# This should be a number, incremented with each change
release=${RELEASE}\
io.k8s.display-name="kohya_ss"\
summary="Kohya's GUI: This repository provides a Gradio GUI for Kohya's Stable Diffusion trainers(https://github.com/kohya-ss/sd-scripts)."\
description="The GUI allows you to set the training parameters and generate and run the required CLI commands to train the model. This is the docker image for Kohya's GUI. For more information about this tool, please visit the following website: https://github.com/bmaltais/kohya_ss."
This is a GUI and CLI for training diffusion models.
This project provides a user-friendly Gradio-based Graphical User Interface (GUI) for [Kohya's Stable Diffusion training scripts](https://github.com/kohya-ss/sd-scripts).
Stable Diffusion training empowers users to customize image generation models by fine-tuning existing models, creating unique artistic styles,
and training specialized models like LoRA (Low-Rank Adaptation).
Key features of this GUI include:
* Easy-to-use interface for setting a wide range of training parameters.
* Automatic generation of the command-line interface (CLI) commands required to run the training scripts.
* Support for various training methods, including LoRA, Dreambooth, fine-tuning, and SDXL training.
Support for Linux and macOS is also available. While Linux support is actively maintained through community contributions, macOS compatibility may vary.
| [](https://colab.research.google.com/github/camenduru/kohya_ss-colab/blob/main/kohya_ss_colab.ipynb) | kohya_ss_gui_colab |
> 💡 If you encounter issues, please report them on camenduru’s repo.
**Special thanks**
I would like to express my gratitude to camenduru for their valuable contribution.
#### Runpod, Novita, Docker
These options are for users running training on hosted GPU infrastructure or containers.
- **[Runpod setup](docs/runpod_setup.md)** – Ready-made GPU background training via templates.
- **[Novita setup](docs/novita_setup.md)** – Similar to Runpod, but integrated into the Novita UI.
- **[Docker setup](docs/docker.md)** – For developers/sysadmins using containerized environments.
## Custom Path Defaults with `config.toml`
The GUI supports a configuration file named `config.toml` that allows you to set default paths for many of the input fields. This is useful for avoiding repetitive manual selection of directories every time you start the GUI.
**Purpose of `config.toml`:**
* Pre-fill default directory paths for pretrained models, datasets, output folders, LoRA models, etc.
* Streamline your workflow by having the GUI remember your preferred locations.
**How to Use and Customize:**
1. **Create your configuration file:**
* In the root directory of the `kohya_ss` repository, you'll find a file named `config example.toml`.
* Copy this file and rename the copy to `config.toml`. This `config.toml` file will be automatically loaded when the GUI starts.
2. **Edit `config.toml`:**
* Open `config.toml` with a text editor.
* The file uses TOML (Tom's Obvious, Minimal Language) format, which consists of `key = "value"` pairs.
* Modify the paths for the keys according to your local directory structure.
* **Important:**
* Use absolute paths (e.g., `C:/Users/YourName/StableDiffusion/Models` or `/home/yourname/sd-models`).
* Alternatively, you can use paths relative to the `kohya_ss` root directory.
* Ensure you use forward slashes (`/`) for paths, even on Windows, as this is generally more compatible with TOML and Python.
* Make sure the specified directories exist on your system.
**Structure of `config.toml`:**
The `config.toml` file can have several sections, typically corresponding to different training modes or general settings. Common keys you might want to set include:
* `model_dir`: Default directory for loading base Stable Diffusion models.
* `lora_model_dir`: Default directory for saving and loading LoRA models.
* `output_dir`: Default base directory for training outputs (images, logs, model checkpoints).
* `dataset_dir`: A general default if you store all your datasets in one place.
* Specific input paths for different training tabs like Dreambooth, Finetune, LoRA, etc. (e.g., `db_model_dir`, `ft_source_model_name_or_path`).
**Example Configurations:**
Here's an example snippet of what your `config.toml` might look like:
# You can find a comprehensive list of all available keys in the `config example.toml` file.
# Refer to it to customize paths for all supported options in the GUI.
```
**Using a Custom Config File Path:**
If you prefer to name your configuration file differently or store it in another location, you can specify its path using the `--config` command-line argument when launching the GUI:
* On Windows: `gui.bat --config D:/my_configs/kohya_settings.toml`
* On Linux/macOS: `./gui.sh --config /home/user/my_configs/kohya_settings.toml`
By effectively using `config.toml`, you can significantly speed up your training setup process. Always refer to the `config example.toml` for the most up-to-date list of configurable paths.
## LoRA
To train a LoRA, you can currently use the `train_network.py` code. You can create a LoRA network by using the all-in-one GUI.
Once you have created the LoRA network, you can generate images using auto1111 by installing [this extension](https://github.com/kohya-ss/sd-webui-additional-networks).
For more detailed information on LoRA training options and advanced configurations, please refer to our LoRA documentation:
- [LoRA Training Guide](docs/LoRA/top_level.md)
- [LoRA Training Options](docs/LoRA/options.md)
## Sample image generation during training
A prompt file might look like this, for example:
```txt
# 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 options can be used:
- `--n`: Negative prompt up to the next option.
- `--w`: Specifies the width of the generated image.
- `--h`: Specifies the height of the generated image.
- `--d`: Specifies the seed of the generated image.
- `--l`: Specifies the CFG scale of the generated image.
- `--s`: Specifies the number of steps in the generation.
The prompt weighting such as `( )` and `[ ]` is working.
## Troubleshooting
If you encounter any issues, refer to the troubleshooting steps below.
### Page File Limit
If you encounter an X error related to the page file, you may need to increase the page file size limit in Windows.
### No module called tkinter
If you encounter an error indicating that the module `tkinter` is not found, try reinstalling Python 3.10 on your system.
### LORA Training on TESLA V100 - GPU Utilization Issue
See [Troubleshooting LORA Training on TESLA V100](docs/troubleshooting_tesla_v100.md) for details.
## SDXL training
For detailed guidance on SDXL training, please refer to the [official sd-scripts documentation](https://github.com/kohya-ss/sd-scripts/blob/main/README.md#sdxl-training) and relevant sections in our [LoRA Training Guide](docs/LoRA/top_level.md).
## Masked loss
The masked loss is supported in each training script. To enable the masked loss, specify the `--masked_loss` option.
> [!WARNING]
> 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](./docs/train_lllite_README.md#preparing-the-dataset).
## Guides
The following are guides extracted from issues discussions
### Using Accelerate Lora Tab to Select GPU ID
#### Starting Accelerate in GUI
- Open the kohya GUI on your desired port.
- Open the `Accelerate launch` tab
- Ensure the Multi-GPU checkbox is unchecked.
- Set GPU IDs to the desired GPU (like 1).
#### Running Multiple Instances (linux)
- For tracking multiple processes, use separate kohya GUI instances on different ports (e.g., 7860, 7861).
- For terminal access, use SSH and tools like `tmux` or `screen`.
For more details, visit the [GitHub issue](https://github.com/bmaltais/kohya_ss/issues/2577).
## Interesting Forks
To finetune HunyuanDiT models or create LoRAs, visit this [fork](https://github.com/Tencent/HunyuanDiT/tree/main/kohya_ss-hydit)
## Contributing
Contributions are welcome! If you'd like to contribute to this project, please consider the following:
- For bug reports or feature requests, please open an issue on the [GitHub Issues page](https://github.com/bmaltais/kohya_ss/issues).
- If you'd like to submit code changes, please open a pull request. Ensure your changes are well-tested and follow the existing code style.
- For security-related concerns, please refer to our `SECURITY.md` file.
## License
This project is licensed under the Apache License 2.0. See the [LICENSE.md](LICENSE.md) file for details.
## Change History
### v25.0.3
- Upgrade Gradio, diffusers and huggingface-hub to latest release to fix issue with ASGI.
- Add a new method to setup and run the GUI. You will find two new script for both Windows (gui-uv.bat) and Linux (gui-uv.sh). With those scripts there is no need to run setup.bat or setup.sh anymore.
### v25.0.2
- Force gradio to 5.14.0 or greater so it is updated.
### v25.0.1
- Fix issue with requirements version causing huggingface download issues
### v25.0.0
- Major update: Introduced support for flux.1 and sd3, moving the GUI to align with more recent script functionalities.
- Users preferring the pre-flux.1/sd3 version can check out tag `v24.1.7`.
```shell
git checkout v24.1.7
```
- For details on new flux.1 and sd3 parameters, refer to the [sd-scripts README](https://github.com/kohya-ss/sd-scripts/blob/sd3/README.md).
NVIDIA Studio Driver(SDR) : Windows 10/11 → 531.79 / 536.67 등 :
아래서 기종 선택하고 Studio Driver 선택하고 검색 버튼
https://www.nvidia.com/ko-kr/geforce/drivers/
제일 낮은 버전이 아마 괜찮을 듯 함.
CUDA 12.3 : https://developer.nvidia.com/cuda-12-3-0-download-archive
`python -m venv` 명령어 실행 시 `python`만 표시된다면, `python`을 `py`로 변경하십시오.
참고: 현재 `bitsandbytes==0.44.0`, `prodigyopt==1.0` 및 `lion-pytorch==0.0.6`이 requirements.txt에 포함되어 있습니다. 다른 버전을 사용하려면 수동으로 설치하십시오.
이 설치는 CUDA 11.8용입니다. 다른 버전의 CUDA를 사용하는 경우, 해당 버전의 PyTorch와 xformers를 설치하십시오. 예를 들어, CUDA 12를 사용하는 경우 `pip install torch==2.1.2 torchvision==0.16.2 --index-url https://download.pytorch.org/whl/cu121` 및 `pip install xformers==0.0.23.post1 --index-url https://download.pytorch.org/whl/cu121`를 실행하십시오.
PyTorch 2.2 이상을 사용하는 경우 `torch==2.1.2`, `torchvision==0.16.2`, `xformers==0.0.23.post1`을 적절한 버전으로 변경하십시오.
PyTorch를 업그레이드하려면 [Windows 설치](#windows-installation) 섹션의 `pip install` 명령어로 업그레이드할 수 있습니다. PyTorch를 업그레이드할 때 `xformers`도 함께 업그레이드해야 합니다.
## 크레딧
LoRA 구현은 [cloneofsimo의 저장소](https://github.com/cloneofsimo/lora)를 기반으로 합니다. 훌륭한 작업에 감사드립니다!
Conv2d 3x3에 대한 LoRA 확장은 cloneofsimo에 의해 처음 공개되었으며, 그 효과는 KohakuBlueleaf에 의해 [LoCon](https://github.com/KohakuBlueleaf/LoCon)에서 입증되었습니다. KohakuBlueleaf님께 진심으로 감사드립니다!
## 라이선스
대부분의 스크립트는 ASL 2.0 라이선스 하에 배포됩니다(Diffusers, cloneofsimo 및 LoCon의 코드 포함). 다만 프로젝트의 일부 구성 요소는 별도의 라이선스 조건이 적용됩니다:
[Memory Efficient Attention Pytorch](https://github.com/lucidrains/memory-efficient-attention-pytorch): MIT
[bitsandbytes](https://github.com/TimDettmers/bitsandbytes): MIT
- Fixed a bug where some of LoRA modules for CLIP Text Encoder were not trained. Thank you Nekotekina for PR [#1964](https://github.com/kohya-ss/sd-scripts/pull/1964)
- The LoRA modules for CLIP Text Encoder are now 264 modules, which is the same as before. Only 88 modules were trained in the previous version.
### Jan 17, 2025 / 2025-01-17 Version 0.9.0
- __important__ The dependent libraries are updated. Please see [Upgrade](#upgrade) and update the libraries.
- bitsandbytes, transformers, accelerate and huggingface_hub are updated.
- If you encounter any issues, please report them.
- The dev branch is merged into main. The documentation is delayed, and I apologize for that. I will gradually improve it.
- The state just before the merge is released as Version 0.8.8, so please use it if you encounter any issues.
- The following changes are included.
#### 변경 사항
## 추가 정보
### LoRA 명명 규칙
`train_network.py`에서 지원하는 LoRA의 명칭을 혼동을 피하기 위해 변경하였습니다. 관련 문서도 업데이트되었습니다. 본 저장소에서 사용하는 LoRA 유형의 명칭은 다음과 같습니다.
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-LierLa는 `train_network.py`의 기본 LoRA 유형입니다(네트워크 인자 `conv_dim` 제외).
<!--
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.
-->
### 훈련 중 샘플 이미지 생성
예를 들어 프롬프트 파일은 다음과 같을 수 있습니다
```
# 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
```
`#`로 시작하는 줄은 주석입니다. 프롬프트 뒤에 `--n`과 같은 옵션을 사용하여 생성된 이미지의 옵션을 지정할 수 있습니다. 다음을 사용할 수 있습니다.
sungjoonkim