MatisseVS commited on
Commit
4d26141
·
verified ·
1 Parent(s): f75b9b4

End of training

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
3
+ library_name: diffusers
4
+ license: openrail++
5
+ instance_prompt: a photo of Will S
6
+ widget: []
7
+ tags:
8
+ - text-to-image
9
+ - text-to-image
10
+ - diffusers-training
11
+ - diffusers
12
+ - lora
13
+ - template:sd-lora
14
+ - stable-diffusion-xl
15
+ - stable-diffusion-xl-diffusers
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 - MatisseVS/SDXL_Dreambooth
23
+
24
+ <Gallery />
25
+
26
+ ## Model description
27
+
28
+ These are MatisseVS/SDXL_Dreambooth 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 a photo of Will S to trigger the image generation.
39
+
40
+ ## Download model
41
+
42
+ Weights for this model are available in Safetensors format.
43
+
44
+ [Download](MatisseVS/SDXL_Dreambooth/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-250/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f96bf4c6a92876136077cefc05c814d03418e749cc9b10acc840289b64bfebff
3
+ size 15133372
checkpoint-250/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d1f7e578f8b4458e13a1d766748633d0c12091d342cff5228dcaebb8b335ba
3
+ size 23390424
checkpoint-250/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ebf39cd6d6994d6869904381c06ea844eaeedbe23a9bf702efaa892108358d
3
+ size 14344
checkpoint-250/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccec82ecb1db9fee8431a9924525ac42c65eba373a478c5528e653b68744a6a9
3
+ size 988
checkpoint-250/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63900f98ac8ba3efebbc10bc30805449bfc970c8cf9a51c1bf41b49aa1f90621
3
+ size 1000
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91effa2563352a7a719f4334d65d47d9d0929d85108310088fbd623af8c814f
3
+ size 15134460
checkpoint-500/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb6574f9a450f0987fdb604a1e28b1ced7053956e723167b5507862e7a03df1
3
+ size 23390424
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0facea6c6dd958e905b8cd7bfff7793bb05d9048dfeaa7ae0102accfb482d2c4
3
+ size 14344
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
3
+ size 988
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf34ac8dd2addc454aeb1ee4eaba3267c2841857e117be40ac2ed02cf581c9c
3
+ size 1000
logs/dreambooth-lora-sd-xl/1746689065.798599/events.out.tfevents.1746689065.51ad53f2e985.15593.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03105200c0e9d0be41d9825dbb82853af7e6b3925bc16649d4cb47c06ba4e1f2
3
+ size 3401
logs/dreambooth-lora-sd-xl/1746689065.800333/hparams.yml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: ./Celebrity Faces Dataset/Will Smith
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
+ image_interpolation_mode: lanczos
25
+ instance_data_dir: null
26
+ instance_prompt: a photo of Will Smith
27
+ learning_rate: 0.0001
28
+ local_rank: -1
29
+ logging_dir: logs
30
+ lr_num_cycles: 1
31
+ lr_power: 1.0
32
+ lr_scheduler: constant
33
+ lr_warmup_steps: 0
34
+ max_grad_norm: 1.0
35
+ max_train_steps: 500
36
+ mixed_precision: fp16
37
+ num_class_images: 100
38
+ num_train_epochs: 15
39
+ num_validation_images: 4
40
+ optimizer: AdamW
41
+ output_dir: SDXL_Dreambooth
42
+ output_kohya_format: false
43
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
44
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
45
+ prior_generation_precision: null
46
+ prior_loss_weight: 1.0
47
+ prodigy_beta3: null
48
+ prodigy_decouple: true
49
+ prodigy_safeguard_warmup: true
50
+ prodigy_use_bias_correction: true
51
+ push_to_hub: false
52
+ random_flip: false
53
+ rank: 4
54
+ repeats: 1
55
+ report_to: tensorboard
56
+ resolution: 1024
57
+ resume_from_checkpoint: null
58
+ revision: null
59
+ sample_batch_size: 4
60
+ scale_lr: false
61
+ seed: 0
62
+ snr_gamma: 5.0
63
+ text_encoder_lr: 5.0e-06
64
+ train_batch_size: 1
65
+ train_text_encoder: false
66
+ use_8bit_adam: true
67
+ use_dora: false
68
+ validation_epochs: 50
69
+ validation_prompt: null
70
+ variant: null
71
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1746694495.0839472/events.out.tfevents.1746694495.51ad53f2e985.38356.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40d33537a2602bd242521257afa77027c1b8ba949574960e6feb4355c2c966fd
3
+ size 3403
logs/dreambooth-lora-sd-xl/1746694495.089546/hparams.yml ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 250
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: ./Celebrity Faces Dataset/Will Smith
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
+ image_interpolation_mode: lanczos
25
+ instance_data_dir: null
26
+ instance_prompt: a photo of skswillsmith
27
+ learning_rate: 0.0001
28
+ local_rank: -1
29
+ logging_dir: logs
30
+ lr_num_cycles: 1
31
+ lr_power: 1.0
32
+ lr_scheduler: constant
33
+ lr_warmup_steps: 0
34
+ max_grad_norm: 1.0
35
+ max_train_steps: 500
36
+ mixed_precision: fp16
37
+ num_class_images: 100
38
+ num_train_epochs: 15
39
+ num_validation_images: 4
40
+ optimizer: AdamW
41
+ output_dir: SDXL_Dreambooth
42
+ output_kohya_format: false
43
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
44
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
45
+ prior_generation_precision: null
46
+ prior_loss_weight: 1.0
47
+ prodigy_beta3: null
48
+ prodigy_decouple: true
49
+ prodigy_safeguard_warmup: true
50
+ prodigy_use_bias_correction: true
51
+ push_to_hub: false
52
+ random_flip: false
53
+ rank: 4
54
+ repeats: 1
55
+ report_to: tensorboard
56
+ resolution: 1024
57
+ resume_from_checkpoint: null
58
+ revision: null
59
+ sample_batch_size: 4
60
+ scale_lr: false
61
+ seed: 0
62
+ snr_gamma: 5.0
63
+ text_encoder_lr: 5.0e-06
64
+ train_batch_size: 1
65
+ train_text_encoder: false
66
+ use_8bit_adam: true
67
+ use_dora: false
68
+ validation_epochs: 50
69
+ validation_prompt: null
70
+ variant: null
71
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1746689065.51ad53f2e985.15593.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e79d0be9fbc1b9a56e37db6a728b6a58221e79ee3d47e9b9dbbf514097cb81
3
+ size 122974
logs/dreambooth-lora-sd-xl/events.out.tfevents.1746694495.51ad53f2e985.38356.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae19932564cbd164b4775f32cfa52b80b26b340cce97f1175a796cd76928dde
3
+ size 122974
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cb6574f9a450f0987fdb604a1e28b1ced7053956e723167b5507862e7a03df1
3
+ size 23390424