txz32102 commited on
Commit
dcc49f5
·
verified ·
1 Parent(s): 2385873

End of training

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +39 -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-2500/optimizer.bin +3 -0
  15. checkpoint-2500/pytorch_model.bin +3 -0
  16. checkpoint-2500/random_states_0.pkl +3 -0
  17. checkpoint-2500/scheduler.bin +3 -0
  18. checkpoint-3000/optimizer.bin +3 -0
  19. checkpoint-3000/pytorch_model.bin +3 -0
  20. checkpoint-3000/random_states_0.pkl +3 -0
  21. checkpoint-3000/scheduler.bin +3 -0
  22. checkpoint-500/optimizer.bin +3 -0
  23. checkpoint-500/pytorch_model.bin +3 -0
  24. checkpoint-500/random_states_0.pkl +3 -0
  25. checkpoint-500/scheduler.bin +3 -0
  26. feature_extractor/preprocessor_config.json +28 -0
  27. learned_embeds-steps-1000.safetensors +3 -0
  28. learned_embeds-steps-1500.safetensors +3 -0
  29. learned_embeds-steps-2000.safetensors +3 -0
  30. learned_embeds-steps-2500.safetensors +3 -0
  31. learned_embeds-steps-3000.safetensors +3 -0
  32. learned_embeds-steps-500.safetensors +3 -0
  33. learned_embeds.safetensors +3 -0
  34. logs/textual_inversion/1734171421.9251878/events.out.tfevents.1734171421.apm.1354771.1 +3 -0
  35. logs/textual_inversion/1734171421.9286308/hparams.yml +48 -0
  36. logs/textual_inversion/1734171484.1768532/events.out.tfevents.1734171484.apm.1355927.1 +3 -0
  37. logs/textual_inversion/1734171484.180341/hparams.yml +48 -0
  38. logs/textual_inversion/1734173355.8942099/events.out.tfevents.1734173355.apm.17192.1 +3 -0
  39. logs/textual_inversion/1734173355.898767/hparams.yml +48 -0
  40. logs/textual_inversion/1734173617.91118/events.out.tfevents.1734173617.apm.21528.1 +3 -0
  41. logs/textual_inversion/1734173617.9150586/hparams.yml +48 -0
  42. logs/textual_inversion/events.out.tfevents.1734171421.apm.1354771.0 +3 -0
  43. logs/textual_inversion/events.out.tfevents.1734171484.apm.1355927.0 +3 -0
  44. logs/textual_inversion/events.out.tfevents.1734173355.apm.17192.0 +3 -0
  45. logs/textual_inversion/events.out.tfevents.1734173617.apm.21528.0 +3 -0
  46. model_index.json +38 -0
  47. safety_checker/config.json +168 -0
  48. safety_checker/model.safetensors +3 -0
  49. scheduler/scheduler_config.json +15 -0
  50. text_encoder/config.json +25 -0
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ inference: true
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - textual_inversion
12
+ - diffusers-training
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+
19
+ # Textual inversion text2image fine-tuning - txz32102/textual_inversion_cat
20
+ These are textual inversion adaption weights for CompVis/stable-diffusion-v1-4. You can find some example images in the following.
21
+
22
+
23
+
24
+
25
+ ## Intended uses & limitations
26
+
27
+ #### How to use
28
+
29
+ ```python
30
+ # TODO: add an example code snippet for running this diffusion pipeline
31
+ ```
32
+
33
+ #### Limitations and bias
34
+
35
+ [TODO: provide examples of latent issues and potential remediations]
36
+
37
+ ## Training details
38
+
39
+ [TODO: describe the data used to train the model]
checkpoint-1000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb3fbbeb0e76ca71ef67f93c41cdf19aef2f9517a78f92dc674a0eefd8b51aa0
3
+ size 303570914
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2979b5dac25f413f516939d589a8484f155083b7561e52cd15d5a8156024f8ca
3
+ size 492322782
checkpoint-1000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe06acbbd133542356cc1ec202196c910f1f4240ad6e54cb8c7c3fb13bf22fb6
3
+ size 14604
checkpoint-1000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76821af0fdb32e3f19270e410db4daed3d905717577593ac24dd05143d81886e
3
+ size 1000
checkpoint-1500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f80e1873b0ce4e2f739d4af84de4f4149786a03651c90a850a7ad09aa61790
3
+ size 303570914
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e19b974757ba8170c5e61f49973abfa0cff9391ec1d4be089a7345bb8250b866
3
+ size 492322782
checkpoint-1500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571b8bdf6589d3e1cbdfe91902c8d9810574a08676b27e8b1de765e9a3a40c22
3
+ size 14604
checkpoint-1500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f516ad5468f03f56a944ca66b4817da8b9af1a6647f8cd7f666ce71d3c0833e7
3
+ size 1000
checkpoint-2000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2081de21c71237b3866c0bd11133575cda87f0210a51233f7a7c5c82d009683
3
+ size 303570914
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5eb97a76bbab6f4f2afd5b2a66c6b2228fa7a5c434aa2a8e0c8dc1453a96da9
3
+ size 492322782
checkpoint-2000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b56bc212a2f3e7a5e3c1a701fe4abfc84a22d4a40b5e6521429b0bf35876773c
3
+ size 14604
checkpoint-2000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9be685bdb49b9911fb7d9a6ca4439f26664c681cbd5c6694ce908b13a0cdec6
3
+ size 1000
checkpoint-2500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de37156b73d629a6bf9b819ac6775fc197f071c3d5d2edfed4d11a25f7333657
3
+ size 303570914
checkpoint-2500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1c85abb61970f6b842959cc0589223223e8607eb13ff577f30db37f3e28ad6
3
+ size 492322782
checkpoint-2500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:237692c88dc6caa679af42d48054bc1a664edb405034aabb05eca47407ba233a
3
+ size 14604
checkpoint-2500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d321a1d322ef3a821a63f56a065d329af9002de50a612e3e0e60e86576cf959f
3
+ size 1000
checkpoint-3000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d866bde034c68f163a97ecb71b8db1effe6cb6977593a66e4cd9c8dcc5efba83
3
+ size 303570914
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98e3421164f3178e70af9c2c9b5158dffb2d09a43d302ae526d85c003ec0679d
3
+ size 492322782
checkpoint-3000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceea11f0ed7a5dddf55582961824269aa08d9b5126fd4f10405a688a5d918324
3
+ size 14540
checkpoint-3000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc5e80e3268786117ee3c9fecc1e370866e374ab1f75bbf3aa94171a7e46775d
3
+ size 1000
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ede10717e83722b771987f7c429765808ae6b27ded8c453baccdde754d6c209
3
+ size 303570914
checkpoint-500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c24040ba0954f71fd2dfd9b7513aea2fe2add5c1f56d9a9630abdb0c61e7bd
3
+ size 492322782
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47fd4145ab62e5a04e4939ef83b5e44d9f32953fd92e14e4514f822883f80937
3
+ size 14604
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7115382e2fcdb8f40cd76a0514e9c1ce9a9384121abbed239ca23efe95e4919
3
+ size 1000
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.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:493e4b04192630beee100a5d2e9305310a7989f960ba4c7aae4faf6bec762c56
3
+ size 3184
learned_embeds-steps-1500.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce0811ef53c46b87b9c567d03159f3da0a021a1b84bcf07b398f2830b00befb
3
+ size 3184
learned_embeds-steps-2000.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89c29a6819c4dbc38609948411359daf0b3ed6ff0063ad1d720a10fe125bee9
3
+ size 3184
learned_embeds-steps-2500.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5564466af3d0d600ddfe804e5519ce22b6c5b35f1c43a2b18530aeef96835d5
3
+ size 3184
learned_embeds-steps-3000.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:331ba6c5c3ed8a25d2a36b44bea39c3e74b2c074cdd33c7a6191eca65a8ed98b
3
+ size 3184
learned_embeds-steps-500.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68ba79743fdeb65e106e035bfd86c9b05b77c3e2dd16c42a9478f11bd3df20f8
3
+ size 3184
learned_embeds.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:331ba6c5c3ed8a25d2a36b44bea39c3e74b2c074cdd33c7a6191eca65a8ed98b
3
+ size 3184
logs/textual_inversion/1734171421.9251878/events.out.tfevents.1734171421.apm.1354771.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfad83b99d5bcbc51b669a6fc5fe12dc7ff78bafdfe3e0d50e0e775a7de4c124
3
+ size 2382
logs/textual_inversion/1734171421.9286308/hparams.yml ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.008
18
+ local_rank: 0
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: 79
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: CompVis/stable-diffusion-v1-4
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/data1/musong/workspace/2024/12/12-14/textual_inversion/data
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
48
+ variant: null
logs/textual_inversion/1734171484.1768532/events.out.tfevents.1734171484.apm.1355927.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb8a54070c2392a98af5030767b21ad768dfcf76b84816fb0a201d212ddb1b18
3
+ size 2382
logs/textual_inversion/1734171484.180341/hparams.yml ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.008
18
+ local_rank: 0
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: 79
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: CompVis/stable-diffusion-v1-4
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/data1/musong/workspace/2024/12/12-14/textual_inversion/data
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
48
+ variant: null
logs/textual_inversion/1734173355.8942099/events.out.tfevents.1734173355.apm.17192.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9856ffa4aae13ea210bd933aed2fa9817ea9a93f88e0fefbdbc3190e12993d2d
3
+ size 2382
logs/textual_inversion/1734173355.898767/hparams.yml ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.004
18
+ local_rank: 0
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: 40
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: CompVis/stable-diffusion-v1-4
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/data1/musong/workspace/2024/12/12-14/textual_inversion/data
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
48
+ variant: null
logs/textual_inversion/1734173617.91118/events.out.tfevents.1734173617.apm.21528.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f97fb7ce8878327c864f54c4a934134390a0b1d86b9f6ce82f86afed9988f23c
3
+ size 2382
logs/textual_inversion/1734173617.9150586/hparams.yml ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 0.004
18
+ local_rank: 0
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: 40
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: CompVis/stable-diffusion-v1-4
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/data1/musong/workspace/2024/12/12-14/textual_inversion/data
45
+ validation_epochs: null
46
+ validation_prompt: null
47
+ validation_steps: 100
48
+ variant: null
logs/textual_inversion/events.out.tfevents.1734171421.apm.1354771.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce723caacc67a0b25da59aa374e363f84914bc1b9ce3cf8ab5a636177b22e56
3
+ size 5406
logs/textual_inversion/events.out.tfevents.1734171484.apm.1355927.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fd0777867aa99651608de57d0b9385f18badbd797d1c34c521d359fcf8b0c6
3
+ size 33122
logs/textual_inversion/events.out.tfevents.1734173355.apm.17192.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82542c8f33eed141222df4f938553203adcf9e7a5e55789b162efa95b16148f9
3
+ size 18608
logs/textual_inversion/events.out.tfevents.1734173617.apm.21528.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509cd03a33d2ac2fde26d7b50f3ea97d0bf926270307eec5ab023dd72614eb87
3
+ size 1007054
model_index.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.32.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ null,
11
+ null
12
+ ],
13
+ "requires_safety_checker": true,
14
+ "safety_checker": [
15
+ "stable_diffusion",
16
+ "StableDiffusionSafetyChecker"
17
+ ],
18
+ "scheduler": [
19
+ "diffusers",
20
+ "PNDMScheduler"
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
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "133a221b8aa7292a167afc5127cb63fb5005638b",
3
+ "_name_or_path": "/home/data1/musong/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/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": "4.30.2",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "torch_dtype": "float32",
89
+ "transformers_version": null,
90
+ "vision_config": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_dropout": 0.0,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "exponential_decay_length_penalty": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "hidden_act": "quick_gelu",
112
+ "hidden_size": 1024,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "image_size": 224,
118
+ "initializer_factor": 1.0,
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 4096,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-05,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "min_length": 0,
131
+ "model_type": "clip_vision_model",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 16,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_channels": 3,
137
+ "num_hidden_layers": 24,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": null,
143
+ "patch_size": 14,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "projection_dim": 512,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "transformers_version": "4.30.2",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ }
168
+ }
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11cfe53105625af8c00faac32a430626641cce686454f3c39d837f14397d858b
3
+ size 1215981832
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.32.0.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": "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
+ "projection_dim": 512,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.2",
24
+ "vocab_size": 49409
25
+ }