Hugging Face's logo

rzemaitis
/
corgy_dog_LoRA

Text-to-Image
Diffusers
TensorBoard
stable-diffusion-xl
stable-diffusion-xl-diffusers
lora
template:sd-lora
diffusers-training
Model card Files Metrics Community
rzemaitis commited on
Commit
2d2b51e
•
1 Parent(s): 5fd9278

End of training

Browse files
Files changed (16) hide show
  1. README.md +39 -0
  2. checkpoint-717/optimizer.bin +3 -0
  3. checkpoint-717/pytorch_lora_weights.safetensors +3 -0
  4. checkpoint-717/random_states_0.pkl +3 -0
  5. checkpoint-717/scaler.pt +3 -0
  6. checkpoint-717/scheduler.bin +3 -0
  7. logs/dreambooth-lora-sd-xl/1707139377.541415/events.out.tfevents.1707139377.2b68c2903b2b.2518.1 +3 -0
  8. logs/dreambooth-lora-sd-xl/1707139377.5435538/hparams.yml +67 -0
  9. logs/dreambooth-lora-sd-xl/1707140953.5884652/events.out.tfevents.1707140953.2b68c2903b2b.9985.1 +3 -0
  10. logs/dreambooth-lora-sd-xl/1707140953.5904312/hparams.yml +67 -0
  11. logs/dreambooth-lora-sd-xl/1707141077.4916365/events.out.tfevents.1707141077.2b68c2903b2b.10524.1 +3 -0
  12. logs/dreambooth-lora-sd-xl/1707141077.4937522/hparams.yml +67 -0
  13. logs/dreambooth-lora-sd-xl/events.out.tfevents.1707139377.2b68c2903b2b.2518.0 +3 -0
  14. logs/dreambooth-lora-sd-xl/events.out.tfevents.1707140953.2b68c2903b2b.9985.0 +3 -0
  15. logs/dreambooth-lora-sd-xl/events.out.tfevents.1707141077.2b68c2903b2b.10524.0 +3 -0
  16. pytorch_lora_weights.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - stable-diffusion-xl
5
+ - stable-diffusion-xl-diffusers
6
+ - text-to-image
7
+ - diffusers
8
+ - lora
9
+ - template:sd-lora
10
+
11
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
12
+ instance_prompt: a photo of TOK dog
13
+ license: openrail++
14
+ ---
15
+
16
+ # SDXL LoRA DreamBooth - rzemaitis/corgy_dog_LoRA
17
+
18
+ <Gallery />
19
+
20
+ ## Model description
21
+
22
+ These are rzemaitis/corgy_dog_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
23
+
24
+ The weights were trained using [DreamBooth](https://dreambooth.github.io/).
25
+
26
+ LoRA for the text encoder was enabled: False.
27
+
28
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
29
+
30
+ ## Trigger words
31
+
32
+ You should use a photo of TOK dog to trigger the image generation.
33
+
34
+ ## Download model
35
+
36
+ Weights for this model are available in Safetensors format.
37
+
38
+ [Download](rzemaitis/corgy_dog_LoRA/tree/main) them in the Files & versions tab.
39
+
checkpoint-717/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b4205fdb9ef1197c81d41ffba5f33d54d660562d2d7e37a6a9af379efbfa258
3
+ size 14991036
checkpoint-717/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba62cba717169eae535b69e2fc0d4aec3acf6482f5105537735522f9bbebda9
3
+ size 23390424
checkpoint-717/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ec6602d66d710a0cfe2dcf7586b123609bf22b32fdfa0cc83a8b5b9a196d09
3
+ size 14280
checkpoint-717/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40394f0c1a0d9600abd0b500693bd334a0baa4c7c7aee59303573a1b766545f1
3
+ size 988
checkpoint-717/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0028676b944fe15df09dc179185c0e69152f44689e48677a847aa42dccd34a4a
3
+ size 1000
logs/dreambooth-lora-sd-xl/1707139377.541415/events.out.tfevents.1707139377.2b68c2903b2b.2518.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aebfc73056b123d09fc160e2c457ddd7cc20ffd119b35b015e252e174b3d148f
3
+ size 3136
logs/dreambooth-lora-sd-xl/1707139377.5435538/hparams.yml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: prompt
9
+ center_crop: false
10
+ checkpointing_steps: 717
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: dog
17
+ enable_xformers_memory_efficient_attention: false
18
+ gradient_accumulation_steps: 3
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ instance_data_dir: null
24
+ instance_prompt: a photo of TOK dog
25
+ learning_rate: 0.0001
26
+ local_rank: -1
27
+ logging_dir: logs
28
+ lr_num_cycles: 1
29
+ lr_power: 1.0
30
+ lr_scheduler: constant
31
+ lr_warmup_steps: 0
32
+ max_grad_norm: 1.0
33
+ max_train_steps: 500
34
+ mixed_precision: fp16
35
+ num_class_images: 100
36
+ num_train_epochs: 250
37
+ num_validation_images: 4
38
+ optimizer: AdamW
39
+ output_dir: corgy_dog_LoRA
40
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
41
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
42
+ prior_generation_precision: null
43
+ prior_loss_weight: 1.0
44
+ prodigy_beta3: null
45
+ prodigy_decouple: true
46
+ prodigy_safeguard_warmup: true
47
+ prodigy_use_bias_correction: true
48
+ push_to_hub: false
49
+ random_flip: false
50
+ rank: 4
51
+ repeats: 1
52
+ report_to: tensorboard
53
+ resolution: 1024
54
+ resume_from_checkpoint: null
55
+ revision: null
56
+ sample_batch_size: 4
57
+ scale_lr: false
58
+ seed: 0
59
+ snr_gamma: 5.0
60
+ text_encoder_lr: 5.0e-06
61
+ train_batch_size: 1
62
+ train_text_encoder: false
63
+ use_8bit_adam: true
64
+ validation_epochs: 50
65
+ validation_prompt: null
66
+ variant: null
67
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1707140953.5884652/events.out.tfevents.1707140953.2b68c2903b2b.9985.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d8d46e1867422cb58baa5723f7970dca2d9c5ab2d770b31b7765b2875305cc
3
+ size 3139
logs/dreambooth-lora-sd-xl/1707140953.5904312/hparams.yml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: prompt
9
+ center_crop: false
10
+ checkpointing_steps: 717
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: gbj
17
+ enable_xformers_memory_efficient_attention: false
18
+ gradient_accumulation_steps: 3
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ instance_data_dir: null
24
+ instance_prompt: a photo of gbj person
25
+ learning_rate: 0.0001
26
+ local_rank: -1
27
+ logging_dir: logs
28
+ lr_num_cycles: 1
29
+ lr_power: 1.0
30
+ lr_scheduler: constant
31
+ lr_warmup_steps: 0
32
+ max_grad_norm: 1.0
33
+ max_train_steps: 500
34
+ mixed_precision: fp16
35
+ num_class_images: 100
36
+ num_train_epochs: 100
37
+ num_validation_images: 4
38
+ optimizer: AdamW
39
+ output_dir: corgy_dog_LoRA
40
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
41
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
42
+ prior_generation_precision: null
43
+ prior_loss_weight: 1.0
44
+ prodigy_beta3: null
45
+ prodigy_decouple: true
46
+ prodigy_safeguard_warmup: true
47
+ prodigy_use_bias_correction: true
48
+ push_to_hub: false
49
+ random_flip: false
50
+ rank: 4
51
+ repeats: 1
52
+ report_to: tensorboard
53
+ resolution: 1024
54
+ resume_from_checkpoint: null
55
+ revision: null
56
+ sample_batch_size: 4
57
+ scale_lr: false
58
+ seed: 0
59
+ snr_gamma: 5.0
60
+ text_encoder_lr: 5.0e-06
61
+ train_batch_size: 1
62
+ train_text_encoder: false
63
+ use_8bit_adam: true
64
+ validation_epochs: 50
65
+ validation_prompt: null
66
+ variant: null
67
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1707141077.4916365/events.out.tfevents.1707141077.2b68c2903b2b.10524.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef6d4d5d589e27d3007c41795e26e65815a94f0cc6bf3a948320e03aa276486
3
+ size 3139
logs/dreambooth-lora-sd-xl/1707141077.4937522/hparams.yml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: prompt
9
+ center_crop: false
10
+ checkpointing_steps: 717
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: gbj
17
+ enable_xformers_memory_efficient_attention: false
18
+ gradient_accumulation_steps: 3
19
+ gradient_checkpointing: true
20
+ hub_model_id: null
21
+ hub_token: null
22
+ image_column: image
23
+ instance_data_dir: null
24
+ instance_prompt: a photo of gbj person
25
+ learning_rate: 0.0001
26
+ local_rank: -1
27
+ logging_dir: logs
28
+ lr_num_cycles: 1
29
+ lr_power: 1.0
30
+ lr_scheduler: constant
31
+ lr_warmup_steps: 0
32
+ max_grad_norm: 1.0
33
+ max_train_steps: 1300
34
+ mixed_precision: fp16
35
+ num_class_images: 100
36
+ num_train_epochs: 260
37
+ num_validation_images: 4
38
+ optimizer: AdamW
39
+ output_dir: corgy_dog_LoRA
40
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
41
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
42
+ prior_generation_precision: null
43
+ prior_loss_weight: 1.0
44
+ prodigy_beta3: null
45
+ prodigy_decouple: true
46
+ prodigy_safeguard_warmup: true
47
+ prodigy_use_bias_correction: true
48
+ push_to_hub: false
49
+ random_flip: false
50
+ rank: 4
51
+ repeats: 1
52
+ report_to: tensorboard
53
+ resolution: 512
54
+ resume_from_checkpoint: null
55
+ revision: null
56
+ sample_batch_size: 4
57
+ scale_lr: false
58
+ seed: 0
59
+ snr_gamma: 5.0
60
+ text_encoder_lr: 5.0e-06
61
+ train_batch_size: 1
62
+ train_text_encoder: false
63
+ use_8bit_adam: true
64
+ validation_epochs: 50
65
+ validation_prompt: null
66
+ variant: null
67
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1707139377.2b68c2903b2b.2518.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11d07b712b3cefea3ad7e6c54101c3895385295f72f0b1fee1112c4b35a82e6
3
+ size 2048
logs/dreambooth-lora-sd-xl/events.out.tfevents.1707140953.2b68c2903b2b.9985.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5809650ddf0c9c928e33270871973bc04d26c037434a7a296d5fe2554881330c
3
+ size 326
logs/dreambooth-lora-sd-xl/events.out.tfevents.1707141077.2b68c2903b2b.10524.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15e10da02c69143eb8836186ae20b822b2f4d2d2b2f0fbf035aa36b3df337d3
3
+ size 283334
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b2ab4da92e18482014f587260698716d0c0362a29930fda4633626b81ba5ce
3
+ size 23390424