End of training

README.md

@@ -0,0 +1,80 @@
+---
+base_model: stabilityai/stable-diffusion-3.5-large
+library_name: diffusers
+license: other
+instance_prompt: high quality photo of an asian jshj baby, head shot, closed eyes,
+  plain cream beanie, plain cream swaddle
+widget: []
+tags:
+- text-to-image
+- diffusers-training
+- diffusers
+- lora
+- template:sd-lora
+- sd3.5-large
+- sd3.5
+- sd3.5-diffusers
+---
+
+<!-- This model card has been generated automatically according to the information the training script had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+
+# SD3.5-Large DreamBooth LoRA - cwhuh/babyface_v1
+
+<Gallery />
+
+## Model description
+
+These are cwhuh/babyface_v1 DreamBooth LoRA weights for stabilityai/stable-diffusion-3.5-large.
+
+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).
+
+Was LoRA for the text encoder enabled? False.
+
+## Trigger words
+
+You should use `high quality photo of an asian jshj baby, head shot, closed eyes, plain cream beanie, plain cream swaddle` to trigger the image generation.
+
+## Download model
+
+[Download the *.safetensors LoRA](cwhuh/babyface_v1/tree/main) in the Files & versions tab.
+
+## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
+pipeline = AutoPipelineForText2Image.from_pretrained(stabilityai/stable-diffusion-3.5-large, torch_dtype=torch.float16).to('cuda')
+pipeline.load_lora_weights('cwhuh/babyface_v1', weight_name='pytorch_lora_weights.safetensors')
+image = pipeline('high quality photo of an asian jshj baby, head shot, closed eyes, plain cream beanie, plain cream swaddle').images[0]
+```
+
+### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
+
+- **LoRA**: download **[`diffusers_lora_weights.safetensors` here 💾](/cwhuh/babyface_v1/blob/main/diffusers_lora_weights.safetensors)**.
+    - Rename it and place it on your `models/Lora` folder.
+    - 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/).
+
+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)
+
+## License
+
+Please adhere to the licensing terms as described [here](https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/LICENSE.md).
+
+
+## Intended uses & limitations
+
+#### How to use
+
+```python
+# TODO: add an example code snippet for running this diffusion pipeline
+```
+
+#### Limitations and bias
+
+[TODO: provide examples of latent issues and potential remediations]
+
+## Training details
+
+[TODO: describe the data used to train the model]

checkpoint-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386776c8ae2faebd4d0030e25da05b8cd77d18bd0bf6947c51bd53710b9b0a30
+size 12653772

checkpoint-1000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65cff21c9e5c276b13c4444fa578564723cddf94f1301c650a27c749b9d2af0c
+size 23659664

checkpoint-1000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca8260076265ca5d27a88ef3040f6bbe784f26bf240a761c66faa8d989ae3f7
+size 14668

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14de7a0ca9221bcb27be7b54dbc3401b8afa923e562a28449420415ef9e1ed4
+size 988

checkpoint-1000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50792addf165b5b10d4e4437a6a0076612d7b074ab54188c6f711f80d3966392
+size 1000

checkpoint-1500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbe8e636867fdc0c07212435e69fb0d8cf59e9acf7a29c16a27047ae4d7fe0f
+size 12653772

checkpoint-1500/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c63a9669d353545d54c7ec3fff250cb63218b8dae241067e6c7e03414063be
+size 23659664

checkpoint-1500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f679b84be05d68f0fc79ba1b607dd0856d65db1eb45ee2cf41e580ff4c1d470c
+size 14668

checkpoint-1500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f62712217a0552c6a450d6f64ae6f9db7003147e1cc5519131c335d8354fc1
+size 988

checkpoint-1500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a908417f6e78a94c53290778cdc42f7ff1db557b7a0dad501f2c6314389d100
+size 1000

checkpoint-2000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c3908f1468e0daa33ed741fe0204d257cba9f5e4dde63b97b01d5f7b69b2e1
+size 12653772

checkpoint-2000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d45c72e38c9910c46b5a0ac317610483916d857f3f9749736679d8b605a422
+size 23659664

checkpoint-2000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7557eb29d605c098cd21814ae75c72f6334e751c72a009ad6d6b4baa2f2e13
+size 14668

checkpoint-2000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6eb017b75b764cd180f4564dd119169c0141f05c1d549ed072f872faa5df569
+size 988

checkpoint-2000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c40e0fb271d5f7ef273c15372e4b1bb468e710ee80dedfa2848d2fd36e1ac3f4
+size 1000

checkpoint-2500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70c62004eef213809a46503acd38a5cca2799a17b680dc387a1ddbec9a820d1
+size 12653772

checkpoint-2500/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86161bb3953d0d3aeec1c4b343972f1ae78e9d0e53027c042569b72ec61ab118
+size 23659664

checkpoint-2500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb08d2742907339da51c55a8d90d48aa2cd266f95ff767c417d8c3210b12806
+size 14668

checkpoint-2500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e45575ae5e96d8bb535fe9434863a29c8c22c99e6a371b791fd728807e2a220
+size 988

checkpoint-2500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566411318f9cac69dc996ce3d421e3ab620c9c06e958e4005276db51998e7e13
+size 1000

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d1d67b8a4a68ff6b5a1ccce07334a8096fc148d499735532d600a20fab6f5c
+size 12653772

checkpoint-500/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe052385042d2c313cfedc379d8bb53531c8ee404b1ab6757d1694b05544056
+size 23659664

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5191e2e5703e8919f7a5fcb85ff9da0246a58983d6997d0459e85847b1d4711
+size 14668

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
+size 988

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6780092897b2cd832212c834efe779d3edce88b63b18e17d67e5bbe3b8d19ba8
+size 1000

logs/dreambooth-sd3-lora/1737352384.094905/events.out.tfevents.1737352384.aigpu08012.2434174.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e62eb9c2643f7678e881b1552d1819755050448c4d02c1636b26a52fa7e5be
+size 3680

logs/dreambooth-sd3-lora/1737352384.1098394/hparams.yml

@@ -0,0 +1,76 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0001
+adam_weight_decay_text_encoder: 0.001
+allow_tf32: false
+cache_dir: /checkpoints/huggingface/
+cache_latents: false
+caption_column: null
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: /data/humanscape-babyface/class
+class_prompt: high quality photo of an asian baby, head shot, closed eyes, plain cream
+  beanie, plain cream swaddle
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: /data/humanscape-babyface/instance
+instance_prompt: high quality photo of an asian jshj baby, head shot, closed eyes,
+  plain cream beanie, plain cream swaddle
+learning_rate: 1.0e-06
+local_rank: 0
+logging_dir: logs
+logit_mean: 0.0
+logit_std: 1.0
+lora_blocks: null
+lora_layers: null
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: cosine_with_restarts
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_sequence_length: 77
+max_train_steps: 2500
+mixed_precision: fp16
+mode_scale: 1.29
+num_class_images: 20
+num_train_epochs: 250
+num_validation_images: 4
+optimizer: AdamW
+output_dir: babyface_v1
+precondition_outputs: 1
+pretrained_model_name_or_path: stabilityai/stable-diffusion-3.5-large
+prior_generation_precision: null
+prior_loss_weight: 0.4
+prodigy_beta3: null
+prodigy_decouple: true
+prodigy_safeguard_warmup: true
+prodigy_use_bias_correction: true
+push_to_hub: true
+random_flip: false
+rank: 4
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: latest
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+text_encoder_lr: 5.0e-06
+train_batch_size: 1
+train_text_encoder: false
+upcast_before_saving: false
+use_8bit_adam: true
+validation_epochs: 50
+validation_prompt: null
+variant: null
+weighting_scheme: logit_normal
+with_prior_preservation: true

logs/dreambooth-sd3-lora/1737352717.1932657/events.out.tfevents.1737352717.aigpu08012.2457521.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98cd03adc9762880f9626838474b64d9fa225c8d003d2e52fda0f820481934f2
+size 3616

logs/dreambooth-sd3-lora/1737352717.2039165/hparams.yml

@@ -0,0 +1,76 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.0001
+adam_weight_decay_text_encoder: 0.001
+allow_tf32: false
+cache_dir: /checkpoints/huggingface/
+cache_latents: false
+caption_column: null
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: /data/humanscape-babyface/class
+class_prompt: high quality photo of an asian baby, head shot, closed eyes, plain cream
+  beanie, plain cream swaddle
+dataloader_num_workers: 0
+dataset_config_name: null
+dataset_name: null
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+hub_model_id: null
+hub_token: null
+image_column: image
+instance_data_dir: /data/humanscape-babyface/instance
+instance_prompt: high quality photo of an asian jshj baby, head shot, closed eyes,
+  plain cream beanie, plain cream swaddle
+learning_rate: 1.0e-06
+local_rank: 0
+logging_dir: logs
+logit_mean: 0.0
+logit_std: 1.0
+lora_blocks: null
+lora_layers: null
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: cosine_with_restarts
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_sequence_length: 77
+max_train_steps: 2500
+mixed_precision: fp16
+mode_scale: 1.29
+num_class_images: 20
+num_train_epochs: 250
+num_validation_images: 4
+optimizer: AdamW
+output_dir: babyface_v1
+precondition_outputs: 1
+pretrained_model_name_or_path: stabilityai/stable-diffusion-3.5-large
+prior_generation_precision: null
+prior_loss_weight: 0.4
+prodigy_beta3: null
+prodigy_decouple: true
+prodigy_safeguard_warmup: true
+prodigy_use_bias_correction: true
+push_to_hub: true
+random_flip: false
+rank: 4
+repeats: 1
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+text_encoder_lr: 5.0e-06
+train_batch_size: 1
+train_text_encoder: false
+upcast_before_saving: false
+use_8bit_adam: true
+validation_epochs: 50
+validation_prompt: null
+variant: null
+weighting_scheme: logit_normal
+with_prior_preservation: true

logs/dreambooth-sd3-lora/events.out.tfevents.1737352384.aigpu08012.2434174.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa66ddfd752081df3f25868e6e59e5bb538f3f9e9448eb88b6430b476c1b75ad
+size 88

logs/dreambooth-sd3-lora/events.out.tfevents.1737352717.aigpu08012.2457521.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f71e2d085e6ae8338e5980a837271f4f8ed63e776b6e2c939e739f5e5d750d
+size 209834

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94336e6df89beea3d850de2c507c1fd01cc14dea38c3707b57e3c02f24244892
+size 11868760