How to install Kohya_SS + PyTorch 2.6.0 (Optional) (Windows)

1)Install Kohya_SS

Open Terminal:

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

cd kohya_ss

git checkout sd3-sd3.5-flux

setup.bat

Kohya_ss setup menu:

1. Install kohya_ss GUI

5. (Optional) Manually configure Accelerate:

>This machine

>No distributed training



Do you want to run your training on CPU only (even if a GPU / Apple Silicon / Ascend NPU device is available)?

>No

Do you wish to optimize your script with torch dynamo?

>No

Do you want to use DeepSpeed?

>No

What GPU(s) (by id) should be used for training on this machine as a comma-seperated list?

>All

Would you like to enable numa efficiency? (Currently only supported on NVIDIA hardware).

>Yes

Do you wish to use FP16 or BF16 (mixed precision)?

>bf16 (If you have a RTX 30/40 series video card choose >bf16. If don't have choose >fp16.)

2)Install PyTorch 2.6.0 for Kohya_SS (Optional) (Experimental)

1.Change text in gui.bat file inside kohya_ss folder and to add --noverify to skip check updates reequipments for kohya_gui.py

@echo off

set PYTHON_VER=3.10.9

:: Deactivate the virtual environment

call .\venv\Scripts\deactivate.bat

:: Activate the virtual environment

call .\venv\Scripts\activate.bat

set PATH=%PATH%;%~dp0venv\Lib\site-packages\torch\lib

:: If the exit code is 0, run the kohya_gui.py script with the command-line arguments

if %errorlevel% equ 0 (

REM Check if the batch was started via double-click

IF /i "%comspec% /c %~0 " equ "%cmdcmdline:"=%" (

REM echo This script was started by double clicking.

cmd /k python.exe kohya_gui.py %* --noverify

) ELSE (

REM echo This script was started from a command prompt.

python.exe kohya_gui.py %* --noverify

)

)

2.Run Terminal inside kohya_ss folder:

python -m venv venv

.\venv\Scripts\activate

pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu124

pip install xformers==0.0.29.dev922

pip3 install torch==2.5.0 torchvision --index-url https://download.pytorch.org/whl/test/cu124

3.Install cuDNN 9.5.0 for Kohya_SS (Option)

Run terminal inside kohya_ss folder:

python -m venv venv

.\venv\Scripts\activate

pip install nvidia-cudnn-cu11==9.5.0.50

3.Install TransformerEngine or MS-AMP for Kohya_SS (In development, Option)

pip install transformer-engine