Hugging Face's logo

yifei28
/
sd-naruto-model

Text-to-Image
Diffusers
TensorBoard
Safetensors
English
stable-diffusion
stable-diffusion-diffusers
diffusers-training
lora
Model card Files Metrics Community
yifei28 commited on
Commit
0e361c4
•
1 Parent(s): 94fbb14

End of training

Browse files
Files changed (33) 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/1720806665.715137/events.out.tfevents.1720806665.autodl-container-05c845b795-ce1e9284.10242.1 +3 -0
  7. logs/text2image-fine-tune/1720806665.71644/hparams.yml +50 -0
  8. logs/text2image-fine-tune/1720806852.0834188/events.out.tfevents.1720806852.autodl-container-05c845b795-ce1e9284.10923.1 +3 -0
  9. logs/text2image-fine-tune/1720806852.085011/hparams.yml +50 -0
  10. logs/text2image-fine-tune/1720807473.73621/events.out.tfevents.1720807473.autodl-container-05c845b795-ce1e9284.11684.1 +3 -0
  11. logs/text2image-fine-tune/1720807473.7379334/hparams.yml +50 -0
  12. logs/text2image-fine-tune/1720807668.8316226/events.out.tfevents.1720807668.autodl-container-05c845b795-ce1e9284.12350.1 +3 -0
  13. logs/text2image-fine-tune/1720807668.832914/hparams.yml +50 -0
  14. logs/text2image-fine-tune/1720808945.9263918/events.out.tfevents.1720808945.autodl-container-05c845b795-ce1e9284.13235.1 +3 -0
  15. logs/text2image-fine-tune/1720808945.9279962/hparams.yml +50 -0
  16. logs/text2image-fine-tune/1720809480.1610758/events.out.tfevents.1720809480.autodl-container-05c845b795-ce1e9284.13970.1 +3 -0
  17. logs/text2image-fine-tune/1720809480.162481/hparams.yml +50 -0
  18. logs/text2image-fine-tune/1720809819.6994493/events.out.tfevents.1720809819.autodl-container-05c845b795-ce1e9284.14619.1 +3 -0
  19. logs/text2image-fine-tune/1720809819.701127/hparams.yml +50 -0
  20. logs/text2image-fine-tune/1720811946.5212452/events.out.tfevents.1720811946.autodl-container-05c845b795-ce1e9284.15681.1 +3 -0
  21. logs/text2image-fine-tune/1720811946.5228236/hparams.yml +50 -0
  22. logs/text2image-fine-tune/1720812002.2183094/events.out.tfevents.1720812002.autodl-container-05c845b795-ce1e9284.16273.1 +3 -0
  23. logs/text2image-fine-tune/1720812002.2198272/hparams.yml +50 -0
  24. logs/text2image-fine-tune/events.out.tfevents.1720806665.autodl-container-05c845b795-ce1e9284.10242.0 +3 -0
  25. logs/text2image-fine-tune/events.out.tfevents.1720806852.autodl-container-05c845b795-ce1e9284.10923.0 +3 -0
  26. logs/text2image-fine-tune/events.out.tfevents.1720807473.autodl-container-05c845b795-ce1e9284.11684.0 +3 -0
  27. logs/text2image-fine-tune/events.out.tfevents.1720807668.autodl-container-05c845b795-ce1e9284.12350.0 +3 -0
  28. logs/text2image-fine-tune/events.out.tfevents.1720808945.autodl-container-05c845b795-ce1e9284.13235.0 +3 -0
  29. logs/text2image-fine-tune/events.out.tfevents.1720809480.autodl-container-05c845b795-ce1e9284.13970.0 +3 -0
  30. logs/text2image-fine-tune/events.out.tfevents.1720809819.autodl-container-05c845b795-ce1e9284.14619.0 +3 -0
  31. logs/text2image-fine-tune/events.out.tfevents.1720811946.autodl-container-05c845b795-ce1e9284.15681.0 +3 -0
  32. logs/text2image-fine-tune/events.out.tfevents.1720812002.autodl-container-05c845b795-ce1e9284.16273.0 +3 -0
  33. pytorch_lora_weights.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: runwayml/stable-diffusion-v1-5
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ tags:
6
+ - stable-diffusion
7
+ - stable-diffusion-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - diffusers-training
11
+ - lora
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 - yifei28/sd-naruto-model
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/1720806665.715137/events.out.tfevents.1720806665.autodl-container-05c845b795-ce1e9284.10242.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3786d700f4bc69931d909018f647eb06eb35bb3af58190b1c992ea8b031108
3
+ size 2243
logs/text2image-fine-tune/1720806665.71644/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: 3000
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: true
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: 400
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 2
31
+ num_validation_images: 4
32
+ output_dir: sd-naruto-model
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: 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: Stephen Curry with a headband
50
+ variant: null
logs/text2image-fine-tune/1720806852.0834188/events.out.tfevents.1720806852.autodl-container-05c845b795-ce1e9284.10923.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c1b0793ae61189b164a226dd3e015b98d34dcda458e6e31037f07115397fe7
3
+ size 2219
logs/text2image-fine-tune/1720806852.085011/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: 3000
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: true
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: 400
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 2
31
+ num_validation_images: 4
32
+ output_dir: sd-naruto-model
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: 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: Eevee
50
+ variant: null
logs/text2image-fine-tune/1720807473.73621/events.out.tfevents.1720807473.autodl-container-05c845b795-ce1e9284.11684.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a24677fc66b52b5be5a7ea1c8c72919d13633a6e61111760302b9d397bf1203
3
+ size 2219
logs/text2image-fine-tune/1720807473.7379334/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: 3000
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: true
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: 400
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 2
31
+ num_validation_images: 4
32
+ output_dir: sd-naruto-model
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: 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: Eevee
50
+ variant: null
logs/text2image-fine-tune/1720807668.8316226/events.out.tfevents.1720807668.autodl-container-05c845b795-ce1e9284.12350.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9acc679bcee0b4d2ade59bace514a89011e144a3649e56c21287098667696886
3
+ size 2219
logs/text2image-fine-tune/1720807668.832914/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: 3000
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: true
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: 400
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 2
31
+ num_validation_images: 4
32
+ output_dir: sd-naruto-model
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: 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: Eevee
50
+ variant: null
logs/text2image-fine-tune/1720808945.9263918/events.out.tfevents.1720808945.autodl-container-05c845b795-ce1e9284.13235.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c0cf9ae22a0a829c37501f835a52ad14b5f0a860705e493c53152e3a01892c
3
+ size 2239
logs/text2image-fine-tune/1720808945.9279962/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: 3000
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: true
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: 400
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 2
31
+ num_validation_images: 4
32
+ output_dir: sd-naruto-model
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: 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: Stephen Curry in hairband
50
+ variant: null
logs/text2image-fine-tune/1720809480.1610758/events.out.tfevents.1720809480.autodl-container-05c845b795-ce1e9284.13970.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:721c724ead30a09a858d48324f7c5555b9468683551fb0f32d243fa00d753ef2
3
+ size 2303
logs/text2image-fine-tune/1720809480.162481/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: 3000
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: true
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: 400
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 2
31
+ num_validation_images: 4
32
+ output_dir: sd-naruto-model
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: latest
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: Stephen Curry in hairband
50
+ variant: null
logs/text2image-fine-tune/1720809819.6994493/events.out.tfevents.1720809819.autodl-container-05c845b795-ce1e9284.14619.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b1dc734d4742f51517830e18f5d420add484bda5c3eea375d9f7f7fe0a8780e
3
+ size 2351
logs/text2image-fine-tune/1720809819.701127/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: 3000
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: true
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: 400
28
+ mixed_precision: fp16
29
+ noise_offset: 0
30
+ num_train_epochs: 2
31
+ num_validation_images: 4
32
+ output_dir: sd-naruto-model
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: latest
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: Stephen Curry in hairband
50
+ variant: null
logs/text2image-fine-tune/1720811946.5212452/events.out.tfevents.1720811946.autodl-container-05c845b795-ce1e9284.15681.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e60c490c8adab257fa2f66f0c53efa0d995b51223dfcf862439303928242ab5
3
+ size 2303
logs/text2image-fine-tune/1720811946.5228236/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: 3000
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: true
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: 400
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 2
31
+ num_validation_images: 4
32
+ output_dir: sd-naruto-model
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: latest
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: Stephen Curry in hairband
50
+ variant: null
logs/text2image-fine-tune/1720812002.2183094/events.out.tfevents.1720812002.autodl-container-05c845b795-ce1e9284.16273.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80eb0d351020b68205e4f3b89fd97692ec528dc7e458ff521645b9e07a1b3a0
3
+ size 2351
logs/text2image-fine-tune/1720812002.2198272/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: 3000
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: true
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: 400
28
+ mixed_precision: fp16
29
+ noise_offset: 0
30
+ num_train_epochs: 2
31
+ num_validation_images: 4
32
+ output_dir: sd-naruto-model
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: latest
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: Stephen Curry in hairband
50
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1720806665.autodl-container-05c845b795-ce1e9284.10242.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e23b06ad7add2c6136b1277efa405fa8178f485552469e9513f7b60d71bc23
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1720806852.autodl-container-05c845b795-ce1e9284.10923.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05450c8c15d9e500104d671ead30eb20f9b872f65791e45736f4f02c8e0605a8
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1720807473.autodl-container-05c845b795-ce1e9284.11684.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1719dbb2774cdddd902dfe69b80d248ca2796bf211383fad57b1910521231c9
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1720807668.autodl-container-05c845b795-ce1e9284.12350.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ceaa80c3a5a32ae186be2ad21b66ed3f5b333be4244cdf962a1ca93f8d5213
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1720808945.autodl-container-05c845b795-ce1e9284.13235.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e39783a5bb8c520de9695eb12ffdbb620bb59df4e40df44c630381e331dd8d6
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1720809480.autodl-container-05c845b795-ce1e9284.13970.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466733566a39c298c09e90e6dffd33fc034cc5afa40664ea1c54229486d336ea
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1720809819.autodl-container-05c845b795-ce1e9284.14619.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39b6855814c5bd036c03c5157e7b5c5a810340cccc0c701ed03f66226d6d63a7
3
+ size 14955
logs/text2image-fine-tune/events.out.tfevents.1720811946.autodl-container-05c845b795-ce1e9284.15681.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d8f0e0e13c002666e7c0ec8b0271340d98aaff113145cc5ef825d13b23d0d8a
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1720812002.autodl-container-05c845b795-ce1e9284.16273.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31fb26f60771468519437bb67a6b5f4254a85ab62f5211d09452585618907f15
3
+ size 4847375
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa8472dc2ffdb17637f8d254f4aac4834d8cf8e36f37a95ee9fa6c3af728c547
3
+ size 3226184