LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.
 
 
 
 
 
Go to file
Akiba a068578e1e
fix DAdaptation
2023-04-22 17:36:34 +08:00
assets add tensorboard script (#18) 2023-03-02 10:50:27 +08:00
huggingface init 2023-01-22 21:45:39 +08:00
logs fix install-cn xformers 2023-01-23 13:45:34 +08:00
output init 2023-01-22 21:45:39 +08:00
sd-models init 2023-01-22 21:45:39 +08:00
sd-scripts@ee5cec7530 bump sd version 2023-04-20 15:47:39 +08:00
toml update 2023-04-20 17:32:52 +08:00
.gitattributes crlf 2023-02-10 14:09:27 +08:00
.gitignore more args 2023-02-04 12:42:37 +08:00
.gitmodules submodule 2023-01-22 21:04:06 +08:00
README.md add tensorboard script (#18) 2023-03-02 10:50:27 +08:00
install-cn.ps1 dadaptation install 2023-04-16 19:08:05 +08:00
install.bash 修复noise_offset,添加TE提早停止,添加lycoris dropout参数 (#83) 2023-04-16 15:51:55 +08:00
install.ps1 dadaptation install 2023-04-16 19:08:05 +08:00
interrogate.ps1 Update interrogate.ps1 (#17) 2023-03-01 20:47:36 +08:00
resize.ps1 更新动态调整方式 2023-03-27 00:22:58 +08:00
tensorboard.ps1 add tensorboard script (#18) 2023-03-02 10:50:27 +08:00
train.ipynb update train.ipynb 2023-01-26 10:35:28 +08:00
train.ps1 fix DAdaptation 2023-04-22 17:36:34 +08:00
train.sh 修改描述 2023-04-22 17:20:41 +08:00
train_by_toml.ps1 update 2023-04-20 16:09:13 +08:00
train_by_toml.sh fix bug 2023-04-20 16:08:06 +08:00

README.md

LoRA-scripts

LoRA training scripts for kohya-ss/sd-scripts

Usage

Clone repo with submodules

git clone --recurse-submodules https://github.com/Akegarasu/lora-scripts

Required Dependencies

Python 3.10.8 and Git

Windows

Installation

Run install.ps1 will automaticilly create a venv for you and install necessary deps.

Train

Edit train.ps1, and run it.

Linux

Installation

Run install.bash will create a venv and install necessary deps.

Train

Training script train.sh will not activate venv for you. You should activate venv first.

source venv/bin/activate

Edit train.sh, and run it.

TensorBoard

Run tensorboard.ps1 will start TensorBoard at http://localhost:6006/