bongbongbong commited on
Commit
9b46ab4
1 Parent(s): 80ac3a5

End of training

Browse files
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: sd-legacy/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 - bongbongbong/LoRA_Output
20
+ These are LoRA adaption weights for sd-legacy/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/1726582576.6716561/events.out.tfevents.1726582576.8c9f9911d24f.6308.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:920d081a9e563e41da1f812143823dcc2a1a22ce38d37a0d88109f668512a744
3
+ size 2257
logs/text2image-fine-tune/1726582576.687166/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: 4
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: 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: 2000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 7
31
+ num_validation_images: 4
32
+ output_dir: /content/drive/MyDrive/LoRA_Output
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: runwayml/stable-diffusion-v1-5
35
+ push_to_hub: false
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: A naruto with blue eyes.
50
+ variant: null
logs/text2image-fine-tune/1726584396.7526689/events.out.tfevents.1726584396.f41229a69832.2341.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a885c5f7ad1620468b1e35e435df061f014c25df5f3b3c8f958a2b1c7692fe16
3
+ size 2257
logs/text2image-fine-tune/1726584396.7835157/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: 4
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: 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: 2000
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 7
31
+ num_validation_images: 4
32
+ output_dir: /content/drive/MyDrive/LoRA_Output
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: A naruto with blue eyes.
50
+ variant: null
logs/text2image-fine-tune/1726585965.1546402/events.out.tfevents.1726585965.f41229a69832.9180.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4dce0ab5fec21119bd98f7513d8a84b9960f94b8d70cd5adf877ce8bd94e944
3
+ size 2258
logs/text2image-fine-tune/1726585965.1635497/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: 4
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: 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: 100
28
+ mixed_precision: null
29
+ noise_offset: 0
30
+ num_train_epochs: 1
31
+ num_validation_images: 4
32
+ output_dir: /content/drive/MyDrive/LoRA_Output
33
+ prediction_type: null
34
+ pretrained_model_name_or_path: sd-legacy/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: A naruto with blue eyes.
50
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1726582576.8c9f9911d24f.6308.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868d139173ed972c831e726cd30fc1b71a93a44b7054e5da46636c3927fac9e0
3
+ size 88
logs/text2image-fine-tune/events.out.tfevents.1726584396.f41229a69832.2341.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9d78be4b3b3bb62f2f4e37448de43c713dde86fcb3cc5178738f28fcd93c3a
3
+ size 14955
logs/text2image-fine-tune/events.out.tfevents.1726585965.f41229a69832.9180.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bbe967f0392784648bc1049f2f115b3d3cc927a3adf5c6e8011c46f833eb15e
3
+ size 3135643
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f84dc09c73be5204fa12779f9c12e7177d183148e0a6c20686bda669b0f3e97
3
+ size 3226184