StableDiffusion/KohyaSS
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
This repository provides a Windows-focused Gradio GUI for Kohya's Stable Diffusion trainers https://github.com/bmaltais/kohya_ss
114 Commits 1 Branch 0 Tags 3.5 MiB
Python 97.6%
Shell 2.1%
Batchfile 0.2%
PowerShell 0.1%
34f7cd8e57
Go to file
bmaltais 34f7cd8e57 Add new Utility to Extract a LoRA from a finetuned model
2023-01-06 18:25:55 -05:00
.vscode Update Utilities logic 2022-12-15 18:34:54 -05:00
bitsandbytes_windows Merge latest kohya_ss code update 2023-01-01 13:10:32 -05:00
examples Update LoRA GUI 2023-01-01 14:14:58 -05:00
finetune Add LoRA support from sd_script repo 2022-12-26 08:47:33 -05:00
library Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00
networks Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00
tools - Add support for --clip_skip option 2023-01-05 19:16:13 -05:00
v2_inference Adding example for SDv2 2022-11-27 16:07:26 -05:00
.gitignore Add LoRA support from sd_script repo 2022-12-26 08:47:33 -05:00
dreambooth_gui.py Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00
fine_tune.py Merge latest kohya_ss code update 2023-01-01 13:10:32 -05:00
finetune_gui.py Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00
gen_img_diffusers.py Merge latest kohya_ss code update 2023-01-01 13:10:32 -05:00
gui.cmd - Add support for --clip_skip option 2023-01-05 19:16:13 -05:00
kohya_gui.py Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00
lora_gui.py Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00
README_dreambooth.md - Fix for conversion tool issue when the source was an sd1.x diffuser model 2022-12-23 07:56:35 -05:00
README_finetune.md - Fix for conversion tool issue when the source was an sd1.x diffuser model 2022-12-23 07:56:35 -05:00
README_train_network-ja.md Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00
README_train_network.md !st rough implementation of LoRA GUI 2022-12-28 23:02:35 -05:00
README.md Add new Utility to Extract a LoRA from a finetuned model 2023-01-06 18:25:55 -05:00
requirements.txt Fix requirements file 2022-12-19 09:26:04 -05:00
setup.py Implement open and save config for LoRA 2022-12-29 14:00:02 -05:00
style.css Add new Utilities Tab 2022-12-15 18:19:35 -05:00
train_db.py - Fix for conversion tool issue when the source was an sd1.x diffuser model 2022-12-23 07:56:35 -05:00
train_network.py Merge latest kohya_ss code update 2023-01-01 13:10:32 -05:00
utilities.cmd Update GUI and Readme 2022-12-22 13:14:46 -05:00

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

Finetune

You can find the finetune solution spercific Finetune README

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>