​
Installation

Rubbrband can be installed through pip.

pip install rubbrband

​
Example Usage

To get a feel for finetuning Dreambooth, you can copy and paste these lines in your terminal to start finetuning. This script will finetune a Dreambooth model to learn a specific man’s face.

# install rubbrband
pip install rubbrband

# download dummy dataset and set folder structure
git clone https://github.com/rubbrband/sample_dataset.git
git clone https://github.com/JoePenna/Stable-Diffusion-Regularization-Images.git --depth 1
mkdir regDir
mv ./Stable-Diffusion-Regularization-Images/man_unsplash ./regDir/man

# start training
rubbrband train dreambooth --class-word man --dataset-dir ./sample_dataset --reg-dir ./regDir --log-dir ./logs

​
Install Docker

Rubbrband requires Docker to be installed. Installation instructions found here.

​
Supported models

  • DreamBooth - Personalize Stable Diffusion with your own images

  • WebUI Stable Diffusion - Use a web interface to train and generate outputs with Stable Diffusion models.

  • ControlNet(beta) - An image model to control diffusion models by adding extra conditions

  • LoRA(beta) - Fine-tune Stable Diffusion models twice as fast as DreamBooth, by Low-rank Adaptation.

​
CLI Commands

# View running MODELS
rubbrband ls

# View all supported MODELS
rubbrband models

# Train a MODEL with a given folder containing data
rubbrband train MODEL --data-dir=""

# Start a webUI model
rubbrband web MODEL