Hugging Face's logo

ffkatya
/
naruto-lora

Text-to-Image
Diffusers
TensorBoard
Safetensors
stable-diffusion
stable-diffusion-diffusers
diffusers-training
lora
Model card Files Metrics Community
ffkatya commited on
Commit
ec6d92c
•
1 Parent(s): e9b5028

End of training

Browse files
Files changed (18) hide show
  1. README.md +43 -0
  2. image_0.png +0 -0
  3. image_1.png +0 -0
  4. image_2.png +0 -0
  5. image_3.png +0 -0
  6. logs/text2image-fine-tune/1715894881.183883/events.out.tfevents.1715894881.00c2cf366f47.5981.1 +3 -0
  7. logs/text2image-fine-tune/1715894881.1855834/hparams.yml +50 -0
  8. logs/text2image-fine-tune/1715895143.540366/events.out.tfevents.1715895143.00c2cf366f47.7173.1 +3 -0
  9. logs/text2image-fine-tune/1715895143.542124/hparams.yml +50 -0
  10. logs/text2image-fine-tune/1715895689.6005714/events.out.tfevents.1715895689.00c2cf366f47.9493.1 +3 -0
  11. logs/text2image-fine-tune/1715895689.6024177/hparams.yml +50 -0
  12. logs/text2image-fine-tune/1715895756.1334956/events.out.tfevents.1715895756.00c2cf366f47.9847.1 +3 -0
  13. logs/text2image-fine-tune/1715895756.1357365/hparams.yml +50 -0
  14. logs/text2image-fine-tune/events.out.tfevents.1715894881.00c2cf366f47.5981.0 +3 -0
  15. logs/text2image-fine-tune/events.out.tfevents.1715895143.00c2cf366f47.7173.0 +3 -0
  16. logs/text2image-fine-tune/events.out.tfevents.1715895689.00c2cf366f47.9493.0 +3 -0
  17. logs/text2image-fine-tune/events.out.tfevents.1715895756.00c2cf366f47.9847.0 +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
+ - stable-diffusion
6
+ - stable-diffusion-diffusers
7
+ - text-to-image
8
+ - diffusers
9
+ - diffusers-training
10
+ - lora
11
+ base_model: runwayml/stable-diffusion-v1-5
12
+ inference: true
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
+ # LoRA text2image fine-tuning - ffkatya/naruto-lora
20
+ These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the lambdalabs/naruto-blip-captions dataset. You can find some example images in the following.
21
+
22
+ ![img_0](./image_0.png)
23
+ ![img_1](./image_1.png)
24
+ ![img_2](./image_2.png)
25
+ ![img_3](./image_3.png)
26
+
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]
image_0.png ADDED
image_1.png ADDED
image_2.png ADDED
image_3.png ADDED
logs/text2image-fine-tune/1715894881.183883/events.out.tfevents.1715894881.00c2cf366f47.5981.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5a9493b17973cacff60591efa28ebe2955aa642930d11804e7eb68af2fc371c
3
+ size 2284
logs/text2image-fine-tune/1715894881.1855834/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/naruto-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: pokemon-lora
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: 50
31
+ num_validation_images: 4
32
+ output_dir: /sddata/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ push_to_hub: true
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: 42
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
50
+ variant: null
logs/text2image-fine-tune/1715895143.540366/events.out.tfevents.1715895143.00c2cf366f47.7173.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701bdd90221320eae2cc8ec112ae526c9b5e1ca4c1ab17a4181be3d910bfa792
3
+ size 2284
logs/text2image-fine-tune/1715895143.542124/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/naruto-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: pokemon-lora
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: 50
31
+ num_validation_images: 4
32
+ output_dir: /sddata/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ push_to_hub: true
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: 42
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
50
+ variant: null
logs/text2image-fine-tune/1715895689.6005714/events.out.tfevents.1715895689.00c2cf366f47.9493.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36d07a7ed6803201a057b6a386c849b38a29b54deb350b1a6c0f94336b2985d
3
+ size 2283
logs/text2image-fine-tune/1715895689.6024177/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/naruto-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: naruto-lora
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: 10000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 33
31
+ num_validation_images: 4
32
+ output_dir: /sddata/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ push_to_hub: true
36
+ random_flip: true
37
+ rank: 4
38
+ report_to: tensorboard
39
+ resolution: 128
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
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
50
+ variant: null
logs/text2image-fine-tune/1715895756.1334956/events.out.tfevents.1715895756.00c2cf366f47.9847.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55fc82bef4de035500a80589527972e040df438ec5a0c966e9d30bcf563bac3
3
+ size 2283
logs/text2image-fine-tune/1715895756.1357365/hparams.yml ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/naruto-blip-captions
14
+ enable_xformers_memory_efficient_attention: false
15
+ gradient_accumulation_steps: 4
16
+ gradient_checkpointing: false
17
+ hub_model_id: naruto-lora
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: 10
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 1
31
+ num_validation_images: 4
32
+ output_dir: /sddata/finetune/lora/pokemon
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ push_to_hub: true
36
+ random_flip: true
37
+ rank: 4
38
+ report_to: tensorboard
39
+ resolution: 128
40
+ resume_from_checkpoint: null
41
+ revision: null
42
+ scale_lr: false
43
+ seed: 42
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
50
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1715894881.00c2cf366f47.5981.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cbf824e95bcf00d0355e19cd8d302dffdd9979b954dd24b83643c7c383eda7d
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1715895143.00c2cf366f47.7173.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df84a61e16f85cf9e63328ae0423afdaeebaa95c4342f17c095ad2cfbc677546
3
+ size 760
logs/text2image-fine-tune/events.out.tfevents.1715895689.00c2cf366f47.9493.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7114130bc512a1615671289435a3c78af11f4a8ca72a949def48b7e3ca51271a
3
+ size 1432
logs/text2image-fine-tune/events.out.tfevents.1715895756.00c2cf366f47.9847.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45db02f7ad63d20bdb40dff5bac19058f53a65b883fabd1447754912a5ee3a75
3
+ size 1692216
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f20548dffc38aa3aad888499d7f8fd80fec33901549b5c6937766a8e43781d79
3
+ size 3226184