Kohya's GUI

This repository provides a Windows-focused Gradio GUI for Kohya's Stable Diffusion trainers. The GUI allows you to set the training parameters and generate and run the required CLI commands to train the model.

If you run on Linux and would like to use the GUI, there is now a port of it as a docker container. You can find the project here.

Table of Contents

• Tutorials
• Required Dependencies
• Installation
  • CUDNN 8.6
• Upgrading
• Launching the GUI
• Dreambooth
• Finetune
• Train Network
• LoRA
• Troubleshooting
  • Page File Limit
  • No module called tkinter
  • FileNotFoundError
• Change History

Tutorials

How to Create a LoRA Part 1: Dataset Preparation:

How to Create a LoRA Part 2: Training the Model:

Required Dependencies

• Install Python 3.10
  • make sure to tick the box to add Python to the 'PATH' environment variable
• Install Git
• Install Visual Studio 2015, 2017, 2019, and 2022 redistributable

Installation

Runpod

Follow the instructions found in this discussion: https://github.com/bmaltais/kohya_ss/discussions/379

Ubuntu

In the terminal, run

git clone https://github.com/bmaltais/kohya_ss.git
cd kohya_ss
bash ubuntu_setup.sh

then configure accelerate with the same answers as in the Windows instructions when prompted.

Windows

Give unrestricted script access to powershell so venv can work:

• Run PowerShell as an administrator
• Run Set-ExecutionPolicy Unrestricted and answer 'A'
• Close PowerShell

Open a regular user Powershell terminal and run the following commands:

git clone https://github.com/bmaltais/kohya_ss.git
cd kohya_ss

python -m venv venv
.\venv\Scripts\activate

pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 --extra-index-url https://download.pytorch.org/whl/cu116
pip install --use-pep517 --upgrade -r requirements.txt
pip install -U -I --no-deps https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/f/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl

cp .\bitsandbytes_windows\*.dll .\venv\Lib\site-packages\bitsandbytes\
cp .\bitsandbytes_windows\cextension.py .\venv\Lib\site-packages\bitsandbytes\cextension.py
cp .\bitsandbytes_windows\main.py .\venv\Lib\site-packages\bitsandbytes\cuda_setup\main.py

accelerate config

Optional: CUDNN 8.6

This step is optional but can improve the learning speed for NVIDIA 30X0/40X0 owners. It allows for larger training batch size and faster training speed.

Due to the file size, I can't host the DLLs needed for CUDNN 8.6 on Github. I strongly advise you download them for a speed boost in sample generation (almost 50% on 4090 GPU) you can download them here.

To install, simply unzip the directory and place the cudnn_windows folder in the root of the this repo.

Run the following commands to install:

.\venv\Scripts\activate

python .\tools\cudann_1.8_install.py

Upgrading

When a new release comes out, you can upgrade your repo with the following commands in the root directory:

git pull

.\venv\Scripts\activate

pip install --use-pep517 --upgrade -r requirements.txt

Once the commands have completed successfully you should be ready to use the new version.

Launching the GUI using gui.bat or gui.ps1

The script can be run with several optional command line arguments:

--listen: the IP address to listen on for connections to Gradio. --username: a username for authentication. --password: a password for authentication. --server_port: the port to run the server listener on. --inbrowser: opens the Gradio UI in a web browser. --share: shares the Gradio UI.

These command line arguments can be passed to the UI function as keyword arguments. To launch the Gradio UI, run the script in a terminal with the desired command line arguments, for example:

gui.ps1 --listen 127.0.0.1 --server_port 7860 --inbrowser --share

or

gui.bat --listen 127.0.0.1 --server_port 7860 --inbrowser --share

Launching the GUI using kohya_gui.py

To run the GUI, simply use this command:

.\venv\Scripts\activate

python.exe .\kohya_gui.py

Dreambooth

You can find the dreambooth solution specific here: Dreambooth README

Finetune

You can find the finetune solution specific here: Finetune README

Train Network

You can find the train network solution specific here: Train network README

LoRA

Training a LoRA currently uses the train_network.py code. You can create a LoRA network by using the all-in-one gui.cmd or by running the dedicated LoRA training GUI with:

.\venv\Scripts\activate

python lora_gui.py

Once you have created the LoRA network, you can generate images via auto1111 by installing this extension.

Troubleshooting

Page File Limit

• X error relating to page file: Increase the page file size limit in Windows.

No module called tkinter

• Re-install Python 3.10 on your system.

FileNotFoundError

This is usually related to an installation issue. Make sure you do not have any python modules installed locally that could conflict with the ones installed in the venv:

1. Open a new powershell terminal and make sure no venv is active.
2. Run the following commands:

pip freeze > uninstall.txt
pip uninstall -r uninstall.txt

This will store your a backup file with your current locally installed pip packages and then uninstall them. Then, redo the installation instructions within the kohya_ss venv.

Change History

• 2023/03/23 (v21.3.2)
  • Fix issue reported: https://github.com/bmaltais/kohya_ss/issues/439
• 2023/03/23 (v21.3.1)
  • Merge PR to fix refactor naming issue for basic captions. Thank @zrma
• 2023/03/22 (v21.3.0)
  • Add a function to load training config with .toml to each training script. Thanks to Linaqruf for this great contribution!
    • Specify .toml file with --config_file. .toml file has key=value entries. Keys are same as command line options. See #241 for details.
    • All sub-sections are combined to a single dictionary (the section names are ignored.)
    • Omitted arguments are the default values for command line arguments.
    • Command line args override the arguments in .toml.
    • With --output_config option, you can output current command line options to the .toml specified with--config_file. Please use as a template.
  • Add --lr_scheduler_type and --lr_scheduler_args arguments for custom LR scheduler to each training script. Thanks to Isotr0py! #271
    • Same as the optimizer.
  • Add sample image generation with weight and no length limit. Thanks to mio2333! #288
    • ( ), (xxxx:1.2) and [ ] can be used.
  • Fix exception on training model in diffusers format with train_network.py Thanks to orenwang! #290
  • Add warning if you are about to overwrite an existing model: https://github.com/bmaltais/kohya_ss/issues/404
  • Add --vae_batch_size for faster latents caching to each training script. This batches VAE calls.
    • Please start with2 or 4 depending on the size of VRAM.
  • Fix a number of training steps with --gradient_accumulation_steps and --max_train_epochs. Thanks to tsukimiya!
  • Extract parser setup to external scripts. Thanks to robertsmieja!
  • Fix an issue without .npz and with --full_path in training.
  • Support extensions with upper cases for images for not Windows environment.
  • Fix resize_lora.py to work with LoRA with dynamic rank (including conv_dim != network_dim). Thanks to toshiaki!
  • Fix issue: https://github.com/bmaltais/kohya_ss/issues/406
  • Add device support to LoRA extract.