Hugging Face's logo

gdivya-nvidia
/
lora_xl

Text-to-Image
Diffusers
TensorBoard
diffusers-training
lora
template:sd-lora
stable-diffusion-xl
stable-diffusion-xl-diffusers
Model card Files Metrics Community
gdivya-nvidia commited on
Commit
cdcabe2
·
verified ·
1 Parent(s): 835b130

End of training

Browse files
Files changed (31) hide show
  1. README.md +74 -0
  2. checkpoint-500/optimizer.bin +3 -0
  3. checkpoint-500/pytorch_lora_weights.safetensors +3 -0
  4. checkpoint-500/random_states_0.pkl +3 -0
  5. checkpoint-500/scheduler.bin +3 -0
  6. image_0.png +0 -0
  7. image_1.png +0 -0
  8. image_2.png +0 -0
  9. image_3.png +0 -0
  10. logs/dreambooth-lora-sd-xl/1728386777.8578603/events.out.tfevents.1728386777.vipatidar-Z590-UD.1105015.1 +3 -0
  11. logs/dreambooth-lora-sd-xl/1728386777.85951/hparams.yml +70 -0
  12. logs/dreambooth-lora-sd-xl/1728402516.2372222/events.out.tfevents.1728402516.vipatidar-Z590-UD.1338594.1 +3 -0
  13. logs/dreambooth-lora-sd-xl/1728402516.2380412/hparams.yml +70 -0
  14. logs/dreambooth-lora-sd-xl/1728444503.029234/events.out.tfevents.1728444503.vipatidar-Z590-UD.1848383.1 +3 -0
  15. logs/dreambooth-lora-sd-xl/1728444503.0300443/hparams.yml +70 -0
  16. logs/dreambooth-lora-sd-xl/1728445396.5506396/events.out.tfevents.1728445396.vipatidar-Z590-UD.1862543.1 +3 -0
  17. logs/dreambooth-lora-sd-xl/1728445396.5515773/hparams.yml +70 -0
  18. logs/dreambooth-lora-sd-xl/1728445547.0736525/events.out.tfevents.1728445547.vipatidar-Z590-UD.1864535.1 +3 -0
  19. logs/dreambooth-lora-sd-xl/1728445547.074412/hparams.yml +70 -0
  20. logs/dreambooth-lora-sd-xl/1728445591.4734476/events.out.tfevents.1728445591.vipatidar-Z590-UD.1865176.1 +3 -0
  21. logs/dreambooth-lora-sd-xl/1728445591.4742537/hparams.yml +70 -0
  22. logs/dreambooth-lora-sd-xl/1728445784.2501283/events.out.tfevents.1728445784.vipatidar-Z590-UD.1868241.1 +3 -0
  23. logs/dreambooth-lora-sd-xl/1728445784.250954/hparams.yml +70 -0
  24. logs/dreambooth-lora-sd-xl/events.out.tfevents.1728386777.vipatidar-Z590-UD.1105015.0 +3 -0
  25. logs/dreambooth-lora-sd-xl/events.out.tfevents.1728402516.vipatidar-Z590-UD.1338594.0 +3 -0
  26. logs/dreambooth-lora-sd-xl/events.out.tfevents.1728444503.vipatidar-Z590-UD.1848383.0 +3 -0
  27. logs/dreambooth-lora-sd-xl/events.out.tfevents.1728445396.vipatidar-Z590-UD.1862543.0 +3 -0
  28. logs/dreambooth-lora-sd-xl/events.out.tfevents.1728445547.vipatidar-Z590-UD.1864535.0 +3 -0
  29. logs/dreambooth-lora-sd-xl/events.out.tfevents.1728445591.vipatidar-Z590-UD.1865176.0 +3 -0
  30. logs/dreambooth-lora-sd-xl/events.out.tfevents.1728445784.vipatidar-Z590-UD.1868241.0 +3 -0
  31. pytorch_lora_weights.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
3
+ library_name: diffusers
4
+ license: openrail++
5
+ tags:
6
+ - text-to-image
7
+ - text-to-image
8
+ - diffusers-training
9
+ - diffusers
10
+ - lora
11
+ - template:sd-lora
12
+ - stable-diffusion-xl
13
+ - stable-diffusion-xl-diffusers
14
+ instance_prompt: infrared sensor image of woman face
15
+ widget:
16
+ - text: infrared sensor image of woman face with makeup
17
+ output:
18
+ url: image_0.png
19
+ - text: infrared sensor image of woman face with makeup
20
+ output:
21
+ url: image_1.png
22
+ - text: infrared sensor image of woman face with makeup
23
+ output:
24
+ url: image_2.png
25
+ - text: infrared sensor image of woman face with makeup
26
+ output:
27
+ url: image_3.png
28
+ ---
29
+
30
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
31
+ should probably proofread and complete it, then remove this comment. -->
32
+
33
+
34
+ # SDXL LoRA DreamBooth - gdivya-nvidia/lora_xl
35
+
36
+ <Gallery />
37
+
38
+ ## Model description
39
+
40
+ These are gdivya-nvidia/lora_xl LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
41
+
42
+ The weights were trained using [DreamBooth](https://dreambooth.github.io/).
43
+
44
+ LoRA for the text encoder was enabled: False.
45
+
46
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
47
+
48
+ ## Trigger words
49
+
50
+ You should use infrared sensor image of woman face to trigger the image generation.
51
+
52
+ ## Download model
53
+
54
+ Weights for this model are available in Safetensors format.
55
+
56
+ [Download](gdivya-nvidia/lora_xl/tree/main) them in the Files & versions tab.
57
+
58
+
59
+
60
+ ## Intended uses & limitations
61
+
62
+ #### How to use
63
+
64
+ ```python
65
+ # TODO: add an example code snippet for running this diffusion pipeline
66
+ ```
67
+
68
+ #### Limitations and bias
69
+
70
+ [TODO: provide examples of latent issues and potential remediations]
71
+
72
+ ## Training details
73
+
74
+ [TODO: describe the data used to train the model]
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea423194de6821177c2b4d579f2bdcd7db000d1c7e1052bfa9d4c98774919506
3
+ size 24168626
checkpoint-500/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6dd2132d84745b0881efa29ccf1749fbacf4281b97e65242c6b085e2193002a
3
+ size 11778368
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:588104ce2d22c3c30a9b499310d84bef7c4bdf92519382961784610e453520e6
3
+ size 14344
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf34ac8dd2addc454aeb1ee4eaba3267c2841857e117be40ac2ed02cf581c9c
3
+ size 1000
image_0.png ADDED
image_1.png ADDED
image_2.png ADDED
image_3.png ADDED
logs/dreambooth-lora-sd-xl/1728386777.8578603/events.out.tfevents.1728386777.vipatidar-Z590-UD.1105015.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d85d3beb7b1f3d604085acb73435866f93cd6724e0a73cf797cb7d9fc369d93
3
+ size 3389
logs/dreambooth-lora-sd-xl/1728386777.85951/hparams.yml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: null
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 4
20
+ gradient_checkpointing: false
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: /home/gdivya/generate_faces/cropped_faces
25
+ instance_prompt: infrared sensor image of woman face
26
+ learning_rate: 0.0001
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 500
35
+ mixed_precision: fp16
36
+ num_class_images: 100
37
+ num_train_epochs: 2
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: /home/gdivya/generate_faces/lora_xl
41
+ output_kohya_format: false
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
43
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
44
+ prior_generation_precision: null
45
+ prior_loss_weight: 1.0
46
+ prodigy_beta3: null
47
+ prodigy_decouple: true
48
+ prodigy_safeguard_warmup: true
49
+ prodigy_use_bias_correction: true
50
+ push_to_hub: true
51
+ random_flip: false
52
+ rank: 4
53
+ repeats: 1
54
+ report_to: tensorboard
55
+ resolution: 1024
56
+ resume_from_checkpoint: null
57
+ revision: null
58
+ sample_batch_size: 4
59
+ scale_lr: false
60
+ seed: 0
61
+ snr_gamma: null
62
+ text_encoder_lr: 5.0e-06
63
+ train_batch_size: 1
64
+ train_text_encoder: false
65
+ use_8bit_adam: false
66
+ use_dora: false
67
+ validation_epochs: 25
68
+ validation_prompt: infrared sensor image of woman face with makeup
69
+ variant: null
70
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1728402516.2372222/events.out.tfevents.1728402516.vipatidar-Z590-UD.1338594.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65133710638a162c3bcb8c3ce8f49131dfb067447cf5ac27088d1051137808c6
3
+ size 3389
logs/dreambooth-lora-sd-xl/1728402516.2380412/hparams.yml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: null
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 4
20
+ gradient_checkpointing: false
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: /home/gdivya/generate_faces/cropped_faces
25
+ instance_prompt: infrared sensor image of woman face
26
+ learning_rate: 0.0001
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 500
35
+ mixed_precision: fp16
36
+ num_class_images: 100
37
+ num_train_epochs: 2
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: /home/gdivya/generate_faces/lora_xl
41
+ output_kohya_format: false
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
43
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
44
+ prior_generation_precision: null
45
+ prior_loss_weight: 1.0
46
+ prodigy_beta3: null
47
+ prodigy_decouple: true
48
+ prodigy_safeguard_warmup: true
49
+ prodigy_use_bias_correction: true
50
+ push_to_hub: true
51
+ random_flip: false
52
+ rank: 4
53
+ repeats: 1
54
+ report_to: tensorboard
55
+ resolution: 1024
56
+ resume_from_checkpoint: null
57
+ revision: null
58
+ sample_batch_size: 4
59
+ scale_lr: false
60
+ seed: 0
61
+ snr_gamma: null
62
+ text_encoder_lr: 5.0e-06
63
+ train_batch_size: 1
64
+ train_text_encoder: false
65
+ use_8bit_adam: false
66
+ use_dora: false
67
+ validation_epochs: 25
68
+ validation_prompt: infrared sensor image of woman face with makeup
69
+ variant: null
70
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1728444503.029234/events.out.tfevents.1728444503.vipatidar-Z590-UD.1848383.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48e1d35e64c842938e63db66ac0e2e9969ec155043a350fd20cd23aa83c44651
3
+ size 3389
logs/dreambooth-lora-sd-xl/1728444503.0300443/hparams.yml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: null
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 4
20
+ gradient_checkpointing: false
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: /home/gdivya/generate_faces/cropped_faces
25
+ instance_prompt: infrared sensor image of woman face
26
+ learning_rate: 0.0001
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 500
35
+ mixed_precision: fp16
36
+ num_class_images: 100
37
+ num_train_epochs: 2
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: /home/gdivya/generate_faces/lora_xl
41
+ output_kohya_format: false
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
43
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
44
+ prior_generation_precision: null
45
+ prior_loss_weight: 1.0
46
+ prodigy_beta3: null
47
+ prodigy_decouple: true
48
+ prodigy_safeguard_warmup: true
49
+ prodigy_use_bias_correction: true
50
+ push_to_hub: true
51
+ random_flip: false
52
+ rank: 4
53
+ repeats: 1
54
+ report_to: tensorboard
55
+ resolution: 1024
56
+ resume_from_checkpoint: null
57
+ revision: null
58
+ sample_batch_size: 4
59
+ scale_lr: false
60
+ seed: 0
61
+ snr_gamma: null
62
+ text_encoder_lr: 5.0e-06
63
+ train_batch_size: 1
64
+ train_text_encoder: false
65
+ use_8bit_adam: false
66
+ use_dora: false
67
+ validation_epochs: 25
68
+ validation_prompt: infrared sensor image of woman face with makeup
69
+ variant: null
70
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1728445396.5506396/events.out.tfevents.1728445396.vipatidar-Z590-UD.1862543.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e909caf24aa06bf89226b18f1743c04c532b638b7d89a9a337c7f05e59409917
3
+ size 3341
logs/dreambooth-lora-sd-xl/1728445396.5515773/hparams.yml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: null
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 4
20
+ gradient_checkpointing: false
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: /home/gdivya/generate_faces/cropped_faces
25
+ instance_prompt: infrared sensor image of woman face
26
+ learning_rate: 0.0001
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 500
35
+ mixed_precision: null
36
+ num_class_images: 100
37
+ num_train_epochs: 2
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: /home/gdivya/generate_faces/lora_xl
41
+ output_kohya_format: false
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
43
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
44
+ prior_generation_precision: null
45
+ prior_loss_weight: 1.0
46
+ prodigy_beta3: null
47
+ prodigy_decouple: true
48
+ prodigy_safeguard_warmup: true
49
+ prodigy_use_bias_correction: true
50
+ push_to_hub: true
51
+ random_flip: false
52
+ rank: 4
53
+ repeats: 1
54
+ report_to: tensorboard
55
+ resolution: 1024
56
+ resume_from_checkpoint: null
57
+ revision: null
58
+ sample_batch_size: 4
59
+ scale_lr: false
60
+ seed: 0
61
+ snr_gamma: null
62
+ text_encoder_lr: 5.0e-06
63
+ train_batch_size: 1
64
+ train_text_encoder: false
65
+ use_8bit_adam: false
66
+ use_dora: false
67
+ validation_epochs: 25
68
+ validation_prompt: infrared sensor image of woman face with makeup
69
+ variant: null
70
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1728445547.0736525/events.out.tfevents.1728445547.vipatidar-Z590-UD.1864535.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e754fdec96fb4a0bf76011db6663fff412ba10f91f75ec63210b4eb935f2a0c
3
+ size 3341
logs/dreambooth-lora-sd-xl/1728445547.074412/hparams.yml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: null
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 4
20
+ gradient_checkpointing: false
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: /home/gdivya/generate_faces/cropped_faces
25
+ instance_prompt: infrared sensor image of woman face
26
+ learning_rate: 0.0001
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 500
35
+ mixed_precision: null
36
+ num_class_images: 100
37
+ num_train_epochs: 2
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: /home/gdivya/generate_faces/lora_xl
41
+ output_kohya_format: false
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
43
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
44
+ prior_generation_precision: null
45
+ prior_loss_weight: 1.0
46
+ prodigy_beta3: null
47
+ prodigy_decouple: true
48
+ prodigy_safeguard_warmup: true
49
+ prodigy_use_bias_correction: true
50
+ push_to_hub: true
51
+ random_flip: false
52
+ rank: 4
53
+ repeats: 1
54
+ report_to: tensorboard
55
+ resolution: 1024
56
+ resume_from_checkpoint: null
57
+ revision: null
58
+ sample_batch_size: 4
59
+ scale_lr: false
60
+ seed: 0
61
+ snr_gamma: null
62
+ text_encoder_lr: 5.0e-06
63
+ train_batch_size: 1
64
+ train_text_encoder: false
65
+ use_8bit_adam: false
66
+ use_dora: false
67
+ validation_epochs: 25
68
+ validation_prompt: infrared sensor image of woman face with makeup
69
+ variant: null
70
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1728445591.4734476/events.out.tfevents.1728445591.vipatidar-Z590-UD.1865176.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:254276e3eb97e8e2c2a5b11ebc1ed0644d40280fa2fc7de1422502d5f4474b7d
3
+ size 3389
logs/dreambooth-lora-sd-xl/1728445591.4742537/hparams.yml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: null
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 4
20
+ gradient_checkpointing: false
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: /home/gdivya/generate_faces/cropped_faces
25
+ instance_prompt: infrared sensor image of woman face
26
+ learning_rate: 0.0001
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 500
35
+ mixed_precision: fp16
36
+ num_class_images: 100
37
+ num_train_epochs: 2
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: /home/gdivya/generate_faces/lora_xl
41
+ output_kohya_format: false
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
43
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
44
+ prior_generation_precision: null
45
+ prior_loss_weight: 1.0
46
+ prodigy_beta3: null
47
+ prodigy_decouple: true
48
+ prodigy_safeguard_warmup: true
49
+ prodigy_use_bias_correction: true
50
+ push_to_hub: true
51
+ random_flip: false
52
+ rank: 4
53
+ repeats: 1
54
+ report_to: tensorboard
55
+ resolution: 1024
56
+ resume_from_checkpoint: null
57
+ revision: null
58
+ sample_batch_size: 4
59
+ scale_lr: false
60
+ seed: 0
61
+ snr_gamma: null
62
+ text_encoder_lr: 5.0e-06
63
+ train_batch_size: 1
64
+ train_text_encoder: false
65
+ use_8bit_adam: false
66
+ use_dora: false
67
+ validation_epochs: 25
68
+ validation_prompt: infrared sensor image of woman face with makeup
69
+ variant: null
70
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1728445784.2501283/events.out.tfevents.1728445784.vipatidar-Z590-UD.1868241.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90b6918df7d25d548356df82d0d8d5c93ec3849d16524be77e9ec546cfb9fc4
3
+ size 3389
logs/dreambooth-lora-sd-xl/1728445784.250954/hparams.yml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: null
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 4
20
+ gradient_checkpointing: false
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: /home/gdivya/generate_faces/cropped_faces
25
+ instance_prompt: infrared sensor image of woman face
26
+ learning_rate: 0.0001
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 500
35
+ mixed_precision: bf16
36
+ num_class_images: 100
37
+ num_train_epochs: 2
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: /home/gdivya/generate_faces/lora_xl
41
+ output_kohya_format: false
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
43
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
44
+ prior_generation_precision: null
45
+ prior_loss_weight: 1.0
46
+ prodigy_beta3: null
47
+ prodigy_decouple: true
48
+ prodigy_safeguard_warmup: true
49
+ prodigy_use_bias_correction: true
50
+ push_to_hub: true
51
+ random_flip: false
52
+ rank: 4
53
+ repeats: 1
54
+ report_to: tensorboard
55
+ resolution: 1024
56
+ resume_from_checkpoint: null
57
+ revision: null
58
+ sample_batch_size: 4
59
+ scale_lr: false
60
+ seed: 0
61
+ snr_gamma: null
62
+ text_encoder_lr: 5.0e-06
63
+ train_batch_size: 1
64
+ train_text_encoder: false
65
+ use_8bit_adam: false
66
+ use_dora: false
67
+ validation_epochs: 25
68
+ validation_prompt: infrared sensor image of woman face with makeup
69
+ variant: null
70
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1728386777.vipatidar-Z590-UD.1105015.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f3d892fda094d4f92c180f138bfccecda0d39f9d240a91ce664decb12bf00b
3
+ size 37058
logs/dreambooth-lora-sd-xl/events.out.tfevents.1728402516.vipatidar-Z590-UD.1338594.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf0516b0b29198ca48df2fe9c3db9c6d07fa0aa0f9ed55a34f9e29fec317f4b3
3
+ size 4364133
logs/dreambooth-lora-sd-xl/events.out.tfevents.1728444503.vipatidar-Z590-UD.1848383.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0d9c281affe742b39eee19da3bab424c49e59a0953d2c19751c44d5bf27513
3
+ size 4363938
logs/dreambooth-lora-sd-xl/events.out.tfevents.1728445396.vipatidar-Z590-UD.1862543.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ce96f8d3151193cd3c9eb917baa2281e1941da0044d68c92915aca744a6beac
3
+ size 88
logs/dreambooth-lora-sd-xl/events.out.tfevents.1728445547.vipatidar-Z590-UD.1864535.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3a5b7cdc5a001f6491dfa843236f8ba293b4c5fe47aaa48eadf932c2ae96f3
3
+ size 88
logs/dreambooth-lora-sd-xl/events.out.tfevents.1728445591.vipatidar-Z590-UD.1865176.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44f80c36a1ebe0308cb66247483e8190b5ee907bcb1c237b16d691721f7ed626
3
+ size 31728
logs/dreambooth-lora-sd-xl/events.out.tfevents.1728445784.vipatidar-Z590-UD.1868241.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18079a0cfe75511fa425764017f301899eecc18c91a7060043b9931f29123532
3
+ size 8054127
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb078a487c97b97ceb8cf6576bfb1616935ab8d0bf3e66fa15a3e1cee0b0ead2
3
+ size 23390424