campusbier_LoRA / README.md
erikhsos's picture
Update README.md
0f0451e verified
---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a photo of CAMPUPUSBIER beer
license: openrail++
---
# SDXL LoRA DreamBooth - erikhsos/campusbier_LoRA
<Gallery />
## Model description
These are erikhsos/campusbier_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 a photo of CAMPUPUSBIER beer to trigger the image generation.
## Training Settings
!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="campusbiernew" \
--output_dir="campusbiernew_LoRA" \
--caption_column="prompt"\
--mixed_precision="fp16" \
--instance_prompt="a photo of [CB] beer" \
--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=500 \
--checkpointing_steps=717 \
--seed="0"
## Download model
Weights for this model are available in Safetensors format.
[Download](erikhsos/campusbier_LoRA/tree/main) them in the Files & versions tab.