vibber commited on
Commit
55157c0
1 Parent(s): e6600fd

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,14 @@ 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
37
+ image-1.png filter=lfs diff=lfs merge=lfs -text
38
+ image-10.png filter=lfs diff=lfs merge=lfs -text
39
+ image-2.png filter=lfs diff=lfs merge=lfs -text
40
+ image-3.png filter=lfs diff=lfs merge=lfs -text
41
+ image-4.png filter=lfs diff=lfs merge=lfs -text
42
+ image-5.png filter=lfs diff=lfs merge=lfs -text
43
+ image-6.png filter=lfs diff=lfs merge=lfs -text
44
+ image-7.png filter=lfs diff=lfs merge=lfs -text
45
+ image-8.png filter=lfs diff=lfs merge=lfs -text
46
+ image-9.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - text: in the style of <s0><s1>
11
+ output:
12
+ url: image-0.png
13
+ - text: in the style of <s0><s1>
14
+ output:
15
+ url: image-1.png
16
+ - text: in the style of <s0><s1>
17
+ output:
18
+ url: image-2.png
19
+ - text: in the style of <s0><s1>
20
+ output:
21
+ url: image-3.png
22
+ - text: in the style of <s0><s1>
23
+ output:
24
+ url: image-4.png
25
+ - text: in the style of <s0><s1>
26
+ output:
27
+ url: image-5.png
28
+ - text: in the style of <s0><s1>
29
+ output:
30
+ url: image-6.png
31
+ - text: in the style of <s0><s1>
32
+ output:
33
+ url: image-7.png
34
+ - text: in the style of <s0><s1>
35
+ output:
36
+ url: image-8.png
37
+ - text: in the style of <s0><s1>
38
+ output:
39
+ url: image-9.png
40
+ - text: in the style of <s0><s1>
41
+ output:
42
+ url: image-10.png
43
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
44
+ instance_prompt: in the style of <s0><s1>
45
+ license: openrail++
46
+ ---
47
+
48
+ # SDXL LoRA DreamBooth - vibber/decim8
49
+
50
+ <Gallery />
51
+
52
+ ## Model description
53
+
54
+ ### These are vibber/decim8 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
55
+
56
+ ## Download model
57
+
58
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
59
+
60
+ - **LoRA**: download **[`decim8.safetensors` here 💾](/vibber/decim8/blob/main/decim8.safetensors)**.
61
+ - Place it on your `models/Lora` folder.
62
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:decim8:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
63
+ - *Embeddings*: download **[`decim8_emb.safetensors` here 💾](/vibber/decim8/blob/main/decim8_emb.safetensors)**.
64
+ - Place it on it on your `embeddings` folder
65
+ - Use it by adding `decim8_emb` to your prompt. For example, `in the style of decim8_emb`
66
+ (you need both the LoRA and the embeddings as they were trained together for this LoRA)
67
+
68
+
69
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
70
+
71
+ ```py
72
+ from diffusers import AutoPipelineForText2Image
73
+ import torch
74
+ from huggingface_hub import hf_hub_download
75
+ from safetensors.torch import load_file
76
+
77
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
78
+ pipeline.load_lora_weights('vibber/decim8', weight_name='pytorch_lora_weights.safetensors')
79
+ embedding_path = hf_hub_download(repo_id='vibber/decim8', filename='decim8_emb.safetensors' repo_type="model")
80
+ state_dict = load_file(embedding_path)
81
+ pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
82
+ pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
83
+
84
+ image = pipeline('in the style of <s0><s1>').images[0]
85
+ ```
86
+
87
+ 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)
88
+
89
+ ## Trigger words
90
+
91
+ To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
92
+
93
+ to trigger concept `TOK` → use `<s0><s1>` in your prompt
94
+
95
+
96
+
97
+ ## Details
98
+ All [Files & versions](/vibber/decim8/tree/main).
99
+
100
+ 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).
101
+
102
+ LoRA for the text encoder was enabled. False.
103
+
104
+ Pivotal tuning was enabled: True.
105
+
106
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
107
+
decim8.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc788bd7f070665e92a8b7795a7bd89e8ff222c48ae771da06d6eb2a744c09f1
3
+ size 186046568
decim8_emb.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff73f54e3d5fa235d72f1b130f98d39b9b76a7c6e5e6fbfc2c04caab7ce67135
3
+ size 16536
image-0.png ADDED

Git LFS Details

  • SHA256: 2f3815bbf504c808eb2dc0e543655c4355981f066d40f8897d18334ad3869c74
  • Pointer size: 132 Bytes
  • Size of remote file: 1.96 MB
image-1.png ADDED

Git LFS Details

  • SHA256: 9ca36842f046c6d3def8e30897c7243055ce4c7296f115a2ba09746b40c10123
  • Pointer size: 132 Bytes
  • Size of remote file: 1.94 MB
image-10.png ADDED

Git LFS Details

  • SHA256: b3d4900ac4e8968167042083e97ef2ad66e6714f7ddb78f87ca4bc2b0ed787f2
  • Pointer size: 132 Bytes
  • Size of remote file: 1.68 MB
image-2.png ADDED

Git LFS Details

  • SHA256: 167fb5d93ecbeb9570cbd4679183ae76b842a9f5c7ee42e002da7766f186e31b
  • Pointer size: 132 Bytes
  • Size of remote file: 1.79 MB
image-3.png ADDED

Git LFS Details

  • SHA256: f25c8ec6b9c006582988319827cbe5986306b75ef06b256b7541e628be02eb8f
  • Pointer size: 132 Bytes
  • Size of remote file: 1.86 MB
image-4.png ADDED

Git LFS Details

  • SHA256: 6577c8b839b69e8a8e213a78e0ad724b63519bd0091a845c20557d36e922c746
  • Pointer size: 132 Bytes
  • Size of remote file: 1.6 MB
image-5.png ADDED

Git LFS Details

  • SHA256: 6adc7aead0942e8f53746e7ea9c653ae9e19e76b45f4bfd4b439e2755ca08e76
  • Pointer size: 132 Bytes
  • Size of remote file: 1.7 MB
image-6.png ADDED

Git LFS Details

  • SHA256: ea6121c062fcef60cb059b037cc6bfd7503a4b29ab7f63170752aa2c54f065d9
  • Pointer size: 132 Bytes
  • Size of remote file: 1.93 MB
image-7.png ADDED

Git LFS Details

  • SHA256: 6d27acf8ca3f494cab09112bb47e8409e5d0448561fa4edf76e0ca62026fac54
  • Pointer size: 132 Bytes
  • Size of remote file: 1.83 MB
image-8.png ADDED

Git LFS Details

  • SHA256: a34dcdea75f83b8e6df817025a6200862c5462785e6316f06fadde2ff34033c7
  • Pointer size: 132 Bytes
  • Size of remote file: 1.89 MB
image-9.png ADDED

Git LFS Details

  • SHA256: 1c43d6e6a0c4145a6ef821b9a3879e44d59a941495d39aeae735d6271edf0851
  • Pointer size: 132 Bytes
  • Size of remote file: 1.74 MB
logs/dreambooth-lora-sd-xl/1710850242.4533927/events.out.tfevents.1710850242.r-vibber-autotrain-decim8-8suq8u8c-1dde3-zedxr.177.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a3cddf34c0ac571d5f62a78f9afa077c7afbec109d7016b332ebc2b17598bc3
3
+ size 3569
logs/dreambooth-lora-sd-xl/1710850242.454653/hparams.yml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: true
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 100000
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: ./1c00269e-d446-46e7-99b6-d398be8ab99a
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: 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: 1500
37
+ mixed_precision: bf16
38
+ noise_offset: 0
39
+ num_class_images: 100
40
+ num_new_tokens_per_abstraction: 2
41
+ num_train_epochs: 137
42
+ num_validation_images: 4
43
+ optimizer: prodigy
44
+ output_dir: decim8
45
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
46
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
47
+ prior_generation_precision: null
48
+ prior_loss_weight: 1.0
49
+ prodigy_beta3: null
50
+ prodigy_decouple: true
51
+ prodigy_safeguard_warmup: true
52
+ prodigy_use_bias_correction: true
53
+ push_to_hub: false
54
+ rank: 32
55
+ repeats: 2
56
+ report_to: tensorboard
57
+ resolution: 1024
58
+ resume_from_checkpoint: null
59
+ revision: null
60
+ sample_batch_size: 4
61
+ scale_lr: false
62
+ seed: 42
63
+ snr_gamma: null
64
+ text_encoder_lr: 1.0
65
+ token_abstraction: TOK
66
+ train_batch_size: 2
67
+ train_text_encoder: false
68
+ train_text_encoder_frac: 1.0
69
+ train_text_encoder_ti: true
70
+ train_text_encoder_ti_frac: 0.5
71
+ use_8bit_adam: false
72
+ validation_epochs: 50
73
+ validation_prompt: null
74
+ variant: null
75
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1710850242.r-vibber-autotrain-decim8-8suq8u8c-1dde3-zedxr.177.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01cb3ba9046e6a58c4e4ff846be63029e29d2556a31b541d2f0ca3bcc12f2839
3
+ size 125834
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15ba82678987c23961883d8de3a1a2083d9b1723d063c89d70d548dac8ab00f
3
+ size 185963768