zhangyi617 commited on
Commit
d355f5b
·
verified ·
1 Parent(s): 1790f65

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_0.07
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 sha256:70e364a147a8fcac45d9e7bb14eda8cf1c101eccbc92e865b92f56577d6b7a24
3
+ size 1722353544
checkpoint-6000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f573633303f611d3c2ebad966470f042badd210c59bc994f2f9ccfa06cbeb027
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:ab0c3bc67c0c7c32866fddf903b1eb948c217c633b9bad9d3947e61defaa4c65
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: 03613d048bf36d0cd61d6a47eaa1f6d5238976f67eb27ac1f636180b728718d7
  • Pointer size: 131 Bytes
  • Size of remote file: 425 kB
image_1.png ADDED

Git LFS Details

  • SHA256: 89c9eec52528161f511a74e135cc3a2ccaf5b3740b8912ad5d5057cd7803e8cc
  • Pointer size: 131 Bytes
  • Size of remote file: 434 kB
image_2.png ADDED

Git LFS Details

  • SHA256: 1ba66d43eafd81fa66beaa69c345c6d1d88dd2ef148016f76590794b543cc4a5
  • Pointer size: 131 Bytes
  • Size of remote file: 379 kB
image_3.png ADDED

Git LFS Details

  • SHA256: cc8329e7200cef3f2777d71c469b74e4ceb0e0a08d120c6a7f61f50b43c577ae
  • Pointer size: 131 Bytes
  • Size of remote file: 450 kB
logs/text2image-fine-tune/1770817758.7846515/events.out.tfevents.1770817758.wmgubws17.wmgds.wmg.warwick.ac.uk.615819.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56d9b1ea1dc2850ddb972aada47b98d66733a214f6927a2531fef98ea3dde68
3
+ size 2495
logs/text2image-fine-tune/1770817758.786188/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: 0.07
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: sd14_naruto_text_0.07
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_0.07
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/1770817784.308517/events.out.tfevents.1770817784.wmgubws17.wmgds.wmg.warwick.ac.uk.616615.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d715e33f046a427c292346d9fec6acb4e31c078a78d135e34c61f7784cc0721f
3
+ size 2495
logs/text2image-fine-tune/1770817784.3099427/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: 0.07
16
+ gradient_accumulation_steps: 1
17
+ gradient_checkpointing: false
18
+ hub_model_id: sd14_naruto_text_0.07
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_0.07
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.1770817758.wmgubws17.wmgds.wmg.warwick.ac.uk.615819.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444c69fc6de7e3aeef3b14130c17280cb8b3f125074d27c53221ce4955586049
3
+ size 376
logs/text2image-fine-tune/events.out.tfevents.1770817784.wmgubws17.wmgds.wmg.warwick.ac.uk.616615.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db460e83ae17c7fdac1bb16131d8300b6405b6d1594a771ccde3fcea03a5855d
3
+ size 37100091
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd375a6bfc46e550ee6ca5eee990c61abbc82d39c2b612a569a1b2e15541b92
3
+ size 3226184