 1
28
+ output_dir: textual_inversion_cat
29
+ placeholder_token: <cat-toy>
30
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
31
+ push_to_hub: true
32
+ repeats: 100
33
+ report_to: tensorboard
34
+ resolution: 512
35
+ resume_from_checkpoint: null
36
+ revision: null
37
+ save_as_full_pipeline: false
38
+ save_steps: 500
39
+ scale_lr: true
40
+ seed: null
41
+ tokenizer_name: null
42
+ train_batch_size: 1
43
+ train_data_dir: ./cat
44
+ validation_epochs: null
45
+ validation_prompt: null
46
+ validation_steps: 100
logs/textual_inversion/1691648687.813039/events.out.tfevents.1691648687.ai-3060-2.80723.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1779d5d854bf45d2578827b34ce8fe2057ae68ff8b58889f3ab717ab44c06d
3
+ size 2260
logs/textual_inversion/1691648687.8139715/hparams.yml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 2000
24
+ mixed_precision: 'no'
25
+ num_train_epochs: 14
26
+ num_validation_images: 4
27
+ num_vectors: 1
28
+ output_dir: textual_inversion_cat
29
+ placeholder_token: <cat-toy>
30
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
31
+ push_to_hub: true
32
+ repeats: 100
33
+ report_to: tensorboard
34
+ resolution: 512
35
+ resume_from_checkpoint: null
36
+ revision: null
37
+ save_as_full_pipeline: false
38
+ save_steps: 500
39
+ scale_lr: true
40
+ seed: null
41
+ tokenizer_name: null
42
+ train_batch_size: 1
43
+ train_data_dir: ./cat
44
+ validation_epochs: null
45
+ validation_prompt: null
46
+ validation_steps: 100
logs/textual_inversion/events.out.tfevents.1691549012.ai-3060-2.56428.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b513ab0e8f3082a6f80ca49b8ee6c7641e192922b7fa75de1ee73f01ce6888
3
+ size 37714
logs/textual_inversion/events.out.tfevents.1691633406.ai-3060-2.17226.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:494f65b7660b22d303453f1e1f36149392f58e066f236313fd35ba1ababf9ddc
3
+ size 1880
logs/textual_inversion/events.out.tfevents.1691633504.ai-3060-2.17544.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c7e73c290696d3f5a3bfa03f308325b443b7002be3d6e19dc944f9a5bb480a5
3
+ size 4504
logs/textual_inversion/events.out.tfevents.1691648687.ai-3060-2.80723.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a185423ae4d8e30809a7c93339637b88dd7cbdcc00533c9a4e7f3af22c188f
3
+ size 671054
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.20.0.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 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "c9ab35ff5f2c362e9e22fbafe278077e196057f0",
3
+ "_name_or_path": "/home/intern/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/c9ab35ff5f2c362e9e22fbafe278077e196057f0/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": "4.25.1",
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": "4.25.1",
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.20.0.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": "4.25.1",
24
+ "vocab_size": 49409
25
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7091680c97b285a50f5cf84c84fe7d72fc9df14c6466447613b761e548523d83
3
+ size 492312865
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<cat-toy>": 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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "runwayml/stable-diffusion-v1-5",
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.20.0.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
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "center_input_sample": false,
17
+ "class_embed_type": null,
18
+ "class_embeddings_concat": false,
19
+ "conv_in_kernel": 3,
20
+ "conv_out_kernel": 3,
21
+ "cross_attention_dim": 768,
22
+ "cross_attention_norm": null,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "encoder_hid_dim": null,
32
+ "encoder_hid_dim_type": null,
33
+ "flip_sin_to_cos": true,
34
+ "freq_shift": 0,
35
+ "in_channels": 4,
36
+ "layers_per_block": 2,
37
+ "mid_block_only_cross_attention": null,
38
+ "mid_block_scale_factor": 1,
39
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
40
+ "norm_eps": 1e-05,
41
+ "norm_num_groups": 32,
42
+ "num_attention_heads": null,
43
+ "num_class_embeds": null,
44
+ "only_cross_attention": false,
45
+ "out_channels": 4,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_out_scale_factor": 1.0,
48
+ "resnet_skip_time_act": false,
49
+ "resnet_time_scale_shift": "default",
50
+ "sample_size": 64,
51
+ "time_cond_proj_dim": null,
52
+ "time_embedding_act_fn": null,
53
+ "time_embedding_dim": null,
54
+ "time_embedding_type": "positional",
55
+ "timestep_post_act": null,
56
+ "transformer_layers_per_block": 1,
57
+ "up_block_types": [
58
+ "UpBlock2D",
59
+ "CrossAttnUpBlock2D",
60
+ "CrossAttnUpBlock2D",
61
+ "CrossAttnUpBlock2D"
62
+ ],
63
+ "upcast_attention": false,
64
+ "use_linear_projection": false
65
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39aeb5f57e936fdb52331f49d69299fb130a5456c269b67c08699b109e8485fd
3
+ size 3438375973
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.20.0.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.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a6fc35e77a2d5696ae6a494f797f01b7ab97b08b5f8f2f17e19d0ef169b1ca
3
+ size 334715569