8glabs commited on
Commit
0a473b3
·
verified ·
1 Parent(s): 95aec18

End of training

Browse files
Files changed (35) hide show
  1. .gitattributes +5 -0
  2. .ipynb_checkpoints/README-checkpoint.md +81 -0
  3. .ipynb_checkpoints/image_0-checkpoint.png +3 -0
  4. .ipynb_checkpoints/image_1-checkpoint.png +3 -0
  5. .ipynb_checkpoints/image_2-checkpoint.png +3 -0
  6. .ipynb_checkpoints/image_3-checkpoint.png +3 -0
  7. 3d-icon-sdxl-lora.safetensors +3 -0
  8. 3d-icon-sdxl-lora_emb.safetensors +3 -0
  9. README.md +95 -0
  10. image_0.png +3 -0
  11. image_1.png +0 -0
  12. image_2.png +0 -0
  13. image_3.png +0 -0
  14. logs/dreambooth-lora-sd-xl/1706105322.8293128/events.out.tfevents.1706105322.5ddc25a43a24.414.1 +3 -0
  15. logs/dreambooth-lora-sd-xl/1706105322.8315356/hparams.yml +74 -0
  16. logs/dreambooth-lora-sd-xl/1706106433.6470418/events.out.tfevents.1706106433.5ddc25a43a24.259.1 +3 -0
  17. logs/dreambooth-lora-sd-xl/1706106433.64954/hparams.yml +74 -0
  18. logs/dreambooth-lora-sd-xl/1706107908.186663/events.out.tfevents.1706107908.5ddc25a43a24.449.1 +3 -0
  19. logs/dreambooth-lora-sd-xl/1706107908.188729/hparams.yml +74 -0
  20. logs/dreambooth-lora-sd-xl/1706108763.8524618/events.out.tfevents.1706108763.5ddc25a43a24.260.1 +3 -0
  21. logs/dreambooth-lora-sd-xl/1706108763.8549922/hparams.yml +74 -0
  22. logs/dreambooth-lora-sd-xl/1706109369.391219/events.out.tfevents.1706109369.5ddc25a43a24.707.1 +3 -0
  23. logs/dreambooth-lora-sd-xl/1706109369.3931785/hparams.yml +74 -0
  24. logs/dreambooth-lora-sd-xl/1706109768.2837665/events.out.tfevents.1706109768.5ddc25a43a24.1825.1 +3 -0
  25. logs/dreambooth-lora-sd-xl/1706109768.285734/hparams.yml +74 -0
  26. logs/dreambooth-lora-sd-xl/1706110683.3978927/events.out.tfevents.1706110683.5ddc25a43a24.4243.1 +3 -0
  27. logs/dreambooth-lora-sd-xl/1706110683.3999639/hparams.yml +75 -0
  28. logs/dreambooth-lora-sd-xl/events.out.tfevents.1706105322.5ddc25a43a24.414.0 +3 -0
  29. logs/dreambooth-lora-sd-xl/events.out.tfevents.1706106433.5ddc25a43a24.259.0 +3 -0
  30. logs/dreambooth-lora-sd-xl/events.out.tfevents.1706107908.5ddc25a43a24.449.0 +3 -0
  31. logs/dreambooth-lora-sd-xl/events.out.tfevents.1706108763.5ddc25a43a24.260.0 +3 -0
  32. logs/dreambooth-lora-sd-xl/events.out.tfevents.1706109369.5ddc25a43a24.707.0 +3 -0
  33. logs/dreambooth-lora-sd-xl/events.out.tfevents.1706109768.5ddc25a43a24.1825.0 +3 -0
  34. logs/dreambooth-lora-sd-xl/events.out.tfevents.1706110683.5ddc25a43a24.4243.0 +3 -0
  35. pytorch_lora_weights.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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
+ .ipynb_checkpoints/image_0-checkpoint.png filter=lfs diff=lfs merge=lfs -text
37
+ .ipynb_checkpoints/image_1-checkpoint.png filter=lfs diff=lfs merge=lfs -text
38
+ .ipynb_checkpoints/image_2-checkpoint.png filter=lfs diff=lfs merge=lfs -text
39
+ .ipynb_checkpoints/image_3-checkpoint.png filter=lfs diff=lfs merge=lfs -text
40
+ image_0.png filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - stable-diffusion-xl
4
+ - stable-diffusion-xl-diffusers
5
+ - text-to-image
6
+ - diffusers
7
+ - lora
8
+ - template:sd-lora
9
+ widget:
10
+
11
+ - text: 'a TOK icon of an astronaut riding a horse, in the style of TOK'
12
+ output:
13
+ url:
14
+ "image_0.png"
15
+
16
+ - text: 'a TOK icon of an astronaut riding a horse, in the style of TOK'
17
+ output:
18
+ url:
19
+ "image_1.png"
20
+
21
+ - text: 'a TOK icon of an astronaut riding a horse, in the style of TOK'
22
+ output:
23
+ url:
24
+ "image_2.png"
25
+
26
+ - text: 'a TOK icon of an astronaut riding a horse, in the style of TOK'
27
+ output:
28
+ url:
29
+ "image_3.png"
30
+
31
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
32
+ instance_prompt: 3d icon in the style of TOK
33
+ license: openrail++
34
+ ---
35
+
36
+ # SDXL LoRA DreamBooth - 3d-icon-sdxl-lora
37
+
38
+ <Gallery />
39
+
40
+ ## Model description
41
+
42
+ ### These are 3d-icon-sdxl-lora LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
43
+
44
+ ## Download model
45
+
46
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
47
+
48
+ - **LoRA**: download **[`3d-icon-sdxl-lora.safetensors` here 💾](/3d-icon-sdxl-lora/blob/main/3d-icon-sdxl-lora.safetensors)**.
49
+ - Place it on your `models/Lora` folder.
50
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:3d-icon-sdxl-lora:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
51
+
52
+
53
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
54
+
55
+ ```py
56
+ from diffusers import AutoPipelineForText2Image
57
+ import torch
58
+
59
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
60
+ pipeline.load_lora_weights('3d-icon-sdxl-lora', weight_name='pytorch_lora_weights.safetensors')
61
+
62
+ image = pipeline('a TOK icon of an astronaut riding a horse, in the style of TOK').images[0]
63
+ ```
64
+
65
+ For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
66
+
67
+ ## Trigger words
68
+
69
+ You should use 3d icon in the style of TOK to trigger the image generation.
70
+
71
+ ## Details
72
+ All [Files & versions](/3d-icon-sdxl-lora/tree/main).
73
+
74
+ The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).
75
+
76
+ LoRA for the text encoder was enabled. False.
77
+
78
+ Pivotal tuning was enabled: False.
79
+
80
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
81
+
.ipynb_checkpoints/image_0-checkpoint.png ADDED

Git LFS Details

  • SHA256: ec3760422020db82dbe1682a937a2e6615732314c3d5332a97c1bf2c4f70f44c
  • Pointer size: 132 Bytes
  • Size of remote file: 1.92 MB
.ipynb_checkpoints/image_1-checkpoint.png ADDED

Git LFS Details

  • SHA256: cdaf044542cf5459425fb9d37a8e27a7fb8981dd48dc696860de96a37d4349e2
  • Pointer size: 132 Bytes
  • Size of remote file: 2.2 MB
.ipynb_checkpoints/image_2-checkpoint.png ADDED

Git LFS Details

  • SHA256: 1e16bab29cb7fd89aa0164cdcd3f30860a3639468e37ded69e1bb302163920e9
  • Pointer size: 132 Bytes
  • Size of remote file: 1.76 MB
.ipynb_checkpoints/image_3-checkpoint.png ADDED

Git LFS Details

  • SHA256: 45f339aee9d9ec117d9e5cb4ad598e13ba8caadc0a933b12c433ea4489195361
  • Pointer size: 132 Bytes
  • Size of remote file: 1.69 MB
3d-icon-sdxl-lora.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d33b0b2e4e62096ac46370124cba935821cbf6e3056f0817e2772aee89da95
3
+ size 46698072
3d-icon-sdxl-lora_emb.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2154d6e0fe5ac56f0855f378391a157f652a723260322f43d73303b0d0450bb5
3
+ size 16536
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - stable-diffusion-xl
4
+ - stable-diffusion-xl-diffusers
5
+ - text-to-image
6
+ - diffusers
7
+ - lora
8
+ - template:sd-lora
9
+ widget:
10
+
11
+ - text: 'a <s0><s1> icon of an astronaut riding a horse, in the style of <s0><s1>'
12
+ output:
13
+ url:
14
+ "image_0.png"
15
+
16
+ - text: 'a <s0><s1> icon of an astronaut riding a horse, in the style of <s0><s1>'
17
+ output:
18
+ url:
19
+ "image_1.png"
20
+
21
+ - text: 'a <s0><s1> icon of an astronaut riding a horse, in the style of <s0><s1>'
22
+ output:
23
+ url:
24
+ "image_2.png"
25
+
26
+ - text: 'a <s0><s1> icon of an astronaut riding a horse, in the style of <s0><s1>'
27
+ output:
28
+ url:
29
+ "image_3.png"
30
+
31
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
32
+ instance_prompt: 3d icon in the style of <s0><s1>
33
+ license: openrail++
34
+ ---
35
+
36
+ # SDXL LoRA DreamBooth - 8glabs/3d-icon-sdxl-lora
37
+
38
+ <Gallery />
39
+
40
+ ## Model description
41
+
42
+ ### These are 8glabs/3d-icon-sdxl-lora LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
43
+
44
+ ## Download model
45
+
46
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
47
+
48
+ - **LoRA**: download **[`3d-icon-sdxl-lora.safetensors` here 💾](/8glabs/3d-icon-sdxl-lora/blob/main/3d-icon-sdxl-lora.safetensors)**.
49
+ - Place it on your `models/Lora` folder.
50
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:3d-icon-sdxl-lora:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
51
+ - *Embeddings*: download **[`3d-icon-sdxl-lora_emb.safetensors` here 💾](/8glabs/3d-icon-sdxl-lora/blob/main/3d-icon-sdxl-lora_emb.safetensors)**.
52
+ - Place it on it on your `embeddings` folder
53
+ - Use it by adding `3d-icon-sdxl-lora_emb` to your prompt. For example, `3d icon in the style of 3d-icon-sdxl-lora_emb`
54
+ (you need both the LoRA and the embeddings as they were trained together for this LoRA)
55
+
56
+
57
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
58
+
59
+ ```py
60
+ from diffusers import AutoPipelineForText2Image
61
+ import torch
62
+ from huggingface_hub import hf_hub_download
63
+ from safetensors.torch import load_file
64
+
65
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
66
+ pipeline.load_lora_weights('8glabs/3d-icon-sdxl-lora', weight_name='pytorch_lora_weights.safetensors')
67
+ embedding_path = hf_hub_download(repo_id='8glabs/3d-icon-sdxl-lora', filename='3d-icon-sdxl-lora_emb.safetensors' repo_type="model")
68
+ state_dict = load_file(embedding_path)
69
+ pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
70
+ pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
71
+
72
+ image = pipeline('a <s0><s1> icon of an astronaut riding a horse, in the style of <s0><s1>').images[0]
73
+ ```
74
+
75
+ For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
76
+
77
+ ## Trigger words
78
+
79
+ To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
80
+
81
+ to trigger concept `TOK` → use `<s0><s1>` in your prompt
82
+
83
+
84
+
85
+ ## Details
86
+ All [Files & versions](/8glabs/3d-icon-sdxl-lora/tree/main).
87
+
88
+ The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).
89
+
90
+ LoRA for the text encoder was enabled. False.
91
+
92
+ Pivotal tuning was enabled: True.
93
+
94
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
95
+
image_0.png ADDED

Git LFS Details

  • SHA256: 62ed1aa75cf026662a578687913f48625d2f8464162cb11877253433fc7fc9fe
  • Pointer size: 132 Bytes
  • Size of remote file: 1.23 MB
image_1.png ADDED
image_2.png ADDED
image_3.png ADDED
logs/dreambooth-lora-sd-xl/1706105322.8293128/events.out.tfevents.1706105322.5ddc25a43a24.414.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5651f3d7e01113c11da81495b81de452c717213008dea2ae17a63dcfc9ebfa88
3
+ size 3588
logs/dreambooth-lora-sd-xl/1706105322.8315356/hparams.yml ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ cache_latents: false
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 500
12
+ checkpoints_total_limit: null
13
+ class_data_dir: null
14
+ class_prompt: null
15
+ crops_coords_top_left_h: 0
16
+ crops_coords_top_left_w: 0
17
+ dataloader_num_workers: 0
18
+ dataset_config_name: null
19
+ dataset_name: ./3d_icon
20
+ enable_xformers_memory_efficient_attention: false
21
+ gradient_accumulation_steps: 1
22
+ gradient_checkpointing: false
23
+ hub_model_id: null
24
+ hub_token: null
25
+ image_column: image
26
+ instance_data_dir: null
27
+ instance_prompt: 3d icon in the style of TOK
28
+ learning_rate: 0.0001
29
+ local_rank: -1
30
+ logging_dir: logs
31
+ lr_num_cycles: 1
32
+ lr_power: 1.0
33
+ lr_scheduler: constant
34
+ lr_warmup_steps: 500
35
+ max_grad_norm: 1.0
36
+ max_train_steps: 8
37
+ mixed_precision: bf16
38
+ num_class_images: 100
39
+ num_new_tokens_per_abstraction: 2
40
+ num_train_epochs: 1
41
+ num_validation_images: 4
42
+ optimizer: adamW
43
+ output_dir: 3d-icon-sdxl-lora
44
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
45
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
46
+ prior_generation_precision: null
47
+ prior_loss_weight: 1.0
48
+ prodigy_beta3: null
49
+ prodigy_decouple: true
50
+ prodigy_safeguard_warmup: true
51
+ prodigy_use_bias_correction: true
52
+ push_to_hub: 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: null
62
+ snr_gamma: null
63
+ text_encoder_lr: 5.0e-06
64
+ token_abstraction: TOK
65
+ train_batch_size: 3
66
+ train_text_encoder: false
67
+ train_text_encoder_frac: 1.0
68
+ train_text_encoder_ti: false
69
+ train_text_encoder_ti_frac: 0.5
70
+ use_8bit_adam: false
71
+ validation_epochs: 50
72
+ validation_prompt: a TOK icon of an astronaut riding a horse, in the style of TOK
73
+ variant: null
74
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1706106433.6470418/events.out.tfevents.1706106433.5ddc25a43a24.259.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4813a67bbd143923b3d16bed4e22c5d8bf0c43b4b0806f6eb568e8f540848b7d
3
+ size 3588
logs/dreambooth-lora-sd-xl/1706106433.64954/hparams.yml ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ cache_latents: false
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 500
12
+ checkpoints_total_limit: null
13
+ class_data_dir: null
14
+ class_prompt: null
15
+ crops_coords_top_left_h: 0
16
+ crops_coords_top_left_w: 0
17
+ dataloader_num_workers: 0
18
+ dataset_config_name: null
19
+ dataset_name: ./3d_icon
20
+ enable_xformers_memory_efficient_attention: false
21
+ gradient_accumulation_steps: 1
22
+ gradient_checkpointing: false
23
+ hub_model_id: null
24
+ hub_token: null
25
+ image_column: image
26
+ instance_data_dir: null
27
+ instance_prompt: 3d icon in the style of TOK
28
+ learning_rate: 0.0001
29
+ local_rank: -1
30
+ logging_dir: logs
31
+ lr_num_cycles: 1
32
+ lr_power: 1.0
33
+ lr_scheduler: constant
34
+ lr_warmup_steps: 500
35
+ max_grad_norm: 1.0
36
+ max_train_steps: 8
37
+ mixed_precision: bf16
38
+ num_class_images: 100
39
+ num_new_tokens_per_abstraction: 2
40
+ num_train_epochs: 1
41
+ num_validation_images: 4
42
+ optimizer: adamW
43
+ output_dir: 3d-icon-sdxl-lora
44
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
45
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
46
+ prior_generation_precision: null
47
+ prior_loss_weight: 1.0
48
+ prodigy_beta3: null
49
+ prodigy_decouple: true
50
+ prodigy_safeguard_warmup: true
51
+ prodigy_use_bias_correction: true
52
+ push_to_hub: 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: null
62
+ snr_gamma: null
63
+ text_encoder_lr: 5.0e-06
64
+ token_abstraction: TOK
65
+ train_batch_size: 3
66
+ train_text_encoder: false
67
+ train_text_encoder_frac: 1.0
68
+ train_text_encoder_ti: false
69
+ train_text_encoder_ti_frac: 0.5
70
+ use_8bit_adam: false
71
+ validation_epochs: 50
72
+ validation_prompt: a TOK icon of an astronaut riding a horse, in the style of TOK
73
+ variant: null
74
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1706107908.186663/events.out.tfevents.1706107908.5ddc25a43a24.449.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25860cf417a0aa505681e87743a4277783fc579bbb520f09b832d79300c922e
3
+ size 3588
logs/dreambooth-lora-sd-xl/1706107908.188729/hparams.yml ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ cache_latents: false
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 500
12
+ checkpoints_total_limit: null
13
+ class_data_dir: null
14
+ class_prompt: null
15
+ crops_coords_top_left_h: 0
16
+ crops_coords_top_left_w: 0
17
+ dataloader_num_workers: 0
18
+ dataset_config_name: null
19
+ dataset_name: ./3d_icon
20
+ enable_xformers_memory_efficient_attention: false
21
+ gradient_accumulation_steps: 1
22
+ gradient_checkpointing: false
23
+ hub_model_id: null
24
+ hub_token: null
25
+ image_column: image
26
+ instance_data_dir: null
27
+ instance_prompt: 3d icon in the style of TOK
28
+ learning_rate: 0.0001
29
+ local_rank: -1
30
+ logging_dir: logs
31
+ lr_num_cycles: 1
32
+ lr_power: 1.0
33
+ lr_scheduler: constant
34
+ lr_warmup_steps: 500
35
+ max_grad_norm: 1.0
36
+ max_train_steps: 8
37
+ mixed_precision: bf16
38
+ num_class_images: 100
39
+ num_new_tokens_per_abstraction: 2
40
+ num_train_epochs: 1
41
+ num_validation_images: 4
42
+ optimizer: adamW
43
+ output_dir: 3d-icon-sdxl-lora
44
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
45
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
46
+ prior_generation_precision: null
47
+ prior_loss_weight: 1.0
48
+ prodigy_beta3: null
49
+ prodigy_decouple: true
50
+ prodigy_safeguard_warmup: true
51
+ prodigy_use_bias_correction: true
52
+ push_to_hub: 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: null
62
+ snr_gamma: null
63
+ text_encoder_lr: 5.0e-06
64
+ token_abstraction: TOK
65
+ train_batch_size: 3
66
+ train_text_encoder: false
67
+ train_text_encoder_frac: 1.0
68
+ train_text_encoder_ti: false
69
+ train_text_encoder_ti_frac: 0.5
70
+ use_8bit_adam: false
71
+ validation_epochs: 50
72
+ validation_prompt: a TOK icon of an astronaut riding a horse, in the style of TOK
73
+ variant: null
74
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1706108763.8524618/events.out.tfevents.1706108763.5ddc25a43a24.260.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3efc571bc43ecb51509652a76ecd696f8e08eb9b79d98c990733613e8191b30
3
+ size 3588
logs/dreambooth-lora-sd-xl/1706108763.8549922/hparams.yml ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ cache_latents: false
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 500
12
+ checkpoints_total_limit: null
13
+ class_data_dir: null
14
+ class_prompt: null
15
+ crops_coords_top_left_h: 0
16
+ crops_coords_top_left_w: 0
17
+ dataloader_num_workers: 0
18
+ dataset_config_name: null
19
+ dataset_name: ./3d_icon
20
+ enable_xformers_memory_efficient_attention: false
21
+ gradient_accumulation_steps: 1
22
+ gradient_checkpointing: false
23
+ hub_model_id: null
24
+ hub_token: null
25
+ image_column: image
26
+ instance_data_dir: null
27
+ instance_prompt: 3d icon in the style of TOK
28
+ learning_rate: 0.0001
29
+ local_rank: -1
30
+ logging_dir: logs
31
+ lr_num_cycles: 1
32
+ lr_power: 1.0
33
+ lr_scheduler: constant
34
+ lr_warmup_steps: 500
35
+ max_grad_norm: 1.0
36
+ max_train_steps: 8
37
+ mixed_precision: bf16
38
+ num_class_images: 100
39
+ num_new_tokens_per_abstraction: 2
40
+ num_train_epochs: 1
41
+ num_validation_images: 4
42
+ optimizer: adamW
43
+ output_dir: 3d-icon-sdxl-lora
44
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
45
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
46
+ prior_generation_precision: null
47
+ prior_loss_weight: 1.0
48
+ prodigy_beta3: null
49
+ prodigy_decouple: true
50
+ prodigy_safeguard_warmup: true
51
+ prodigy_use_bias_correction: true
52
+ push_to_hub: 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: null
62
+ snr_gamma: null
63
+ text_encoder_lr: 5.0e-06
64
+ token_abstraction: TOK
65
+ train_batch_size: 3
66
+ train_text_encoder: false
67
+ train_text_encoder_frac: 1.0
68
+ train_text_encoder_ti: false
69
+ train_text_encoder_ti_frac: 0.5
70
+ use_8bit_adam: false
71
+ validation_epochs: 50
72
+ validation_prompt: a TOK icon of an astronaut riding a horse, in the style of TOK
73
+ variant: null
74
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1706109369.391219/events.out.tfevents.1706109369.5ddc25a43a24.707.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15a970ff71f1473c56e925343aa36a06f76fec0b8f6b40a18722e720c144e39
3
+ size 3588
logs/dreambooth-lora-sd-xl/1706109369.3931785/hparams.yml ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ cache_latents: false
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 500
12
+ checkpoints_total_limit: null
13
+ class_data_dir: null
14
+ class_prompt: null
15
+ crops_coords_top_left_h: 0
16
+ crops_coords_top_left_w: 0
17
+ dataloader_num_workers: 0
18
+ dataset_config_name: null
19
+ dataset_name: ./3d_icon
20
+ enable_xformers_memory_efficient_attention: false
21
+ gradient_accumulation_steps: 1
22
+ gradient_checkpointing: false
23
+ hub_model_id: null
24
+ hub_token: null
25
+ image_column: image
26
+ instance_data_dir: null
27
+ instance_prompt: 3d icon in the style of TOK
28
+ learning_rate: 0.0001
29
+ local_rank: -1
30
+ logging_dir: logs
31
+ lr_num_cycles: 1
32
+ lr_power: 1.0
33
+ lr_scheduler: constant
34
+ lr_warmup_steps: 500
35
+ max_grad_norm: 1.0
36
+ max_train_steps: 8
37
+ mixed_precision: bf16
38
+ num_class_images: 100
39
+ num_new_tokens_per_abstraction: 2
40
+ num_train_epochs: 1
41
+ num_validation_images: 4
42
+ optimizer: adamW
43
+ output_dir: 3d-icon-sdxl-lora
44
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
45
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
46
+ prior_generation_precision: null
47
+ prior_loss_weight: 1.0
48
+ prodigy_beta3: null
49
+ prodigy_decouple: true
50
+ prodigy_safeguard_warmup: true
51
+ prodigy_use_bias_correction: true
52
+ push_to_hub: 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: null
62
+ snr_gamma: null
63
+ text_encoder_lr: 5.0e-06
64
+ token_abstraction: TOK
65
+ train_batch_size: 3
66
+ train_text_encoder: false
67
+ train_text_encoder_frac: 1.0
68
+ train_text_encoder_ti: false
69
+ train_text_encoder_ti_frac: 0.5
70
+ use_8bit_adam: false
71
+ validation_epochs: 50
72
+ validation_prompt: a TOK icon of an astronaut riding a horse, in the style of TOK
73
+ variant: null
74
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1706109768.2837665/events.out.tfevents.1706109768.5ddc25a43a24.1825.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:897b258ff9733e9d2738b6546293b224b4f1ffdcc4b5abc5b93db18a7a28b5d8
3
+ size 3588
logs/dreambooth-lora-sd-xl/1706109768.285734/hparams.yml ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: null
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ cache_latents: false
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 500
12
+ checkpoints_total_limit: null
13
+ class_data_dir: null
14
+ class_prompt: null
15
+ crops_coords_top_left_h: 0
16
+ crops_coords_top_left_w: 0
17
+ dataloader_num_workers: 0
18
+ dataset_config_name: null
19
+ dataset_name: ./3d_icon
20
+ enable_xformers_memory_efficient_attention: false
21
+ gradient_accumulation_steps: 1
22
+ gradient_checkpointing: false
23
+ hub_model_id: null
24
+ hub_token: null
25
+ image_column: image
26
+ instance_data_dir: null
27
+ instance_prompt: 3d icon in the style of TOK
28
+ learning_rate: 0.0001
29
+ local_rank: -1
30
+ logging_dir: logs
31
+ lr_num_cycles: 1
32
+ lr_power: 1.0
33
+ lr_scheduler: constant
34
+ lr_warmup_steps: 500
35
+ max_grad_norm: 1.0
36
+ max_train_steps: 8
37
+ mixed_precision: bf16
38
+ num_class_images: 100
39
+ num_new_tokens_per_abstraction: 2
40
+ num_train_epochs: 1
41
+ num_validation_images: 4
42
+ optimizer: adamW
43
+ output_dir: 3d-icon-sdxl-lora
44
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
45
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
46
+ prior_generation_precision: null
47
+ prior_loss_weight: 1.0
48
+ prodigy_beta3: null
49
+ prodigy_decouple: true
50
+ prodigy_safeguard_warmup: true
51
+ prodigy_use_bias_correction: true
52
+ push_to_hub: 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: null
62
+ snr_gamma: null
63
+ text_encoder_lr: 5.0e-06
64
+ token_abstraction: TOK
65
+ train_batch_size: 3
66
+ train_text_encoder: false
67
+ train_text_encoder_frac: 1.0
68
+ train_text_encoder_ti: false
69
+ train_text_encoder_ti_frac: 0.5
70
+ use_8bit_adam: false
71
+ validation_epochs: 50
72
+ validation_prompt: a TOK icon of an astronaut riding a horse, in the style of TOK
73
+ variant: null
74
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/1706110683.3978927/events.out.tfevents.1706110683.5ddc25a43a24.4243.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6045ee6ab44dac0bf71b7cd82464472d8cfffd1088753e5a2941520cd333c0cd
3
+ size 3673
logs/dreambooth-lora-sd-xl/1706110683.3999639/hparams.yml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.99
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: null
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ cache_latents: false
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 2000
12
+ checkpoints_total_limit: null
13
+ class_data_dir: null
14
+ class_prompt: null
15
+ crops_coords_top_left_h: 0
16
+ crops_coords_top_left_w: 0
17
+ dataloader_num_workers: 0
18
+ dataset_config_name: null
19
+ dataset_name: ./3d_icon
20
+ enable_xformers_memory_efficient_attention: false
21
+ gradient_accumulation_steps: 1
22
+ gradient_checkpointing: true
23
+ hub_model_id: null
24
+ hub_token: null
25
+ image_column: image
26
+ instance_data_dir: null
27
+ instance_prompt: 3d icon in the style of <s0><s1>
28
+ learning_rate: 1.0
29
+ local_rank: -1
30
+ logging_dir: logs
31
+ lr_num_cycles: 1
32
+ lr_power: 1.0
33
+ lr_scheduler: constant
34
+ lr_warmup_steps: 0
35
+ max_grad_norm: 1.0
36
+ max_train_steps: 1000
37
+ mixed_precision: bf16
38
+ num_class_images: 100
39
+ num_new_tokens_per_abstraction: 2
40
+ num_train_epochs: 125
41
+ num_validation_images: 4
42
+ optimizer: prodigy
43
+ output_dir: 3d-icon-sdxl-lora
44
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
45
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
46
+ prior_generation_precision: null
47
+ prior_loss_weight: 1.0
48
+ prodigy_beta3: null
49
+ prodigy_decouple: true
50
+ prodigy_safeguard_warmup: true
51
+ prodigy_use_bias_correction: true
52
+ push_to_hub: true
53
+ rank: 8
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: 1.0
64
+ token_abstraction: TOK
65
+ train_batch_size: 3
66
+ train_text_encoder: false
67
+ train_text_encoder_frac: 1.0
68
+ train_text_encoder_ti: true
69
+ train_text_encoder_ti_frac: 0.5
70
+ use_8bit_adam: false
71
+ validation_epochs: 50
72
+ validation_prompt: a <s0><s1> icon of an astronaut riding a horse, in the style of
73
+ <s0><s1>
74
+ variant: null
75
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1706105322.5ddc25a43a24.414.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82cf269072e74152a11298564cf6fda7517925667c04f81aafc4aa70b84ce385
3
+ size 6410984
logs/dreambooth-lora-sd-xl/events.out.tfevents.1706106433.5ddc25a43a24.259.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b334cf91cc2b5d1d80e91423c0e54ffcb488fdd70243c432337d2f96205ab41b
3
+ size 15254123
logs/dreambooth-lora-sd-xl/events.out.tfevents.1706107908.5ddc25a43a24.449.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea00b0843d76762167b1b88964c822cc24efc9693df16ec26c16c280f2377187
3
+ size 88
logs/dreambooth-lora-sd-xl/events.out.tfevents.1706108763.5ddc25a43a24.260.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c242f62f5594100bcde52288a9c2e0119acc4d66e74b5b44a721bb5500b450aa
3
+ size 14462560
logs/dreambooth-lora-sd-xl/events.out.tfevents.1706109369.5ddc25a43a24.707.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b744fb564f229734ddbf10f89c97afc9504d90620f13894a1a1309707fb1657
3
+ size 14475404
logs/dreambooth-lora-sd-xl/events.out.tfevents.1706109768.5ddc25a43a24.1825.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766a61fd248182b14a6463e03fd8ff450ee0181e3b7ec3f69fad1eb66b01a533
3
+ size 13448259
logs/dreambooth-lora-sd-xl/events.out.tfevents.1706110683.5ddc25a43a24.4243.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551aa121581ee9499d0f303f4451bed5ba5311a959b7fd2775f72dd22ced8543
3
+ size 18246102
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bf5c500155c9f01f46e1991169d405c596acfc028d2ccf272ec7fce14e7055
3
+ size 46615272