naveennagar0909 commited on
Commit
4053e60
·
verified ·
1 Parent(s): 894e89c

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: segmind/SSD-1B
3
+ library_name: diffusers
4
+ license: openrail++
5
+ instance_prompt: a photo of sks coke
6
+ widget:
7
+ - text: A photo of sks coke on a mountain
8
+ output:
9
+ url: image_0.png
10
+ tags:
11
+ - text-to-image
12
+ - text-to-image
13
+ - diffusers-training
14
+ - diffusers
15
+ - lora
16
+ - template:sd-lora
17
+ - stable-diffusion-xl
18
+ - stable-diffusion-xl-diffusers
19
+ ---
20
+
21
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
22
+ should probably proofread and complete it, then remove this comment. -->
23
+
24
+
25
+ # SDXL LoRA DreamBooth - naveennagar0909/lora-coke-SSD-1B
26
+
27
+ <Gallery />
28
+
29
+ ## Model description
30
+
31
+ These are naveennagar0909/lora-coke-SSD-1B LoRA adaption weights for segmind/SSD-1B.
32
+
33
+ The weights were trained using [DreamBooth](https://dreambooth.github.io/).
34
+
35
+ LoRA for the text encoder was enabled: False.
36
+
37
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
38
+
39
+ ## Trigger words
40
+
41
+ You should use a photo of sks coke to trigger the image generation.
42
+
43
+ ## Download model
44
+
45
+ Weights for this model are available in Safetensors format.
46
+
47
+ [Download](naveennagar0909/lora-coke-SSD-1B/tree/main) them in the Files & versions tab.
48
+
49
+
50
+
51
+ ## Intended uses & limitations
52
+
53
+ #### How to use
54
+
55
+ ```python
56
+ # TODO: add an example code snippet for running this diffusion pipeline
57
+ ```
58
+
59
+ #### Limitations and bias
60
+
61
+ [TODO: provide examples of latent issues and potential remediations]
62
+
63
+ ## Training details
64
+
65
+ [TODO: describe the data used to train the model]
image_0.png ADDED

Git LFS Details

  • SHA256: 79eca60e5f8afe5d4fdeed9f4745b0a375586cabaae6891c7ea4b7e4dd3aa352
  • Pointer size: 132 Bytes
  • Size of remote file: 1.54 MB
logs/dreambooth-lora-sd-xl/1746018540.642145/events.out.tfevents.1746018540.3397260b9ea6.21648.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca123d0aef5fd19f017baa2deb7435cb2d945707a64f468bb3a3337b79b5034
3
+ size 3350
logs/dreambooth-lora-sd-xl/1746018540.6451545/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: null
9
+ center_crop: true
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
+ do_edm_style_training: false
18
+ enable_xformers_memory_efficient_attention: false
19
+ gradient_accumulation_steps: 2
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: coke_can
26
+ instance_prompt: a photo of sks coke
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: 200
36
+ mixed_precision: fp16
37
+ num_class_images: 100
38
+ num_train_epochs: 50
39
+ num_validation_images: 1
40
+ optimizer: AdamW
41
+ output_dir: lora-coke-SSD-1B
42
+ output_kohya_format: false
43
+ pretrained_model_name_or_path: segmind/SSD-1B
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: true
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: null
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: 300
69
+ validation_prompt: A photo of sks coke on a mountain
70
+ variant: null
71
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1746018540.3397260b9ea6.21648.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f1a03e84a0082aeb4da0db7b7991dec7aa2d9386049e090107d7379e8e89bf
3
+ size 3185012
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d40f2f9eb3fd35593a1f375004bf00a1c01132f5e3646682772dac69258a95b
3
+ size 10910072