briannlongzhao commited on
Commit
abe78d9
1 Parent(s): d48d2a0

End of training

Browse files
Files changed (49) 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/1706280421.578669/events.out.tfevents.1706280421.iLab1.2204967.1 +3 -0
  5. logs/textual_inversion/1706280421.5903156/hparams.yml +50 -0
  6. logs/textual_inversion/1706280825.454071/events.out.tfevents.1706280825.iLab1.2206154.1 +3 -0
  7. logs/textual_inversion/1706280825.4620266/hparams.yml +50 -0
  8. logs/textual_inversion/1706350703.133833/events.out.tfevents.1706350703.iLab1.2382622.1 +3 -0
  9. logs/textual_inversion/1706350703.1423192/hparams.yml +50 -0
  10. logs/textual_inversion/1706371045.0783992/events.out.tfevents.1706371045.iLab1.2434479.1 +3 -0
  11. logs/textual_inversion/1706371045.0874188/hparams.yml +50 -0
  12. logs/textual_inversion/1706371141.669214/events.out.tfevents.1706371141.iLab1.2434814.1 +3 -0
  13. logs/textual_inversion/1706371141.6791615/hparams.yml +50 -0
  14. logs/textual_inversion/1706371354.8574433/events.out.tfevents.1706371354.iLab1.2435567.1 +3 -0
  15. logs/textual_inversion/1706371354.8662636/hparams.yml +50 -0
  16. logs/textual_inversion/1706371561.3719206/events.out.tfevents.1706371561.iLab1.2436226.1 +3 -0
  17. logs/textual_inversion/1706371561.3834906/hparams.yml +50 -0
  18. logs/textual_inversion/1706371717.5312033/events.out.tfevents.1706371717.iLab1.2436700.1 +3 -0
  19. logs/textual_inversion/1706371717.5418997/hparams.yml +50 -0
  20. logs/textual_inversion/1706371855.6283345/events.out.tfevents.1706371855.iLab1.2437159.1 +3 -0
  21. logs/textual_inversion/1706371855.636531/hparams.yml +50 -0
  22. logs/textual_inversion/1706371949.914301/events.out.tfevents.1706371949.iLab1.2437530.1 +3 -0
  23. logs/textual_inversion/1706371949.922713/hparams.yml +50 -0
  24. logs/textual_inversion/1706372280.9472425/events.out.tfevents.1706372280.iLab1.2438547.1 +3 -0
  25. logs/textual_inversion/1706372280.955396/hparams.yml +50 -0
  26. logs/textual_inversion/events.out.tfevents.1706280421.iLab1.2204967.0 +3 -0
  27. logs/textual_inversion/events.out.tfevents.1706280825.iLab1.2206154.0 +3 -0
  28. logs/textual_inversion/events.out.tfevents.1706350703.iLab1.2382622.0 +3 -0
  29. logs/textual_inversion/events.out.tfevents.1706371045.iLab1.2434479.0 +3 -0
  30. logs/textual_inversion/events.out.tfevents.1706371141.iLab1.2434814.0 +3 -0
  31. logs/textual_inversion/events.out.tfevents.1706371354.iLab1.2435567.0 +3 -0
  32. logs/textual_inversion/events.out.tfevents.1706371561.iLab1.2436226.0 +3 -0
  33. logs/textual_inversion/events.out.tfevents.1706371717.iLab1.2436700.0 +3 -0
  34. logs/textual_inversion/events.out.tfevents.1706371855.iLab1.2437159.0 +3 -0
  35. logs/textual_inversion/events.out.tfevents.1706371949.iLab1.2437530.0 +3 -0
  36. logs/textual_inversion/events.out.tfevents.1706372280.iLab1.2438547.0 +3 -0
  37. model_index.json +38 -0
  38. scheduler/scheduler_config.json +20 -0
  39. text_encoder/config.json +25 -0
  40. text_encoder/model.safetensors +3 -0
  41. tokenizer/added_tokens.json +3 -0
  42. tokenizer/merges.txt +0 -0
  43. tokenizer/special_tokens_map.json +24 -0
  44. tokenizer/tokenizer_config.json +33 -0
  45. tokenizer/vocab.json +0 -0
  46. unet/config.json +73 -0
  47. unet/diffusion_pytorch_model.safetensors +3 -0
  48. vae/config.json +32 -0
  49. vae/diffusion_pytorch_model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: stabilityai/stable-diffusion-2-1
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 - briannlongzhao/0
15
+ These are textual inversion adaption weights for stabilityai/stable-diffusion-2-1. 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 sha256:59e35299370efccb3f7280ace07784d1de9822112778591c0e34d5beae9c406a
3
+ size 4216
logs/textual_inversion/1706280421.578669/events.out.tfevents.1706280421.iLab1.2204967.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:745a85edf2f6ea4b0a997f5bd7f62a3e3780147db4226ffae02bb7639482d08c
3
+ size 2514
logs/textual_inversion/1706280421.5903156/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 3000
26
+ mixed_precision: bf16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 22
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 100
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706280825.454071/events.out.tfevents.1706280825.iLab1.2206154.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9b8a1a6c07ff7c7667d98d2aece1ad433fd664d3b1d1003c6993a002086860
3
+ size 2514
logs/textual_inversion/1706280825.4620266/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 3000
26
+ mixed_precision: bf16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 24
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 100
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706350703.133833/events.out.tfevents.1706350703.iLab1.2382622.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b491e4c0ce0c5f988d6c46acdde6ce9708390ee339e7647b364870f37d13e9
3
+ size 2514
logs/textual_inversion/1706350703.1423192/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 3000
26
+ mixed_precision: bf16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 24
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 100
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706371045.0783992/events.out.tfevents.1706371045.iLab1.2434479.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a5e68db49653f6d4b3ac3fcd1a81cebafb203d1452df8e9647df682027f6e6
3
+ size 2514
logs/textual_inversion/1706371045.0874188/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 5000
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 40
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 100
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706371141.669214/events.out.tfevents.1706371141.iLab1.2434814.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9b4aa6f1f581febb38aeb81afb25ad88adeda4b647f84ba522201356ab693f
3
+ size 2514
logs/textual_inversion/1706371141.6791615/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 5000
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 40
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 100
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706371354.8574433/events.out.tfevents.1706371354.iLab1.2435567.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd557b45b3f9b4f2f23257828a47c474b9d958a052d1872d70925962908146eb
3
+ size 2514
logs/textual_inversion/1706371354.8662636/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 5000
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 40
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 100
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706371561.3719206/events.out.tfevents.1706371561.iLab1.2436226.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee803061af5876651aeaa6844c08840b9b5fc9695b287e31831e6aa9468db8b7
3
+ size 2514
logs/textual_inversion/1706371561.3834906/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 5000
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 40
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 100
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706371717.5312033/events.out.tfevents.1706371717.iLab1.2436700.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95310f2d9d843b2b9bd135575c2760104ba218dae12db0ef1ca0fd7bbc69e9eb
3
+ size 2514
logs/textual_inversion/1706371717.5418997/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 5000
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 2500
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 1
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706371855.6283345/events.out.tfevents.1706371855.iLab1.2437159.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3401fdf9f66cdeeac74d2c57643f9ef65fc4bac3eed23f2ba0f9a30d17a39bbe
3
+ size 2514
logs/textual_inversion/1706371855.636531/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 10
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 5
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 1
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706371949.914301/events.out.tfevents.1706371949.iLab1.2437530.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f76099bcddaf3422f9f89cda26a4e67b6a6bb2378bfee193272d9a26958589
3
+ size 2514
logs/textual_inversion/1706371949.922713/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 10
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 5
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: false
35
+ repeats: 1
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/1706372280.9472425/events.out.tfevents.1706372280.iLab1.2438547.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f95fb5aecd71685651e6b422a26b3bc453b5e7ff6072659cfb23f3d246aa661
3
+ size 2514
logs/textual_inversion/1706372280.955396/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_name: American robin
10
+ dataloader_num_workers: 0
11
+ enable_xformers_memory_efficient_attention: true
12
+ gradient_accumulation_steps: 4
13
+ gradient_checkpointing: false
14
+ hub_model_id: null
15
+ hub_token: null
16
+ idx: 0
17
+ initializer_token: American robin
18
+ learnable_property: object
19
+ learning_rate: 0.004
20
+ local_rank: 0
21
+ logging_dir: logs
22
+ lr_num_cycles: 1
23
+ lr_scheduler: constant
24
+ lr_warmup_steps: 0
25
+ max_train_steps: 10
26
+ mixed_precision: fp16
27
+ no_safe_serialization: false
28
+ num_train_epochs: 5
29
+ num_validation_images: 4
30
+ num_vectors: 1
31
+ output_dir: textual_inversion_models/0
32
+ placeholder_token: <American robin>
33
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
34
+ push_to_hub: true
35
+ repeats: 1
36
+ report_to: tensorboard
37
+ resolution: 512
38
+ resume_from_checkpoint: null
39
+ revision: null
40
+ save_as_full_pipeline: false
41
+ save_steps: 500
42
+ scale_lr: true
43
+ seed: null
44
+ tokenizer_name: null
45
+ train_batch_size: 1
46
+ train_data_dir: /lab/tmpig7b/u/brian-data/imagenet/images/train_small/n01558993
47
+ validation_epochs: null
48
+ validation_prompt: null
49
+ validation_steps: 100
50
+ wnid: n01558993
logs/textual_inversion/events.out.tfevents.1706280421.iLab1.2204967.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b67d4ba724e76074496fd1b42f54fd96d9545a3983168974be48e8e726eb127
3
+ size 88
logs/textual_inversion/events.out.tfevents.1706280825.iLab1.2206154.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc62365dfb792c3b56d22fbae0c8af10b5063547d1c053cce375683285ff5007
3
+ size 12048
logs/textual_inversion/events.out.tfevents.1706350703.iLab1.2382622.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa6c033836a370aa050a8b4cf3a933c9edc818588b1b08339e060eda28f432b
3
+ size 11556
logs/textual_inversion/events.out.tfevents.1706371045.iLab1.2434479.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28ee53edaa43ad8d6abbe9eeaae5959a881b518f3fa931c373947f87c8d3544
3
+ size 10162
logs/textual_inversion/events.out.tfevents.1706371141.iLab1.2434814.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93396b9922cf0d9321a69ff582a983b08722a5f985b9a0b4751787572d5a5efd
3
+ size 2536
logs/textual_inversion/events.out.tfevents.1706371354.iLab1.2435567.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06ec4d04aae49850325fb794c02c2816029c27fc953f228538ec6cf6a1b6bee
3
+ size 88
logs/textual_inversion/events.out.tfevents.1706371561.iLab1.2436226.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c452f77e9ae84f6ed39dfe9b17a797ec210de72290041ea337a6e69bfac6554
3
+ size 4586
logs/textual_inversion/events.out.tfevents.1706371717.iLab1.2436700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb03591e96023d386928d08a7c05167e947afbf2f46a565d7d46c18c27b5fbf
3
+ size 2946
logs/textual_inversion/events.out.tfevents.1706371855.iLab1.2437159.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b2b56f3109458ca4b86baa3b99525952d2d4b964c4b0f723a8f0c5b60e425e5
3
+ size 2126
logs/textual_inversion/events.out.tfevents.1706371949.iLab1.2437530.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28eea5dff7c2e72ef1d69fd08232e7f7968f6d4082f6b303c9a39a0e30800dcc
3
+ size 2126
logs/textual_inversion/events.out.tfevents.1706372280.iLab1.2438547.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f78378d79247efcff1edcf27a07b3deb691642f2b12edd3ccf9318e21a87dc6
3
+ size 2126
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.25.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ null,
11
+ null
12
+ ],
13
+ "requires_safety_checker": false,
14
+ "safety_checker": [
15
+ null,
16
+ null
17
+ ],
18
+ "scheduler": [
19
+ "diffusers",
20
+ "DDIMScheduler"
21
+ ],
22
+ "text_encoder": [
23
+ "transformers",
24
+ "CLIPTextModel"
25
+ ],
26
+ "tokenizer": [
27
+ "transformers",
28
+ "CLIPTokenizer"
29
+ ],
30
+ "unet": [
31
+ "diffusers",
32
+ "UNet2DConditionModel"
33
+ ],
34
+ "vae": [
35
+ "diffusers",
36
+ "AutoencoderKL"
37
+ ]
38
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.25.1",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "v_prediction",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
+ "set_alpha_to_one": false,
15
+ "skip_prk_steps": true,
16
+ "steps_offset": 1,
17
+ "thresholding": false,
18
+ "timestep_spacing": "leading",
19
+ "trained_betas": null
20
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": "float32",
23
+ "transformers_version": "4.28.1",
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 sha256:6fc0fe2724055322732c6e6f99bd8723df319d483c88a7e3c83d776e6aeadf4d
3
+ size 1361601112
tokenizer/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<American robin>": 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": "!",
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 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.25.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": [
10
+ 5,
11
+ 10,
12
+ 20,
13
+ 20
14
+ ],
15
+ "attention_type": "default",
16
+ "block_out_channels": [
17
+ 320,
18
+ 640,
19
+ 1280,
20
+ 1280
21
+ ],
22
+ "center_input_sample": false,
23
+ "class_embed_type": null,
24
+ "class_embeddings_concat": false,
25
+ "conv_in_kernel": 3,
26
+ "conv_out_kernel": 3,
27
+ "cross_attention_dim": 1024,
28
+ "cross_attention_norm": null,
29
+ "down_block_types": [
30
+ "CrossAttnDownBlock2D",
31
+ "CrossAttnDownBlock2D",
32
+ "CrossAttnDownBlock2D",
33
+ "DownBlock2D"
34
+ ],
35
+ "downsample_padding": 1,
36
+ "dropout": 0.0,
37
+ "dual_cross_attention": false,
38
+ "encoder_hid_dim": null,
39
+ "encoder_hid_dim_type": null,
40
+ "flip_sin_to_cos": true,
41
+ "freq_shift": 0,
42
+ "in_channels": 4,
43
+ "layers_per_block": 2,
44
+ "mid_block_only_cross_attention": null,
45
+ "mid_block_scale_factor": 1,
46
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
47
+ "norm_eps": 1e-05,
48
+ "norm_num_groups": 32,
49
+ "num_attention_heads": null,
50
+ "num_class_embeds": null,
51
+ "only_cross_attention": false,
52
+ "out_channels": 4,
53
+ "projection_class_embeddings_input_dim": null,
54
+ "resnet_out_scale_factor": 1.0,
55
+ "resnet_skip_time_act": false,
56
+ "resnet_time_scale_shift": "default",
57
+ "reverse_transformer_layers_per_block": null,
58
+ "sample_size": 96,
59
+ "time_cond_proj_dim": null,
60
+ "time_embedding_act_fn": null,
61
+ "time_embedding_dim": null,
62
+ "time_embedding_type": "positional",
63
+ "timestep_post_act": null,
64
+ "transformer_layers_per_block": 1,
65
+ "up_block_types": [
66
+ "UpBlock2D",
67
+ "CrossAttnUpBlock2D",
68
+ "CrossAttnUpBlock2D",
69
+ "CrossAttnUpBlock2D"
70
+ ],
71
+ "upcast_attention": true,
72
+ "use_linear_projection": true
73
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3a4d7978884c5e4ef00b62641b1b544b257be2f6715d984188610ad6475ad2
3
+ size 1731904736
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.25.1",
4
+ "_name_or_path": "stabilityai/stable-diffusion-2-1",
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": 768,
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 sha256:3e4c08995484ee61270175e9e7a072b66a6e4eeb5f0c266667fe1f45b90daf9a
3
+ size 167335342