End of training

README.md

@@ -0,0 +1,79 @@
+---
+base_model: stabilityai/stable-diffusion-3.5-large
+library_name: diffusers
+license: other
+instance_prompt: jshj 3d ultrasound image of baby face, headshot
+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/v4_sd35large_reconstruction
+
+<Gallery />
+
+## Model description
+
+These are cwhuh/v4_sd35large_reconstruction 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 `jshj 3d ultrasound image of baby face, headshot` to trigger the image generation.
+
+## Download model
+
+[Download the *.safetensors LoRA](cwhuh/v4_sd35large_reconstruction/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/v4_sd35large_reconstruction', weight_name='pytorch_lora_weights.safetensors')
+image = pipeline('jshj 3d ultrasound image of baby face, headshot').images[0]
+```
+
+### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
+
+- **LoRA**: download **[`diffusers_lora_weights.safetensors` here 💾](/cwhuh/v4_sd35large_reconstruction/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-3000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72f3a1fc19a3ec30ba916f3470a17ef1b14ef4baf2c408ef1ec0122e8545f0f
+size 12653772

checkpoint-3000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1be6bc996f439e22b07a9da1293c0520924f53602955dfd86faf2f1e36cb26
+size 23659664

checkpoint-3000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bbf5aa5df7ca2a46533f206ebf45412c1366a8b6cd25b90ef604eb11b984e5
+size 14604

checkpoint-3000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5291be7d8726e5411b4ac39d2502198bc13709cd96b0a6eb8dde2179ad2d3f52
+size 988

checkpoint-3000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be4ef6ed37e12e328c106df1145df7b9f8dea90bbcbe6eb3ff6a700d290e19d
+size 1000

checkpoint-3500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996b40ed0c04b070afb3721a2a314a93b41400848bb32e905526fffa696b8fce
+size 12653772

checkpoint-3500/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ae33403a8a8ed07f9fc899dc0cc3c818568b05c68badee2715efcb79190e13
+size 23659664

checkpoint-3500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c774d9ba76d0721c5e496faac95c3e1ee29234bbb1ca46da0d03451195354b3e
+size 14604

checkpoint-3500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb913706215ccc9d9ccf4fc0f14a4c20e4a18dd92591503d729182f3e36ce2d
+size 988

checkpoint-3500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed28e749e4028a2d95f32c19375d1420796464dc9bf62be3663471b1abf91d89
+size 1000

checkpoint-4000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d2d738fa5f9a72cb9a0be1c86ca98a3347a756972fdeedf059da65e97ad497
+size 12653772

checkpoint-4000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d4fddf123d99f8c1ae621d28464a60a190170530d857a472f6faf15939c9da
+size 23659664

checkpoint-4000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb38f0bd75770c4a3015ae0c73cc3d859b8ced311cd6f8430a8753e32e3babff
+size 14604

checkpoint-4000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c53add6cfd5f8f4527aacff574391604f848d41d090a750ad63d3f7460f146d8
+size 988

checkpoint-4000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078acbbbca635109b6445084e59035558d27595f52b1b054a746c5b6864d154d
+size 1000

checkpoint-4500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df46a1b1aa1ce815a73ee9425cc11592a66fa23c0574f433b6a70fc3483279f6
+size 12653772

checkpoint-4500/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e3594430008a086d22ff0435e258f818485162d4443af7a96e2f3b0c923775
+size 23659664

checkpoint-4500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707bdf7b0eb1cc2bec43265b7d0f9315e2513b7f9b6d331ad6aaee293b5c85b9
+size 14604

checkpoint-4500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc94d591ddd9fe77a205fddf5e0e46b295cc74374d5284fcd7e8f6e5cf1c97d5
+size 988

checkpoint-4500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8ccce061cf6bb006ffdc7854f920837a7450621b21697275f4ac036cb0cce7
+size 1000

checkpoint-5000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080b0917d96d8f34790791fa1ea168450e3883a39c08ea0f0af5e99968ac7c93
+size 12653772

checkpoint-5000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8142e2828adb0104b195654591200364b449ccc5c549479c605804bc9d7e2f8
+size 23659664

checkpoint-5000/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b477f7d35457f29f99aee12fdd62a457674d3b3c0ba7052b376b1261797a11
+size 14604

checkpoint-5000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b1b898839cf1edb588b268226dc534a9e4df6d4ac42d05cfaffa93b44a4ccd
+size 988

checkpoint-5000/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e0c643a4dd147fb0c633051ecb841866884452856ed4a9411597dbd5658ec2
+size 1000

hcwf-2500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8138ce2d3b99833c664e302842e85fd2e1d889a2d22815e58f3b48c9d62939
+size 12653772

hcwf-2500/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363c091c8023127eac19eb83ecd2293217ed1cde41a4239066ace5f74fb7fd41
+size 23659664

hcwf-2500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd9b74bef8f9a41086b6da6a8f649153839604369745ec7bf7c9e93e1862d16
+size 14604

hcwf-2500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4eea61758cf25b69753bafd5203566231fc909ec8202addd2e36ed0b09504fd
+size 988

hcwf-2500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ade86c167a5553c5fd7cb50957f3cb1efd9f2200bd967481aa2c8c55ebab79
+size 1000

logs/dreambooth-sd3-lora/1734752690.5382943/events.out.tfevents.1734752690.aigpu08012.666434.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f04e0e8d9d9834e424c7367d4aeed627ac2e0d39b0a6da4883f3c56631d020
+size 3603

logs/dreambooth-sd3-lora/1734752690.5487766/hparams.yml

@@ -0,0 +1,74 @@
+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: /code/chaewon/humanscape/data/ps1/truncated
+class_prompt: 3d ultrasound image of baby face, headshot
+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: /code/chaewon/humanscape/data/ps1/instance
+instance_prompt: jshj 3d ultrasound image of baby face, headshot
+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: 5000
+mixed_precision: fp16
+mode_scale: 1.29
+num_class_images: 1000
+num_train_epochs: 10
+num_validation_images: 4
+optimizer: AdamW
+output_dir: v4_sd35large_reconstruction
+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: hcwf-2500
+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.1734752690.aigpu08012.666434.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e347044a4a10a56998be664fd36d22956010d59ac3245bcaae4f4d3f5a7006bc
+size 210088

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17adfe13be23ec38a8cf7d4ce63a57b7cf0649eaca4a566b5eb7b05830dfbd9
+size 11868760