Hugging Face's logo

amanalok
/
ram

Text-to-Image
Diffusers
TensorBoard
lora
diffusers-training
stable-diffusion
stable-diffusion-diffusers
Model card Files Metrics Community
amanalok commited on
Commit
2d11778
·
verified ·
1 Parent(s): 81b13f1

End of training

Browse files
Files changed (18) hide show
  1. README.md +43 -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. logs/dreambooth-lora/1710617806.6140509/events.out.tfevents.1710617806.aman-ROG-Strix-G513RM-G513RM.79549.1 +3 -0
  7. logs/dreambooth-lora/1710617806.615639/hparams.yml +56 -0
  8. logs/dreambooth-lora/1710618753.5639186/events.out.tfevents.1710618753.aman-ROG-Strix-G513RM-G513RM.80369.1 +3 -0
  9. logs/dreambooth-lora/1710618753.5657837/hparams.yml +56 -0
  10. logs/dreambooth-lora/1710619749.8277392/events.out.tfevents.1710619749.aman-ROG-Strix-G513RM-G513RM.81357.1 +3 -0
  11. logs/dreambooth-lora/1710619749.8293247/hparams.yml +56 -0
  12. logs/dreambooth-lora/events.out.tfevents.1710617806.aman-ROG-Strix-G513RM-G513RM.79549.0 +3 -0
  13. logs/dreambooth-lora/events.out.tfevents.1710618753.aman-ROG-Strix-G513RM-G513RM.80369.0 +3 -0
  14. logs/dreambooth-lora/events.out.tfevents.1710619749.aman-ROG-Strix-G513RM-G513RM.81357.0 +3 -0
  15. logs/dreambooth/1710617719.8913963/events.out.tfevents.1710617719.aman-ROG-Strix-G513RM-G513RM.79455.1 +3 -0
  16. logs/dreambooth/1710617719.8930438/hparams.yml +60 -0
  17. logs/dreambooth/events.out.tfevents.1710617719.aman-ROG-Strix-G513RM-G513RM.79455.0 +3 -0
  18. pytorch_lora_weights.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: creativeml-openrail-m
3
+ library_name: diffusers
4
+ tags:
5
+ - text-to-image
6
+ - diffusers
7
+ - lora
8
+ - diffusers-training
9
+ - stable-diffusion
10
+ - stable-diffusion-diffusers
11
+ inference: true
12
+ base_model: CompVis/stable-diffusion-v1-4
13
+ instance_prompt: Portrait of Lord Shri Ram
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+
20
+ # LoRA DreamBooth - amanalok/ram
21
+
22
+ These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were trained on Portrait of Lord Shri Ram using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
23
+
24
+
25
+
26
+ LoRA for the text encoder was enabled: False.
27
+
28
+
29
+ ## Intended uses & limitations
30
+
31
+ #### How to use
32
+
33
+ ```python
34
+ # TODO: add an example code snippet for running this diffusion pipeline
35
+ ```
36
+
37
+ #### Limitations and bias
38
+
39
+ [TODO: provide examples of latent issues and potential remediations]
40
+
41
+ ## Training details
42
+
43
+ [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:b93d0210f47d0629e00d96c83689252bf8c4e2de6de6c1a9c6bf369ee97620b4
3
+ size 3403386
checkpoint-500/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8d654246e38e78d98746e29b3534f8619aa7781fb63584fbb8a835e67875a4
3
+ size 1631936
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c93aa66d74412e820b7b6d53c2e8bf95ed1057c233be04dd931df24a681adea
3
+ size 14280
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65115106fbd9463fa6c7133b543dece71c31fcba363ff15b8c73f8c7eb0739c5
3
+ size 1000
logs/dreambooth-lora/1710617806.6140509/events.out.tfevents.1710617806.aman-ROG-Strix-G513RM-G513RM.79549.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad427f6b9904ebd1d53893280d1307a5a71e3dd96598b42b12792d2c7c875cd3
3
+ size 2672
logs/dreambooth-lora/1710617806.615639/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_labels_conditioning: null
11
+ class_prompt: null
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 1
15
+ gradient_checkpointing: false
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: /home/aman/SelfStudy/Datasets/ram
19
+ instance_prompt: Portrait of Lord Shri Ram
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 0
27
+ max_grad_norm: 1.0
28
+ max_train_steps: 96
29
+ mixed_precision: bf16
30
+ num_class_images: 100
31
+ num_train_epochs: 12
32
+ num_validation_images: 4
33
+ output_dir: /home/aman/SelfStudy/Models/stable-diffusion/finetune/dreambooth/ram
34
+ pre_compute_text_embeddings: false
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ prior_generation_precision: null
37
+ prior_loss_weight: 1.0
38
+ push_to_hub: false
39
+ rank: 4
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ text_encoder_use_attention_mask: false
48
+ tokenizer_max_length: null
49
+ tokenizer_name: null
50
+ train_batch_size: 1
51
+ train_text_encoder: false
52
+ use_8bit_adam: false
53
+ validation_epochs: 50
54
+ validation_prompt: null
55
+ variant: null
56
+ with_prior_preservation: false
logs/dreambooth-lora/1710618753.5639186/events.out.tfevents.1710618753.aman-ROG-Strix-G513RM-G513RM.80369.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612f36116b22f335d920556b40947cd6aed29fe8b6e800b17612eb8a9bd6adec
3
+ size 2672
logs/dreambooth-lora/1710618753.5657837/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_labels_conditioning: null
11
+ class_prompt: null
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 1
15
+ gradient_checkpointing: false
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: /home/aman/SelfStudy/Datasets/ram
19
+ instance_prompt: Portrait of Lord Shri Ram
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 0
27
+ max_grad_norm: 1.0
28
+ max_train_steps: 96
29
+ mixed_precision: bf16
30
+ num_class_images: 100
31
+ num_train_epochs: 12
32
+ num_validation_images: 4
33
+ output_dir: /home/aman/SelfStudy/Models/stable-diffusion/finetune/dreambooth/ram
34
+ pre_compute_text_embeddings: false
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ prior_generation_precision: null
37
+ prior_loss_weight: 1.0
38
+ push_to_hub: false
39
+ rank: 4
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ text_encoder_use_attention_mask: false
48
+ tokenizer_max_length: null
49
+ tokenizer_name: null
50
+ train_batch_size: 1
51
+ train_text_encoder: false
52
+ use_8bit_adam: false
53
+ validation_epochs: 50
54
+ validation_prompt: null
55
+ variant: null
56
+ with_prior_preservation: false
logs/dreambooth-lora/1710619749.8277392/events.out.tfevents.1710619749.aman-ROG-Strix-G513RM-G513RM.81357.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d433d02077eea9a2ca1a1b0b78fd5b903dafd6515b8e2420ccd75c013bd70348
3
+ size 2672
logs/dreambooth-lora/1710619749.8293247/hparams.yml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_labels_conditioning: null
11
+ class_prompt: null
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 1
15
+ gradient_checkpointing: false
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: /home/aman/SelfStudy/Datasets/ram
19
+ instance_prompt: Portrait of Lord Shri Ram
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 0
27
+ max_grad_norm: 1.0
28
+ max_train_steps: 960
29
+ mixed_precision: bf16
30
+ num_class_images: 100
31
+ num_train_epochs: 120
32
+ num_validation_images: 4
33
+ output_dir: /home/aman/SelfStudy/Models/stable-diffusion/finetune/dreambooth/ram
34
+ pre_compute_text_embeddings: false
35
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
36
+ prior_generation_precision: null
37
+ prior_loss_weight: 1.0
38
+ push_to_hub: true
39
+ rank: 4
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ text_encoder_use_attention_mask: false
48
+ tokenizer_max_length: null
49
+ tokenizer_name: null
50
+ train_batch_size: 1
51
+ train_text_encoder: false
52
+ use_8bit_adam: false
53
+ validation_epochs: 50
54
+ validation_prompt: null
55
+ variant: null
56
+ with_prior_preservation: false
logs/dreambooth-lora/events.out.tfevents.1710617806.aman-ROG-Strix-G513RM-G513RM.79549.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18f99d5cb935e23c965338880c060bc8309eee4b5d7a81799832f0dd7e2739a
3
+ size 7960
logs/dreambooth-lora/events.out.tfevents.1710618753.aman-ROG-Strix-G513RM-G513RM.80369.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec74502caba96d3e2022eba557144ade530aeab17454af514cf7920068da096f
3
+ size 7960
logs/dreambooth-lora/events.out.tfevents.1710619749.aman-ROG-Strix-G513RM-G513RM.81357.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123e1dec8284ba98bd480314706bd2a1711ac4228203f3b483cacc56e667164e
3
+ size 80474
logs/dreambooth/1710617719.8913963/events.out.tfevents.1710617719.aman-ROG-Strix-G513RM-G513RM.79455.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccf63e486f2babe265c00c93522c3dd9cc2246ada0b4a55a258f75d8faa018c
3
+ size 2926
logs/dreambooth/1710617719.8930438/hparams.yml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.01
5
+ allow_tf32: false
6
+ center_crop: false
7
+ checkpointing_steps: 500
8
+ checkpoints_total_limit: null
9
+ class_data_dir: null
10
+ class_labels_conditioning: null
11
+ class_prompt: null
12
+ dataloader_num_workers: 0
13
+ enable_xformers_memory_efficient_attention: false
14
+ gradient_accumulation_steps: 1
15
+ gradient_checkpointing: false
16
+ hub_model_id: null
17
+ hub_token: null
18
+ instance_data_dir: /home/aman/SelfStudy/Datasets/ram
19
+ instance_prompt: Portrait of Lord Shri Ram
20
+ learning_rate: 5.0e-06
21
+ local_rank: -1
22
+ logging_dir: logs
23
+ lr_num_cycles: 1
24
+ lr_power: 1.0
25
+ lr_scheduler: constant
26
+ lr_warmup_steps: 0
27
+ max_grad_norm: 1.0
28
+ max_train_steps: 96
29
+ mixed_precision: bf16
30
+ num_class_images: 100
31
+ num_train_epochs: 12
32
+ num_validation_images: 4
33
+ offset_noise: false
34
+ output_dir: /home/aman/SelfStudy/Models/stable-diffusion/finetune/dreambooth/ram
35
+ pre_compute_text_embeddings: false
36
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
37
+ prior_generation_precision: null
38
+ prior_loss_weight: 1.0
39
+ push_to_hub: false
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ sample_batch_size: 4
45
+ scale_lr: false
46
+ seed: null
47
+ set_grads_to_none: false
48
+ skip_save_text_encoder: false
49
+ snr_gamma: 5.0
50
+ text_encoder_use_attention_mask: false
51
+ tokenizer_max_length: null
52
+ tokenizer_name: null
53
+ train_batch_size: 1
54
+ train_text_encoder: false
55
+ use_8bit_adam: false
56
+ validation_prompt: null
57
+ validation_scheduler: DPMSolverMultistepScheduler
58
+ validation_steps: 100
59
+ variant: null
60
+ with_prior_preservation: false
logs/dreambooth/events.out.tfevents.1710617719.aman-ROG-Strix-G513RM-G513RM.79455.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e3be1e036407cee8dfbab4e7bae70fd473d6d1c4ce7df682f740c3758f6797d
3
+ size 88
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e303e96969800191ab02d1c6cbbccc25a0ceb071f5f5f9d775767f4b819decda
3
+ size 3226184