|
|
--- |
|
|
datasets: |
|
|
- erikhsos/cbbier |
|
|
tags: |
|
|
- text-to-image |
|
|
- dreambooth |
|
|
- lora |
|
|
- diffusers |
|
|
pipeline_tag: text-to-image |
|
|
--- |
|
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
|
instance_prompt: [CB] bottle photo |
|
|
license: openrail++ |
|
|
--- |
|
|
|
|
|
# SDXL LoRA DreamBooth - erikhsos/cbbier_LoRA |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
## Model description |
|
|
|
|
|
These are erikhsos/campusbiernew_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. |
|
|
|
|
|
The weights were trained using [DreamBooth](https://dreambooth.github.io/). |
|
|
|
|
|
LoRA for the text encoder was enabled: False. |
|
|
|
|
|
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. |
|
|
|
|
|
## Trigger words |
|
|
|
|
|
You should use [CB] bottle photo to trigger the image generation. |
|
|
|
|
|
## Training Settings |
|
|
#!/usr/bin/env bash |
|
|
!accelerate launch train_dreambooth_lora_sdxl.py \ |
|
|
--pretrained_model_name_or_path="stabilityai/stable-diffusion-xl-base-1.0" \ |
|
|
--pretrained_vae_model_name_or_path="madebyollin/sdxl-vae-fp16-fix" \ |
|
|
--dataset_name="cbbier" \ |
|
|
--output_dir="cbbier_LoRA" \ |
|
|
--caption_column="prompt"\ |
|
|
--mixed_precision="fp16" \ |
|
|
--instance_prompt="[CB] bottle photo" \ |
|
|
--resolution=1024 \ |
|
|
--train_batch_size=1 \ |
|
|
--gradient_accumulation_steps=3 \ |
|
|
--gradient_checkpointing \ |
|
|
--learning_rate=1e-4 \ |
|
|
--snr_gamma=5.0 \ |
|
|
--lr_scheduler="constant" \ |
|
|
--lr_warmup_steps=0 \ |
|
|
--mixed_precision="fp16" \ |
|
|
--use_8bit_adam \ |
|
|
--max_train_steps=100 \ |
|
|
--checkpointing_steps=717 \ |
|
|
--seed="0" |
|
|
|
|
|
## Download model |
|
|
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
|
|
[Download](erikhsos/cbbier_LoRA/tree/main) them in the Files & versions tab. |
