Ubuntu commited on
Commit
8737c72
1 Parent(s): 861edb9

Initial version

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 +21 -0
  2. checkpoint-12000/optimizer.bin +3 -0
  3. checkpoint-12000/pytorch_model.bin +3 -0
  4. checkpoint-12000/random_states_0.pkl +3 -0
  5. checkpoint-12000/scaler.pt +3 -0
  6. checkpoint-12000/scheduler.bin +3 -0
  7. checkpoint-15000/optimizer.bin +3 -0
  8. checkpoint-15000/pytorch_model.bin +3 -0
  9. checkpoint-15000/random_states_0.pkl +3 -0
  10. checkpoint-15000/scaler.pt +3 -0
  11. checkpoint-15000/scheduler.bin +3 -0
  12. checkpoint-3000/optimizer.bin +3 -0
  13. checkpoint-3000/pytorch_model.bin +3 -0
  14. checkpoint-3000/random_states_0.pkl +3 -0
  15. checkpoint-3000/scaler.pt +3 -0
  16. checkpoint-3000/scheduler.bin +3 -0
  17. checkpoint-6000/optimizer.bin +3 -0
  18. checkpoint-6000/pytorch_model.bin +3 -0
  19. checkpoint-6000/random_states_0.pkl +3 -0
  20. checkpoint-6000/scaler.pt +3 -0
  21. checkpoint-6000/scheduler.bin +3 -0
  22. checkpoint-9000/optimizer.bin +3 -0
  23. checkpoint-9000/pytorch_model.bin +3 -0
  24. checkpoint-9000/random_states_0.pkl +3 -0
  25. checkpoint-9000/scaler.pt +3 -0
  26. checkpoint-9000/scheduler.bin +3 -0
  27. image_0.png +0 -0
  28. image_1.png +0 -0
  29. image_2.png +0 -0
  30. image_3.png +0 -0
  31. logs/text2image-fine-tune/1696595011.3248403/events.out.tfevents.1696595011.ip-172-31-74-58.30410.1 +3 -0
  32. logs/text2image-fine-tune/1696595011.326139/hparams.yml +49 -0
  33. logs/text2image-fine-tune/1696595363.4708042/events.out.tfevents.1696595363.ip-172-31-74-58.30523.1 +3 -0
  34. logs/text2image-fine-tune/1696595363.4720597/hparams.yml +49 -0
  35. logs/text2image-fine-tune/1696595453.8307884/events.out.tfevents.1696595453.ip-172-31-74-58.30621.1 +3 -0
  36. logs/text2image-fine-tune/1696595453.8320503/hparams.yml +49 -0
  37. logs/text2image-fine-tune/1696595841.9614737/events.out.tfevents.1696595841.ip-172-31-74-58.30727.1 +3 -0
  38. logs/text2image-fine-tune/1696595841.9627361/hparams.yml +51 -0
  39. logs/text2image-fine-tune/1696596216.8387234/events.out.tfevents.1696596216.ip-172-31-74-58.31023.1 +3 -0
  40. logs/text2image-fine-tune/1696596216.839982/hparams.yml +51 -0
  41. logs/text2image-fine-tune/1696596455.980185/events.out.tfevents.1696596455.ip-172-31-74-58.31417.1 +3 -0
  42. logs/text2image-fine-tune/1696596455.9814188/hparams.yml +51 -0
  43. logs/text2image-fine-tune/1696596713.968424/events.out.tfevents.1696596713.ip-172-31-74-58.31718.1 +3 -0
  44. logs/text2image-fine-tune/1696596713.9696558/hparams.yml +51 -0
  45. logs/text2image-fine-tune/1696597149.1165948/events.out.tfevents.1696597149.ip-172-31-74-58.31897.1 +3 -0
  46. logs/text2image-fine-tune/1696597149.117868/hparams.yml +51 -0
  47. logs/text2image-fine-tune/1696597363.589507/events.out.tfevents.1696597363.ip-172-31-74-58.31999.1 +3 -0
  48. logs/text2image-fine-tune/1696597363.590807/hparams.yml +51 -0
  49. logs/text2image-fine-tune/1696597573.0591679/events.out.tfevents.1696597573.ip-172-31-74-58.32098.1 +3 -0
  50. logs/text2image-fine-tune/1696597573.0604246/hparams.yml +51 -0
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - lora
11
+ inference: true
12
+ ---
13
+
14
+ # LoRA text2image fine-tuning - juliensimon/stable-diffusion-v1-5-pokemon-lora
15
+ These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the lambdalabs/pokemon-blip-captions dataset. You can find some example images in the following.
16
+
17
+ ![img_0](./image_0.png)
18
+ ![img_1](./image_1.png)
19
+ ![img_2](./image_2.png)
20
+ ![img_3](./image_3.png)
21
+
checkpoint-12000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:909e373388a79db58ca5c6412bd3a15f439035983bdfec30e7c2416ae976a811
3
+ size 6591685
checkpoint-12000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ec935976cc9bbe2295fdab763b2492dc32fa62f360b5f5d132536315ed8179
3
+ size 3285965
checkpoint-12000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8d370aff3279edbf54596c44f92ae762032e8df820f0ab54157e0c63285094
3
+ size 14727
checkpoint-12000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a61fa205a26ba2985bf4e0e515406104e0b0e5d6ebd86749ac9477a519632ca
3
+ size 557
checkpoint-12000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28d4d8b38f5624e590d136bcff096c9ffe80acb26ad1d633d8574f0067de8993
3
+ size 563
checkpoint-15000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010b2114a6bc912848797d17ab65c52e1d365920823d05d8ddfd174a91bb10c8
3
+ size 6591685
checkpoint-15000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fe8a58a60e965aacaa5777bde1685ec1eafbed60caac51612ec0f5f82e2c20c
3
+ size 3285965
checkpoint-15000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba343e899f7ec7cf8ddabbb0a35f66c9d3bccf82a21cb3c72540d8b1399edd3
3
+ size 14727
checkpoint-15000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fb33b1da2125feaa501f6acf7c67409ff703b0320e8e55bf616863891dd3346
3
+ size 557
checkpoint-15000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443fc08d26d2d0693cc6baad3c50f5f662e36a37e175b26d6a45a7f7b0a49e06
3
+ size 563
checkpoint-3000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ed77c198dac9ca29a2314d212b2664d50274e52a1d5988f78da9c2ea7deda9
3
+ size 6591685
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48896f7738bf19b70b3285d847b8b664727650775a37b1e9b88ab389294d2445
3
+ size 3285965
checkpoint-3000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f842d915b624719efd45edb422b5e2d65837901a1b9bc2ed8a8efff5f283e5e
3
+ size 14727
checkpoint-3000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1f9398b77268202e8e1465734a63d123b1ef11c27f20f2473677e9883a6869
3
+ size 557
checkpoint-3000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de4aa60280732f1a74ecc56607832e243aca3d16a6e8ba3b89382201e491ad2
3
+ size 563
checkpoint-6000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba99258d69d17365149d9cf75c1d1b117728297367d1cc075c1619cbc9b66921
3
+ size 6591685
checkpoint-6000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68559945e0cdb244f1aaf1455b3dda08b45176fec3845e39623bd6675f9dec8f
3
+ size 3285965
checkpoint-6000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccbed282d42902ea89f915bc118bc5c7fe8cf000d1c5162beb3cc55347692038
3
+ size 14727
checkpoint-6000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a00ef97fc41c0d653df466126d855f16646dd10726d3ac99a23f55ca70ec19a
3
+ size 557
checkpoint-6000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ddb9befe76772fdd295e69bf22435272e8d1ff1d165460cc0197a1c6ff7d85
3
+ size 563
checkpoint-9000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1103c8c070aaded3aaddfa31c4d277bfb96f59a86418b824eb9d488e06906822
3
+ size 6591685
checkpoint-9000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd117b39ee8f5bbfe88172e8736e2096a6e23f57dc22acec096e2bd4f34bb83
3
+ size 3285965
checkpoint-9000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2dc57dfead8506c1fc20c1fe577f472fba528867d0b380542bc4269c750fb89
3
+ size 14727
checkpoint-9000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be7a7b56cfc3e79d33648a4c49d4f11c6593d8d653b129207b2e38f2684a284
3
+ size 557
checkpoint-9000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:525f4feebe5bad6afaaa83b6aeee5fb0cf18c2b273ace3668248c0fe1cad6d6c
3
+ size 563
image_0.png ADDED
image_1.png ADDED
image_2.png ADDED
image_3.png ADDED
logs/text2image-fine-tune/1696595011.3248403/events.out.tfevents.1696595011.ip-172-31-74-58.30410.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e4b9e51d383c7baf8186be39564ac228b29cd67add4985d2c3293baf7d1391a
3
+ size 2229
logs/text2image-fine-tune/1696595011.326139/hparams.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 72
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ push_to_hub: false
36
+ random_flip: true
37
+ rank: 4
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 1337
44
+ snr_gamma: null
45
+ train_batch_size: 1
46
+ train_data_dir: null
47
+ use_8bit_adam: false
48
+ validation_epochs: 1
49
+ validation_prompt: Totoro
logs/text2image-fine-tune/1696595363.4708042/events.out.tfevents.1696595363.ip-172-31-74-58.30523.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a3d57131bc9d60f79f3bf810d9c4b7590262e40692edf676547df2302ce448
3
+ size 2229
logs/text2image-fine-tune/1696595363.4720597/hparams.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 72
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ push_to_hub: false
36
+ random_flip: true
37
+ rank: 4
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 1337
44
+ snr_gamma: null
45
+ train_batch_size: 1
46
+ train_data_dir: null
47
+ use_8bit_adam: false
48
+ validation_epochs: 1
49
+ validation_prompt: Totoro
logs/text2image-fine-tune/1696595453.8307884/events.out.tfevents.1696595453.ip-172-31-74-58.30621.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba20eff77904fb34ec89c7d7b4662d690584aca5738eaca6321bf9e746b2b65
3
+ size 2229
logs/text2image-fine-tune/1696595453.8320503/hparams.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 72
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ push_to_hub: false
36
+ random_flip: true
37
+ rank: 4
38
+ report_to: tensorboard
39
+ resolution: 512
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 1337
44
+ snr_gamma: null
45
+ train_batch_size: 1
46
+ train_data_dir: null
47
+ use_8bit_adam: false
48
+ validation_epochs: 1
49
+ validation_prompt: Totoro
logs/text2image-fine-tune/1696595841.9614737/events.out.tfevents.1696595841.ip-172-31-74-58.30727.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db1f186f793a93cb2344eb938dfce19d4cdb126cd5700eb4a4f05969913f3f9
3
+ size 2296
logs/text2image-fine-tune/1696595841.9627361/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 72
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
35
+ pretrained_vae_model_name_or_path: null
36
+ push_to_hub: false
37
+ random_flip: true
38
+ rank: 4
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: 1337
45
+ snr_gamma: null
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ train_text_encoder: false
49
+ use_8bit_adam: false
50
+ validation_epochs: 1
51
+ validation_prompt: Totoro
logs/text2image-fine-tune/1696596216.8387234/events.out.tfevents.1696596216.ip-172-31-74-58.31023.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd82289626dfd9f95b842617d2cecfa7b1e19064257795a5ad021be6ff90fb1
3
+ size 2296
logs/text2image-fine-tune/1696596216.839982/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 72
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
35
+ pretrained_vae_model_name_or_path: null
36
+ push_to_hub: false
37
+ random_flip: true
38
+ rank: 4
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: 1337
45
+ snr_gamma: null
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ train_text_encoder: false
49
+ use_8bit_adam: false
50
+ validation_epochs: 1
51
+ validation_prompt: Totoro
logs/text2image-fine-tune/1696596455.980185/events.out.tfevents.1696596455.ip-172-31-74-58.31417.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a0bd9019cbe3ea96604a56322b1974252baa9d21d77e1314a71ba852975640
3
+ size 2296
logs/text2image-fine-tune/1696596455.9814188/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 72
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
35
+ pretrained_vae_model_name_or_path: null
36
+ push_to_hub: false
37
+ random_flip: true
38
+ rank: 4
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: 1337
45
+ snr_gamma: null
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ train_text_encoder: false
49
+ use_8bit_adam: false
50
+ validation_epochs: 1
51
+ validation_prompt: Totoro
logs/text2image-fine-tune/1696596713.968424/events.out.tfevents.1696596713.ip-172-31-74-58.31718.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c7fdcd05df29237e76c751caef8672b3f554801e0d86519bef8d093e10f80f9
3
+ size 2296
logs/text2image-fine-tune/1696596713.9696558/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 72
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
35
+ pretrained_vae_model_name_or_path: null
36
+ push_to_hub: false
37
+ random_flip: true
38
+ rank: 4
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: 1337
45
+ snr_gamma: null
46
+ train_batch_size: 1
47
+ train_data_dir: null
48
+ train_text_encoder: false
49
+ use_8bit_adam: false
50
+ validation_epochs: 1
51
+ validation_prompt: Totoro
logs/text2image-fine-tune/1696597149.1165948/events.out.tfevents.1696597149.ip-172-31-74-58.31897.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf5e07d85e7b33eb4807577b0b3c86768e0ea8ed4bd10d15d882ddf061a83e1f
3
+ size 2296
logs/text2image-fine-tune/1696597149.117868/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 143
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
35
+ pretrained_vae_model_name_or_path: null
36
+ push_to_hub: false
37
+ random_flip: true
38
+ rank: 4
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: 1337
45
+ snr_gamma: null
46
+ train_batch_size: 2
47
+ train_data_dir: null
48
+ train_text_encoder: false
49
+ use_8bit_adam: false
50
+ validation_epochs: 1
51
+ validation_prompt: Totoro
logs/text2image-fine-tune/1696597363.589507/events.out.tfevents.1696597363.ip-172-31-74-58.31999.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee1e25f11a4103248e2d9a5cee9bdb9119cf9aa22f7c0b1e2a04dde524e3d0b4
3
+ size 2296
logs/text2image-fine-tune/1696597363.590807/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 143
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
35
+ pretrained_vae_model_name_or_path: null
36
+ push_to_hub: false
37
+ random_flip: true
38
+ rank: 4
39
+ report_to: tensorboard
40
+ resolution: 512
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: 1337
45
+ snr_gamma: null
46
+ train_batch_size: 2
47
+ train_data_dir: null
48
+ train_text_encoder: false
49
+ use_8bit_adam: false
50
+ validation_epochs: 1
51
+ validation_prompt: Totoro
logs/text2image-fine-tune/1696597573.0591679/events.out.tfevents.1696597573.ip-172-31-74-58.32098.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb3654bd30d44e1893110c106edcf6c823252bbbc7239f5f9ce25f00d1b69c8
3
+ size 2296
logs/text2image-fine-tune/1696597573.0604246/hparams.yml ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ cache_dir: null
7
+ caption_column: text
8
+ center_crop: true
9
+ checkpointing_steps: 500
10
+ checkpoints_total_limit: null
11
+ dataloader_num_workers: 8
12
+ dataset_config_name: null
13
+ dataset_name: lambdalabs/pokemon-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: null
18
+ hub_token: null
19
+ image_column: image
20
+ learning_rate: 0.0001
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_scheduler: cosine
24
+ lr_warmup_steps: 0
25
+ max_grad_norm: 1.0
26
+ max_train_samples: null
27
+ max_train_steps: 15000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 143
31
+ num_validation_images: 4
32
+ output_dir: ~/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
35
+ pretrained_vae_model_name_or_path: null
36
+ push_to_hub: false
37
+ random_flip: true
38
+ rank: 4
39
+ report_to: tensorboard
40
+ resolution: 1024
41
+ resume_from_checkpoint: null
42
+ revision: null
43
+ scale_lr: false
44
+ seed: 1337
45
+ snr_gamma: null
46
+ train_batch_size: 2
47
+ train_data_dir: null
48
+ train_text_encoder: false
49
+ use_8bit_adam: false
50
+ validation_epochs: 1
51
+ validation_prompt: Totoro