ripanroy commited on
Commit
304d829
·
verified ·
1 Parent(s): 248df48

End of training

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: openrail++
3
+ library_name: diffusers
4
+ tags:
5
+ - text-to-image
6
+ - text-to-image
7
+ - diffusers-training
8
+ - diffusers
9
+ - dora
10
+ - template:sd-lora
11
+ - stable-diffusion-xl
12
+ - stable-diffusion-xl-diffusers
13
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
14
+ instance_prompt: Indian Ethenic dresses like kurta for male and lehenga for female
15
+ widget: []
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+
22
+ # SDXL LoRA DreamBooth - ripanroy/vto_demo
23
+
24
+ <Gallery />
25
+
26
+ ## Model description
27
+
28
+ These are ripanroy/vto_demo LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
29
+
30
+ The weights were trained using [DreamBooth](https://dreambooth.github.io/).
31
+
32
+ LoRA for the text encoder was enabled: False.
33
+
34
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
35
+
36
+ ## Trigger words
37
+
38
+ You should use Indian Ethenic dresses like kurta for male and lehenga for female to trigger the image generation.
39
+
40
+ ## Download model
41
+
42
+ Weights for this model are available in Safetensors format.
43
+
44
+ [Download](ripanroy/vto_demo/tree/main) them in the Files & versions tab.
45
+
46
+
47
+
48
+ ## Intended uses & limitations
49
+
50
+ #### How to use
51
+
52
+ ```python
53
+ # TODO: add an example code snippet for running this diffusion pipeline
54
+ ```
55
+
56
+ #### Limitations and bias
57
+
58
+ [TODO: provide examples of latent issues and potential remediations]
59
+
60
+ ## Training details
61
+
62
+ [TODO: describe the data used to train the model]
checkpoint-717/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb18263475c28bb7f869c554c4252fae68f86154be4019a19d33d8c2ea2c8c9
3
+ size 14991036
checkpoint-717/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5de9811a5ca5fa8f226aa7b8242bc52789a2f27446f7673d433bbc003c78e7
3
+ size 23390424
checkpoint-717/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61fd5ff3ac6eed12d1331bef408d00c5e43a05b4cd132ec63f66df5f99a2f63f
3
+ size 14280
checkpoint-717/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40394f0c1a0d9600abd0b500693bd334a0baa4c7c7aee59303573a1b766545f1
3
+ size 988
checkpoint-717/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a4bb04f62068d6f0b818f7cea537cc7dc78803ab50c8081ee56e01a72f10df
3
+ size 1000
logs/dreambooth-lora-sd-xl/1710231627.5336943/events.out.tfevents.1710231627.5378c96cc52e.3645.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dbbdfd2c0f516afeec76bf8b3f3317c8a45aba52526aa1d2c52a4b92b6ec65f
3
+ size 3289
logs/dreambooth-lora-sd-xl/1710231627.535645/hparams.yml ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: prompt
9
+ center_crop: false
10
+ checkpointing_steps: 717
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: dataset
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 3
20
+ gradient_checkpointing: true
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: null
25
+ instance_prompt: Indian Ethenic dresses like kurta for male and lehenga for female
26
+ learning_rate: 0.0001
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 15000
35
+ mixed_precision: fp16
36
+ num_class_images: 100
37
+ num_train_epochs: 3750
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: vto_demo
41
+ pretrained_model_name_or_path: diffusers/stable-diffusion-xl-1.0-inpainting-0.1
42
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
43
+ prior_generation_precision: null
44
+ prior_loss_weight: 1.0
45
+ prodigy_beta3: null
46
+ prodigy_decouple: true
47
+ prodigy_safeguard_warmup: true
48
+ prodigy_use_bias_correction: true
49
+ push_to_hub: false
50
+ random_flip: false
51
+ rank: 4
52
+ repeats: 1
53
+ report_to: tensorboard
54
+ resolution: 1024
55
+ resume_from_checkpoint: null
56
+ revision: null
57
+ sample_batch_size: 4
58
+ scale_lr: false
59
+ seed: 0
60
+ snr_gamma: 5.0
61
+ text_encoder_lr: 5.0e-06
62
+ train_batch_size: 1
63
+ train_text_encoder: false
64
+ use_8bit_adam: true
65
+ use_dora: false
66
+ validation_epochs: 50
67
+ validation_prompt: null
68
+ variant: null
69
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1710231778.7881057/events.out.tfevents.1710231778.5378c96cc52e.4525.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b7e472d790c07c5c843270ddc649bdd363baef754a77cad31b42d0298c1de2
3
+ size 3281
logs/dreambooth-lora-sd-xl/1710231778.7901704/hparams.yml ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: prompt
9
+ center_crop: false
10
+ checkpointing_steps: 717
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: dataset
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 3
20
+ gradient_checkpointing: true
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: null
25
+ instance_prompt: Indian Ethenic dresses like kurta for male and lehenga for female
26
+ learning_rate: 1.0e-05
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 15000
35
+ mixed_precision: fp16
36
+ num_class_images: 100
37
+ num_train_epochs: 3750
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: vto_demo
41
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
42
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
43
+ prior_generation_precision: null
44
+ prior_loss_weight: 1.0
45
+ prodigy_beta3: null
46
+ prodigy_decouple: true
47
+ prodigy_safeguard_warmup: true
48
+ prodigy_use_bias_correction: true
49
+ push_to_hub: false
50
+ random_flip: false
51
+ rank: 4
52
+ repeats: 1
53
+ report_to: tensorboard
54
+ resolution: 1024
55
+ resume_from_checkpoint: null
56
+ revision: null
57
+ sample_batch_size: 4
58
+ scale_lr: false
59
+ seed: 0
60
+ snr_gamma: 5.0
61
+ text_encoder_lr: 5.0e-06
62
+ train_batch_size: 1
63
+ train_text_encoder: false
64
+ use_8bit_adam: true
65
+ use_dora: false
66
+ validation_epochs: 50
67
+ validation_prompt: null
68
+ variant: null
69
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1710231954.7707374/events.out.tfevents.1710231954.5378c96cc52e.5496.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2eb4e15294c08ea72d4eed157df269bb96fbf9a96cd492106f41c73e123e6e
3
+ size 3281
logs/dreambooth-lora-sd-xl/1710231954.7726834/hparams.yml ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: 0.001
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ caption_column: prompt
9
+ center_crop: false
10
+ checkpointing_steps: 717
11
+ checkpoints_total_limit: null
12
+ class_data_dir: null
13
+ class_prompt: null
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: dataset
17
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 3
20
+ gradient_checkpointing: true
21
+ hub_model_id: null
22
+ hub_token: null
23
+ image_column: image
24
+ instance_data_dir: null
25
+ instance_prompt: Indian Ethenic dresses like kurta for male and lehenga for female
26
+ learning_rate: 1.0e-05
27
+ local_rank: -1
28
+ logging_dir: logs
29
+ lr_num_cycles: 1
30
+ lr_power: 1.0
31
+ lr_scheduler: constant
32
+ lr_warmup_steps: 0
33
+ max_grad_norm: 1.0
34
+ max_train_steps: 1000
35
+ mixed_precision: fp16
36
+ num_class_images: 100
37
+ num_train_epochs: 250
38
+ num_validation_images: 4
39
+ optimizer: AdamW
40
+ output_dir: vto_demo
41
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
42
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
43
+ prior_generation_precision: null
44
+ prior_loss_weight: 1.0
45
+ prodigy_beta3: null
46
+ prodigy_decouple: true
47
+ prodigy_safeguard_warmup: true
48
+ prodigy_use_bias_correction: true
49
+ push_to_hub: false
50
+ random_flip: false
51
+ rank: 4
52
+ repeats: 1
53
+ report_to: tensorboard
54
+ resolution: 1024
55
+ resume_from_checkpoint: null
56
+ revision: null
57
+ sample_batch_size: 4
58
+ scale_lr: false
59
+ seed: 0
60
+ snr_gamma: 5.0
61
+ text_encoder_lr: 5.0e-06
62
+ train_batch_size: 1
63
+ train_text_encoder: false
64
+ use_8bit_adam: true
65
+ use_dora: false
66
+ validation_epochs: 50
67
+ validation_prompt: null
68
+ variant: null
69
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1710231627.5378c96cc52e.3645.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3018f92734acf592b73cd6cdc892a10985ef388fe5d701738b712fe302309cd0
3
+ size 88
logs/dreambooth-lora-sd-xl/events.out.tfevents.1710231778.5378c96cc52e.4525.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4b1cd1131f027cf30779fb88feb4414d808861a5126b711bb78482bbe1d08d
3
+ size 8936
logs/dreambooth-lora-sd-xl/events.out.tfevents.1710231954.5378c96cc52e.5496.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0722133e2c515b7b39e30e51a383af136d2b77c63f0a0427be208d2c61261908
3
+ size 209442
pytorch_lora_weights.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65bf23560ca3a71e3ea93d98ee049b9203bc9fb8e52d11555a6fa61f9120b7fc
3
- size 3357296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1989218d073537a209e853917268a44cbdfe7048f389b0cfb07d537ea8d48c2
3
+ size 23390424