KohyaSS/README.md

# Kohya's dreambooth and finetuning

This repository now includes the solutions provided by Kohya_ss in a single location. I have combined both solutions under one repository to align with the new official Kohya repository where he will maintain his code from now on: https://github.com/kohya-ss/sd-scripts.

A note accompanying the release of his new repository can be found here: https://note.com/kohya_ss/n/nba4eceaa4594

## Dreambooth

You can find the dreambooth solution spercific [Dreambooth README](README_dreambooth.md)

## Finetune

You can find the finetune solution spercific [Finetune README](README_finetune.md)

## LoRA

You can create LoRA network by running the dedicated GUI with:

```
python lora_gui.py
```

or via the all in one GUI:

```
python kahya_gui.py
```

Once you have created the LoRA network you can generate images via auto1111 by installing the extension found here: https://github.com/kohya-ss/sd-webui-additional-networks

## Change history

* 2023/01/06 (v19.4):
    - Add new Utility to Extract a LoRA from a finetuned model
* 2023/01/06 (v19.3.1):
    - Emergency fix for dreambooth_ui no longer working, sorry
    - Add LoRA network merge too GUI. Run `pip install -U -r requirements.txt` after pulling this new release.
* 2023/01/05 (v19.3):
    - Add support for `--clip_skip` option
    - Add missing `detect_face_rotate.py` to tools folder
    - Add `gui.cmd` for easy start of GUI
* 2023/01/02 (v19.2) update:
    - Finetune, add xformers, 8bit adam, min bucket, max bucket, batch size and flip augmentation support for dataset preparation
    - Finetune, add "Dataset preparation" tab to group task specific options
* 2023/01/01 (v19.2) update:
    - add support for color and flip augmentation to "Dreambooth LoRA"
* 2023/01/01 (v19.1) update:
    - merge kohys_ss upstream code  updates
    - rework Dreambooth LoRA GUI
    - fix bug where LoRA network weights were not loaded to properly resume training
* 2022/12/30 (v19) update:
    - support for LoRA network training in kohya_gui.py.
* 2022/12/23 (v18.8) update:
    - Fix for conversion tool issue when the source was an sd1.x diffuser model
    - Other minor code and GUI fix
* 2022/12/22 (v18.7) update:
    - Merge dreambooth and finetune is a common GUI
    - General bug fixes and code improvements
* 2022/12/21 (v18.6.1) update:
    - fix issue with dataset balancing when the number of detected images in the folder is 0

* 2022/12/21 (v18.6) update:
    - add optional GUI authentication support via: `python fine_tune.py --username=<name> --password=<password>`
Merge dreambooth and finetuning in one repo to align with kohya_ss new repo (#10) * Merge both dreambooth and finetune back in one repo 2022-12-20 14:15:17 +00:00			`# Kohya's dreambooth and finetuning`
1st commit 2022-10-30 15:15:09 +00:00
Create model and log folder when running th dreambooth folder creation utility 2022-12-20 15:07:22 +00:00			`This repository now includes the solutions provided by Kohya_ss in a single location. I have combined both solutions under one repository to align with the new official Kohya repository where he will maintain his code from now on: https://github.com/kohya-ss/sd-scripts.`
Update readme 2022-10-30 15:40:55 +00:00
Create model and log folder when running th dreambooth folder creation utility 2022-12-20 15:07:22 +00:00			`A note accompanying the release of his new repository can be found here: https://note.com/kohya_ss/n/nba4eceaa4594`
Add dependencies 2022-10-30 17:37:42 +00:00
Merge dreambooth and finetuning in one repo to align with kohya_ss new repo (#10) * Merge both dreambooth and finetune back in one repo 2022-12-20 14:15:17 +00:00			`## Dreambooth`
Update doc 2022-10-30 17:39:00 +00:00
Merge dreambooth and finetuning in one repo to align with kohya_ss new repo (#10) * Merge both dreambooth and finetune back in one repo 2022-12-20 14:15:17 +00:00			`You can find the dreambooth solution spercific [Dreambooth README](README_dreambooth.md)`
Add dependencies 2022-10-30 17:37:42 +00:00
Merge dreambooth and finetuning in one repo to align with kohya_ss new repo (#10) * Merge both dreambooth and finetune back in one repo 2022-12-20 14:15:17 +00:00			`## Finetune`
Update README to help with Powershell rights issue. 2022-11-01 11:46:55 +00:00
Add authentication support 2022-12-21 14:05:06 +00:00			`You can find the finetune solution spercific [Finetune README](README_finetune.md)`

Update LoRA GUI Various improvements 2023-01-01 19:14:58 +00:00			`## LoRA`

			`You can create LoRA network by running the dedicated GUI with:`

			```
			`python lora_gui.py`
			```

			`or via the all in one GUI:`

			```
			`python kahya_gui.py`
			```

			`Once you have created the LoRA network you can generate images via auto1111 by installing the extension found here: https://github.com/kohya-ss/sd-webui-additional-networks`

Add authentication support 2022-12-21 14:05:06 +00:00			`## Change history`

Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 23:25:55 +00:00			`* 2023/01/06 (v19.4):`
			`- Add new Utility to Extract a LoRA from a finetuned model`
Emergency fix for dreambooth_ui no longer working, sorry - Add LoRA network merge too GUI. Run `pip install -U -r requirements.txt` after pulling this new release. 2023-01-06 12:13:12 +00:00			`* 2023/01/06 (v19.3.1):`
			`- Emergency fix for dreambooth_ui no longer working, sorry`
			- Add LoRA network merge too GUI. Run `pip install -U -r requirements.txt` after pulling this new release.
			`* 2023/01/05 (v19.3):`
- Add support for `--clip_skip` option - Add missing `detect_face_rotate.py` to tools folder - Add `gui.cmd` for easy start of GUI 2023-01-06 00:16:13 +00:00			- Add support for `--clip_skip` option
			- Add missing `detect_face_rotate.py` to tools folder
			- Add `gui.cmd` for easy start of GUI
- Finetune, add xformers, 8bit adam, min bucket, max bucket, batch size and flip augmentation support for dataset preparation - Finetune, add "Dataset preparation" tab to group task specific options 2023-01-02 18:07:17 +00:00			`* 2023/01/02 (v19.2) update:`
			`- Finetune, add xformers, 8bit adam, min bucket, max bucket, batch size and flip augmentation support for dataset preparation`
			`- Finetune, add "Dataset preparation" tab to group task specific options`
add support for color and flip augmentation to "Dreambooth LoRA" 2023-01-02 03:43:44 +00:00			`* 2023/01/01 (v19.2) update:`
			`- add support for color and flip augmentation to "Dreambooth LoRA"`
Update LoRA GUI Various improvements 2023-01-01 19:14:58 +00:00			`* 2023/01/01 (v19.1) update:`
			`- merge kohys_ss upstream code updates`
			`- rework Dreambooth LoRA GUI`
			`- fix bug where LoRA network weights were not loaded to properly resume training`
			`* 2022/12/30 (v19) update:`
Update readme 2022-12-31 01:50:01 +00:00			`- support for LoRA network training in kohya_gui.py.`
Update LoRA GUI Various improvements 2023-01-01 19:14:58 +00:00			`* 2022/12/23 (v18.8) update:`
- Fix for conversion tool issue when the source was an sd1.x diffuser model - Other minor code and GUI fix 2022-12-23 12:56:35 +00:00			`- Fix for conversion tool issue when the source was an sd1.x diffuser model`
			`- Other minor code and GUI fix`
Update LoRA GUI Various improvements 2023-01-01 19:14:58 +00:00			`* 2022/12/22 (v18.7) update:`
Add revision info 2022-12-22 18:19:28 +00:00			`- Merge dreambooth and finetune is a common GUI`
			`- General bug fixes and code improvements`
Update LoRA GUI Various improvements 2023-01-01 19:14:58 +00:00			`* 2022/12/21 (v18.6.1) update:`
fix issue with dataset balancing when the number of detected images in the folder is 0 2022-12-21 16:02:49 +00:00			`- fix issue with dataset balancing when the number of detected images in the folder is 0`

Update LoRA GUI Various improvements 2023-01-01 19:14:58 +00:00			`* 2022/12/21 (v18.6) update:`
Add authentication support 2022-12-21 14:05:06 +00:00			- add optional GUI authentication support via: `python fine_tune.py --username=<name> --password=<password>`