Kvisten commited on
Commit
f166157
·
verified ·
1 Parent(s): 000135e

End of training

Browse files
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - lora
10
+ - sd3
11
+ - sd3-diffusers
12
+ - template:sd-lora
13
+ instance_prompt: photo of a nobcap can
14
+ widget: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+
21
+ # SD3 DreamBooth LoRA - Kvisten/output
22
+
23
+ <Gallery />
24
+
25
+ ## Model description
26
+
27
+ These are Kvisten/output DreamBooth LoRA weights for stabilityai/stable-diffusion-3-medium-diffusers.
28
+
29
+ The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [SD3 diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sd3.md).
30
+
31
+ Was LoRA for the text encoder enabled? True.
32
+
33
+ ## Trigger words
34
+
35
+ You should use `photo of a nobcap can` to trigger the image generation.
36
+
37
+ ## Download model
38
+
39
+ [Download the *.safetensors LoRA](Kvisten/output/tree/main) in the Files & versions tab.
40
+
41
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
42
+
43
+ ```py
44
+ from diffusers import AutoPipelineForText2Image
45
+ import torch
46
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-3-medium-diffusers', torch_dtype=torch.float16).to('cuda')
47
+ pipeline.load_lora_weights('Kvisten/output', weight_name='pytorch_lora_weights.safetensors')
48
+ image = pipeline('photo of a nobcap can').images[0]
49
+ ```
50
+
51
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
52
+
53
+ - **LoRA**: download **[`diffusers_lora_weights.safetensors` here 💾](/Kvisten/output/blob/main/diffusers_lora_weights.safetensors)**.
54
+ - Rename it and place it on your `models/Lora` folder.
55
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:your_new_name:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
56
+
57
+ 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)
58
+
59
+ ## License
60
+
61
+ Please adhere to the licensing terms as described [here](https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/LICENSE).
62
+
63
+
64
+ ## Intended uses & limitations
65
+
66
+ #### How to use
67
+
68
+ ```python
69
+ # TODO: add an example code snippet for running this diffusion pipeline
70
+ ```
71
+
72
+ #### Limitations and bias
73
+
74
+ [TODO: provide examples of latent issues and potential remediations]
75
+
76
+ ## Training details
77
+
78
+ [TODO: describe the data used to train the model]
checkpoint-200/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dbb00c2f93a66099fd3ba739c1e493b623cc6f627f668c095975ed1fd976edd
3
+ size 7920596
checkpoint-200/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ed9b6ee9c24574454db032c4f5a1bd601fa3f8f36eb4d272dc1890a5f36c48
3
+ size 10021856
checkpoint-200/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a860c51fe521f3e89be0b4113a5543769d6cd30453d3ac643dd53bc90fc86831
3
+ size 14408
checkpoint-200/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6630fdd0e418c253e3be417ff02e57b63286957556959cd63a300eee4bfb6eed
3
+ size 988
checkpoint-200/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef496abc54de24fc4df160c5b89364117193581875909d735f4509fbe589968
3
+ size 1064
checkpoint-400/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20119bd6800a0c0e802a6403af5eace3145740a9ebe2a2acb0eb6079bf41ea9f
3
+ size 7921108
checkpoint-400/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931b500e3698cc03a8112e818ae80ad5d7c537c3ab7b69cf2f7b4cff702945ce
3
+ size 10021856
checkpoint-400/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0cb7683b232830128d950caccb8ae3bd8b2bff49dad1fbd8c7859aae9e14f0d
3
+ size 14408
checkpoint-400/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69721b7c3030b92742c20b83f2de9f4cc0f6329b7a45ca043434f7cc147bae1e
3
+ size 988
checkpoint-400/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec78f2e61deab06b2c3522bea5fa3eefa870bca6f31f33a60849a35665c628f
3
+ size 1064
checkpoint-600/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e8714575588a46e81aff98d18b77c24dfe797e1eb0f2040f7563c88253e281
3
+ size 7921108
checkpoint-600/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65907b84866847d06e78adbd3dceb0214e4c70cb6b838a2bcdab68d3f8d94999
3
+ size 10021856
checkpoint-600/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2089a4e5640c2bfb39c1c79e615a5c946816aed4c389d95536be6a4209b3325c
3
+ size 14408
checkpoint-600/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51fdae63ffd18266be53775458b57aa1d06f0fe91322fbd22a80597848b86646
3
+ size 988
checkpoint-600/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec49ce6453e72db85d36ef96ba6077c827f097a6b6b4e0cf00862890d04adfe6
3
+ size 1064
checkpoint-800/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:038a703cfa7fd454e4ecc78af3e962f3f336738d816e9f7938e0a3e9980654a6
3
+ size 7921108
checkpoint-800/pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42497fd7d2bbe82651033b3c437e52cafaba4c17189d28b83ea93b3d51e5299c
3
+ size 10021856
checkpoint-800/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:145c1ecef59f1349299d780b0b3c769e6cdd7a3f1a77b55948ed9d002d42ee9a
3
+ size 14408
checkpoint-800/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1248f9a2325721dc8581abfb32cc9c3acaca011e9090f7a1c2f60e0144bbfb3
3
+ size 988
checkpoint-800/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a735bcb69a4ffe2945f075234c946ab1390b909d3bf63f20edc472dcfc2e9e
3
+ size 1064
logs/dreambooth-sd3-lora/1726573216.3968687/events.out.tfevents.1726573216.7f503c0f795c.1999.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a4887e70a4d331659d33b84e88aa187e99ffecf4243e741347092e7640b276
3
+ size 3353
logs/dreambooth-sd3-lora/1726573216.399005/hparams.yml ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 200
11
+ checkpoints_total_limit: null
12
+ class_data_dir: /content/data/class_images
13
+ class_prompt: photo of a can
14
+ dataloader_num_workers: 0
15
+ dataset_config_name: null
16
+ dataset_name: null
17
+ gradient_accumulation_steps: 1
18
+ gradient_checkpointing: true
19
+ hub_model_id: null
20
+ hub_token: null
21
+ image_column: image
22
+ instance_data_dir: /content/data/images
23
+ instance_prompt: photo of a nobcap can
24
+ learning_rate: 2.0e-06
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_sequence_length: 77
35
+ max_train_steps: 800
36
+ mixed_precision: fp16
37
+ mode_scale: 1.29
38
+ num_class_images: 50
39
+ num_train_epochs: 16
40
+ num_validation_images: 4
41
+ optimizer: AdamW
42
+ output_dir: output
43
+ precondition_outputs: 1
44
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-3-medium-diffusers
45
+ prior_generation_precision: fp16
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: 512
57
+ resume_from_checkpoint: null
58
+ revision: null
59
+ sample_batch_size: 2
60
+ scale_lr: false
61
+ seed: 1337
62
+ text_encoder_lr: 5.0e-06
63
+ train_batch_size: 1
64
+ train_text_encoder: true
65
+ use_8bit_adam: true
66
+ validation_epochs: 50
67
+ validation_prompt: null
68
+ variant: null
69
+ weighting_scheme: logit_normal
70
+ with_prior_preservation: true
logs/dreambooth-sd3-lora/events.out.tfevents.1726573216.7f503c0f795c.1999.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c8bfdab5aa53d6f05766075e0d5775bdb83b11b98c32cf1e4bef71b88c5df3
3
+ size 67034
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693f6a221706a527e57ec681fd86542260e7111686db638359cc2afe015de99c
3
+ size 11215440