zhangyi617 commited on
Commit
c85ae5e
·
verified ·
1 Parent(s): 16066f4

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ image_0.png filter=lfs diff=lfs merge=lfs -text
37
+ image_1.png filter=lfs diff=lfs merge=lfs -text
38
+ image_2.png filter=lfs diff=lfs merge=lfs -text
39
+ image_3.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: CompVis/stable-diffusion-v1-4
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ inference: true
6
+ tags:
7
+ - stable-diffusion
8
+ - stable-diffusion-diffusers
9
+ - text-to-image
10
+ - diffusers
11
+ - diffusers-training
12
+ - lora
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 - zhangyi617/sd14_naruto_text_0.005
20
+ These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. 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]
checkpoint-6000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ab8b6e5c232dffb618c433acc1446c321ddddf6560644ec54acf7c29bdb76f
3
+ size 1722353544
checkpoint-6000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4ac111c78abe3838c439c1998d9219cf329701d2a79ba7021a0022c69be610
3
+ size 6592523
checkpoint-6000/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4d8e67897b10b34139622b04e5a3cc79b4c3ffe8ec04b9e9fae59633bff4b5
3
+ size 3226184
checkpoint-6000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119b45dc050f67f8ac6ef9a1863bdb7ed8b76bba0c35c5bbd6d2ea7c00967bee
3
+ size 14821
checkpoint-6000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb2b51b22f222dc6df63edb791d76de5de25b8bb724e885f8753e34cfb8ae10
3
+ size 1383
checkpoint-6000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd36bc98fdcd79a93149a23d5d1fe1a31ea2e04bc414545257bbcc4e0ffd739
3
+ size 1401
image_0.png ADDED

Git LFS Details

  • SHA256: e785bb2c11329a2fa41c8ae307b0b3ddef0ae88c469d43a9bd368de4e6c8bab9
  • Pointer size: 131 Bytes
  • Size of remote file: 408 kB
image_1.png ADDED

Git LFS Details

  • SHA256: 8a146f7ae4a48e9f03af1d577f8fe459b12d86768ec5b108ac2e03c605f478f0
  • Pointer size: 131 Bytes
  • Size of remote file: 430 kB
image_2.png ADDED

Git LFS Details

  • SHA256: ff5cfaad8e7d574b13e809988070856c92ffee7882138f71b67b0ab57fa59c14
  • Pointer size: 131 Bytes
  • Size of remote file: 387 kB
image_3.png ADDED

Git LFS Details

  • SHA256: 24340f61412ff56009efce696f456971edc18ecf7bad166f4538ce6d9d86c96d
  • Pointer size: 131 Bytes
  • Size of remote file: 447 kB
logs/text2image-fine-tune/1770811172.0550454/events.out.tfevents.1770811172.wmgubws17.wmgds.wmg.warwick.ac.uk.457045.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e01ebae3c66e4b59abd2ade37291d15125059c36655459e14a5cc30807ce723
3
+ size 2497
logs/text2image-fine-tune/1770811172.05654/hparams.yml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 6000
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
+ epsilon_m: 0.005
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: sd14_naruto_text_0.005
19
+ hub_token: null
20
+ image_column: image
21
+ image_interpolation_mode: lanczos
22
+ learning_rate: 0.0001
23
+ local_rank: -1
24
+ logging_dir: logs
25
+ lr_scheduler: cosine
26
+ lr_warmup_steps: 0
27
+ max_grad_norm: 1.0
28
+ max_train_samples: null
29
+ max_train_steps: 6120
30
+ mixed_precision: fp16
31
+ noise_offset: 0
32
+ num_train_epochs: 20
33
+ num_validation_images: 4
34
+ output_dir: output_models/sd14_naruto_text_0.005
35
+ prediction_type: null
36
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
37
+ push_to_hub: true
38
+ random_flip: true
39
+ rank: 4
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: 42
46
+ snr_gamma: null
47
+ train_batch_size: 4
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ validation_epochs: 1
51
+ validation_prompt: a car is driving down the road with another car
52
+ variant: null
logs/text2image-fine-tune/1770811212.0592792/events.out.tfevents.1770811212.wmgubws17.wmgds.wmg.warwick.ac.uk.458543.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834ff5da2207bbc8258938625ee718bcf14ed456ba9a6645ca51f63a355acb88
3
+ size 2497
logs/text2image-fine-tune/1770811212.0607045/hparams.yml ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 6000
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
+ epsilon_m: 0.005
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: sd14_naruto_text_0.005
19
+ hub_token: null
20
+ image_column: image
21
+ image_interpolation_mode: lanczos
22
+ learning_rate: 0.0001
23
+ local_rank: -1
24
+ logging_dir: logs
25
+ lr_scheduler: cosine
26
+ lr_warmup_steps: 0
27
+ max_grad_norm: 1.0
28
+ max_train_samples: null
29
+ max_train_steps: 6120
30
+ mixed_precision: fp16
31
+ noise_offset: 0
32
+ num_train_epochs: 20
33
+ num_validation_images: 4
34
+ output_dir: output_models/sd14_naruto_text_0.005
35
+ prediction_type: null
36
+ pretrained_model_name_or_path: CompVis/stable-diffusion-v1-4
37
+ push_to_hub: true
38
+ random_flip: true
39
+ rank: 4
40
+ report_to: tensorboard
41
+ resolution: 512
42
+ resume_from_checkpoint: null
43
+ revision: null
44
+ scale_lr: false
45
+ seed: 42
46
+ snr_gamma: null
47
+ train_batch_size: 4
48
+ train_data_dir: null
49
+ use_8bit_adam: false
50
+ validation_epochs: 1
51
+ validation_prompt: a car is driving down the road with another car
52
+ variant: null
logs/text2image-fine-tune/events.out.tfevents.1770811172.wmgubws17.wmgds.wmg.warwick.ac.uk.457045.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb8a70681605c423d71f2abca766272a7c4120dde64385c46e5a97a70298d7f
3
+ size 1384
logs/text2image-fine-tune/events.out.tfevents.1770811212.wmgubws17.wmgds.wmg.warwick.ac.uk.458543.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6caf17e91d4f4c68d758837f60104b22bb9393aff28159a126ac5bd7812edcd
3
+ size 36489716
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e699ee9a7f78993696214af025952a1a31bef814cfc5270966929cf7671ed3
3
+ size 3226184