Home

Awesome

This repository contains training, generation and utility scripts for Stable Diffusion.

Change History is moved to the bottom of the page. 更新履歴はページ末尾に移しました。

日本語版READMEはこちら

The development version is in the dev branch. Please check the dev branch for the latest changes.

FLUX.1 and SD3/SD3.5 support is done in the sd3 branch. If you want to train them, please use the sd3 branch.

For easier use (GUI and PowerShell scripts etc...), please visit the repository maintained by bmaltais. Thanks to @bmaltais!

This repository contains the scripts for:

About requirements.txt

The file does not contain requirements for PyTorch. Because the version of PyTorch depends on the environment, it is not included in the file. Please install PyTorch first according to the environment. See installation instructions below.

The scripts are tested with Pytorch 2.1.2. 2.0.1 and 1.12.1 is not tested but should work.

Links to usage documentation

Most of the documents are written in Japanese.

English translation by darkstorm2150 is here. Thanks to darkstorm2150!

Windows Required Dependencies

Python 3.10.6 and Git:

Give unrestricted script access to powershell so venv can work:

Windows Installation

Open a regular Powershell terminal and type the following inside:

git clone https://github.com/kohya-ss/sd-scripts.git
cd sd-scripts

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

pip install torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu118
pip install --upgrade -r requirements.txt
pip install xformers==0.0.23.post1 --index-url https://download.pytorch.org/whl/cu118

accelerate config

If python -m venv shows only python, change python to py.

Note: Now bitsandbytes==0.43.0, prodigyopt==1.0 and lion-pytorch==0.0.6 are included in the requirements.txt. If you'd like to use the another version, please install it manually.

This installation is for CUDA 11.8. If you use a different version of CUDA, please install the appropriate version of PyTorch and xformers. For example, if you use CUDA 12, please install pip install torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu121 and pip install xformers==0.0.23.post1 --index-url https://download.pytorch.org/whl/cu121.

<!-- 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 -->

Answers to accelerate config:

- This machine
- No distributed training
- NO
- NO
- NO
- all
- fp16

If you'd like to use bf16, please answer bf16 to the last question.

Note: Some user reports ValueError: fp16 mixed precision requires a GPU is occurred in training. In this case, answer 0 for the 6th question: What GPU(s) (by id) should be used for training on this machine as a comma-separated list? [all]:

(Single GPU with id 0 will be used.)

Upgrade

When a new release comes out you can upgrade your repo with the following command:

cd sd-scripts
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.

Upgrade PyTorch

If you want to upgrade PyTorch, you can upgrade it with pip install command in Windows Installation section. xformers is also required to be upgraded when PyTorch is upgraded.

Credits

The implementation for LoRA is based on cloneofsimo's repo. Thank you for great work!

The LoRA expansion to Conv2d 3x3 was initially released by cloneofsimo and its effectiveness was demonstrated at LoCon by KohakuBlueleaf. Thank you so much KohakuBlueleaf!

License

The majority of scripts is licensed under ASL 2.0 (including codes from Diffusers, cloneofsimo's and LoCon), however portions of the project are available under separate license terms:

Memory Efficient Attention Pytorch: MIT

bitsandbytes: MIT

BLIP: BSD-3-Clause

Change History

Oct 27, 2024 / 2024-10-27:

Oct 26, 2024 / 2024-10-26:

Sep 13, 2024 / 2024-09-13:

Jun 23, 2024 / 2024-06-23:

Apr 7, 2024 / 2024-04-07: v0.8.7

Apr 7, 2024 / 2024-04-07: v0.8.6

Highlights

Training scripts

Dataset settings

Image tagging

About Masked loss

The masked loss is supported in each training script. To enable the masked loss, specify the --masked_loss option.

The feature is not fully tested, so there may be bugs. If you find any issues, please open an Issue.

ControlNet dataset is used to specify the mask. The mask images should be the RGB images. The pixel value 255 in R channel is treated as the mask (the loss is calculated only for the pixels with the mask), and 0 is treated as the non-mask. The pixel values 0-255 are converted to 0-1 (i.e., the pixel value 128 is treated as the half weight of the loss). See details for the dataset specification in the LLLite documentation.

About Scheduled Huber Loss

Scheduled Huber Loss has been introduced to each training scripts. This is a method to improve robustness against outliers or anomalies (data corruption) in the training data.

With the traditional MSE (L2) loss function, the impact of outliers could be significant, potentially leading to a degradation in the quality of generated images. On the other hand, while the Huber loss function can suppress the influence of outliers, it tends to compromise the reproduction of fine details in images.

To address this, the proposed method employs a clever application of the Huber loss function. By scheduling the use of Huber loss in the early stages of training (when noise is high) and MSE in the later stages, it strikes a balance between outlier robustness and fine detail reproduction.

Experimental results have confirmed that this method achieves higher accuracy on data containing outliers compared to pure Huber loss or MSE. The increase in computational cost is minimal.

The newly added arguments loss_type, huber_schedule, and huber_c allow for the selection of the loss function type (Huber, smooth L1, MSE), scheduling method (exponential, constant, SNR), and Huber's parameter. This enables optimization based on the characteristics of the dataset.

See PR #1228 for details.

Please read Releases for recent updates.

主要な変更点

学習スクリプト

データセット設定

画像のタグ付け

マスクロスについて

各学習スクリプトでマスクロスをサポートしました。マスクロスを有効にするには --masked_loss オプションを指定してください。

機能は完全にテストされていないため、不具合があるかもしれません。その場合は Issue を立てていただけると助かります。

マスクの指定には ControlNet データセットを使用します。マスク画像は RGB 画像である必要があります。R チャンネルのピクセル値 255 がロス計算対象、0 がロス計算対象外になります。0-255 の値は、0-1 の範囲に変換されます(つまりピクセル値 128 の部分はロスの重みが半分になります)。データセットの詳細は LLLite ドキュメント をご覧ください。

Scheduled Huber Loss について

各学習スクリプトに、学習データ中の異常値や外れ値(data corruption)への耐性を高めるための手法、Scheduled Huber Lossが導入されました。

従来のMSE(L2)損失関数では、異常値の影響を大きく受けてしまい、生成画像の品質低下を招く恐れがありました。一方、Huber損失関数は異常値の影響を抑えられますが、画像の細部再現性が損なわれがちでした。

この手法ではHuber損失関数の適用を工夫し、学習の初期段階(ノイズが大きい場合)ではHuber損失を、後期段階ではMSEを用いるようスケジューリングすることで、異常値耐性と細部再現性のバランスを取ります。

実験の結果では、この手法が純粋なHuber損失やMSEと比べ、異常値を含むデータでより高い精度を達成することが確認されています。また計算コストの増加はわずかです。

具体的には、新たに追加された引数loss_type、huber_schedule、huber_cで、損失関数の種類(Huber, smooth L1, MSE)とスケジューリング方法(exponential, constant, SNR)を選択できます。これによりデータセットに応じた最適化が可能になります。

詳細は PR #1228 をご覧ください。

PR 内でいくつかの比較が共有されています。この機能を試す場合、最初は --loss_type smooth_l1 --huber_schedule snr --huber_c 0.1 などで試してみるとよいかもしれません。

最近の更新情報は Release をご覧ください。

Additional Information

Naming of LoRA

The LoRA supported by train_network.py has been named to avoid confusion. The documentation has been updated. The following are the names of LoRA types in this repository.

  1. LoRA-LierLa : (LoRA for Li n e a r La yers)

    LoRA for Linear layers and Conv2d layers with 1x1 kernel

  2. LoRA-C3Lier : (LoRA for C olutional layers with 3 x3 Kernel and Li n e a r layers)

    In addition to 1., LoRA for Conv2d layers with 3x3 kernel

LoRA-LierLa is the default LoRA type for train_network.py (without conv_dim network arg).

<!-- LoRA-LierLa can be used with [our extension](https://github.com/kohya-ss/sd-webui-additional-networks) for AUTOMATIC1111's Web UI, or with the built-in LoRA feature of the Web UI. To use LoRA-C3Lier with Web UI, please use our extension. -->

Sample image generation during training

A prompt file might look like this, for example

# prompt 1
masterpiece, best quality, (1girl), in white shirts, upper body, looking at viewer, simple background --n low quality, worst quality, bad anatomy,bad composition, poor, low effort --w 768 --h 768 --d 1 --l 7.5 --s 28

# prompt 2
masterpiece, best quality, 1boy, in business suit, standing at street, looking back --n (low quality, worst quality), bad anatomy,bad composition, poor, low effort --w 576 --h 832 --d 2 --l 5.5 --s 40

Lines beginning with # are comments. You can specify options for the generated image with options like --n after the prompt. The following can be used.

The prompt weighting such as ( ) and [ ] are working.