anhvth5 commited on
Commit
dddc57e
1 Parent(s): c133d3a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stabilityai/stable-diffusion-3-medium-diffusers
3
+ library_name: diffusers
4
+ license: openrail++
5
+ tags:
6
+ - text-to-image
7
+ - diffusers-training
8
+ - diffusers
9
+ - sd3
10
+ - sd3-diffusers
11
+ - template:sd-lora
12
+ instance_prompt: a photo of FIO, game character
13
+ widget: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+
20
+ # SD3 DreamBooth LoRA - anhvth5/trained-sd3-lora
21
+
22
+ <Gallery />
23
+
24
+ ## Model description
25
+
26
+ These are anhvth5/trained-sd3-lora DreamBooth weights for stabilityai/stable-diffusion-3-medium-diffusers.
27
+
28
+ The weights were trained using [DreamBooth](https://dreambooth.github.io/).
29
+
30
+ ## Trigger words
31
+
32
+ You should use a photo of FIO, game character to trigger the image generation.
33
+
34
+ ## Download model
35
+
36
+ [Download](anhvth5/trained-sd3-lora/tree/main) them in the Files & versions tab.
37
+
38
+ ## License
39
+
40
+ Please adhere to the licensing terms as described `[here](https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/LICENSE)`.
41
+
42
+
43
+ ## Intended uses & limitations
44
+
45
+ #### How to use
46
+
47
+ ```python
48
+ # TODO: add an example code snippet for running this diffusion pipeline
49
+ ```
50
+
51
+ #### Limitations and bias
52
+
53
+ [TODO: provide examples of latent issues and potential remediations]
54
+
55
+ ## Training details
56
+
57
+ [TODO: describe the data used to train the model]
logs/dreambooth-sd3-lora/1718623611.732331/events.out.tfevents.1718623611.5f78c22962cf.43618.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db8bfebb93c55711a678a266f578630cdd53a854b7bd1c682e6021358500f68
3
+ size 3052
logs/dreambooth-sd3-lora/1718623611.7336228/hparams.yml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
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: null
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ image_column: image
22
+ instance_data_dir: dog
23
+ instance_prompt: a photo of sks dog
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ logit_mean: 0.0
28
+ logit_std: 1.0
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: 500
35
+ mixed_precision: fp16
36
+ mode_scale: 1.29
37
+ num_class_images: 100
38
+ num_train_epochs: 250
39
+ num_validation_images: 4
40
+ optimizer: AdamW
41
+ output_dir: trained-sd3-lora
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-3-medium-diffusers
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: true
50
+ random_flip: false
51
+ rank: 4
52
+ repeats: 1
53
+ report_to: tensorboard
54
+ resolution: 512
55
+ resume_from_checkpoint: null
56
+ revision: null
57
+ sample_batch_size: 4
58
+ scale_lr: false
59
+ seed: 0
60
+ text_encoder_lr: 5.0e-06
61
+ train_batch_size: 1
62
+ use_8bit_adam: false
63
+ validation_epochs: 25
64
+ validation_prompt: A photo of sks dog in a bucket
65
+ variant: null
66
+ weighting_scheme: sigma_sqrt
67
+ with_prior_preservation: false
logs/dreambooth-sd3-lora/1718623818.9102495/events.out.tfevents.1718623818.5f78c22962cf.45687.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab22025952547bb347b3ac97033fc36a2754b5c3c2f382150d4960633c194ec
3
+ size 3052
logs/dreambooth-sd3-lora/1718623818.9115388/hparams.yml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
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: null
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ image_column: image
22
+ instance_data_dir: dog
23
+ instance_prompt: a photo of sks dog
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ logit_mean: 0.0
28
+ logit_std: 1.0
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: 500
35
+ mixed_precision: fp16
36
+ mode_scale: 1.29
37
+ num_class_images: 100
38
+ num_train_epochs: 250
39
+ num_validation_images: 4
40
+ optimizer: AdamW
41
+ output_dir: trained-sd3-lora
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-3-medium-diffusers
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: true
50
+ random_flip: false
51
+ rank: 4
52
+ repeats: 1
53
+ report_to: tensorboard
54
+ resolution: 512
55
+ resume_from_checkpoint: null
56
+ revision: null
57
+ sample_batch_size: 4
58
+ scale_lr: false
59
+ seed: 0
60
+ text_encoder_lr: 5.0e-06
61
+ train_batch_size: 1
62
+ use_8bit_adam: false
63
+ validation_epochs: 25
64
+ validation_prompt: A photo of sks dog in a bucket
65
+ variant: null
66
+ weighting_scheme: sigma_sqrt
67
+ with_prior_preservation: false
logs/dreambooth-sd3-lora/1718624048.3597517/events.out.tfevents.1718624048.5f78c22962cf.47443.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439033948b5a36325b5d1be588ebff1721ccc559a9b6bd474a065e573df6f5b1
3
+ size 3052
logs/dreambooth-sd3-lora/1718624048.3610606/hparams.yml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
9
+ center_crop: false
10
+ checkpointing_steps: 500
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: null
17
+ gradient_accumulation_steps: 4
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ image_column: image
22
+ instance_data_dir: dog
23
+ instance_prompt: a photo of sks dog
24
+ learning_rate: 1.0e-05
25
+ local_rank: -1
26
+ logging_dir: logs
27
+ logit_mean: 0.0
28
+ logit_std: 1.0
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: 500
35
+ mixed_precision: fp16
36
+ mode_scale: 1.29
37
+ num_class_images: 100
38
+ num_train_epochs: 250
39
+ num_validation_images: 4
40
+ optimizer: AdamW
41
+ output_dir: trained-sd3-lora
42
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-3-medium-diffusers
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: true
50
+ random_flip: false
51
+ rank: 4
52
+ repeats: 1
53
+ report_to: tensorboard
54
+ resolution: 512
55
+ resume_from_checkpoint: null
56
+ revision: null
57
+ sample_batch_size: 4
58
+ scale_lr: false
59
+ seed: 0
60
+ text_encoder_lr: 5.0e-06
61
+ train_batch_size: 1
62
+ use_8bit_adam: false
63
+ validation_epochs: 25
64
+ validation_prompt: A photo of sks dog in a bucket
65
+ variant: null
66
+ weighting_scheme: sigma_sqrt
67
+ with_prior_preservation: false
logs/dreambooth-sd3-lora/events.out.tfevents.1718623611.5f78c22962cf.43618.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50713bd31cd106c87b50ce41d887f7cea83058bb627f037778eafef97c47ab6
3
+ size 88
logs/dreambooth-sd3-lora/events.out.tfevents.1718623818.5f78c22962cf.45687.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f8a87141574e1ae392b5bcaae6889b040543cb56e603bbe2b3d334e90666be
3
+ size 88
logs/dreambooth-sd3-lora/events.out.tfevents.1718624048.5f78c22962cf.47443.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed067788e9efa40f84c77780e447739c8847b2b78f8ad1f21e9441db47bb4ff3
3
+ size 88
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55850e98ec5d8d15602cadc52431880e3083cb7376075d5f45683c55f9a33020
3
+ size 4742848