This repository provides a Windows-focused Gradio GUI for Kohya's Stable Diffusion trainers
https://github.com/bmaltais/kohya_ss
.vscode | ||
bitsandbytes_windows | ||
examples | ||
finetune | ||
library | ||
tools | ||
v2_inference | ||
.gitignore | ||
dreambooth_gui.py | ||
dreambooth.cmd | ||
fine_tune.py | ||
finetune_gui.py | ||
finetune.cmd | ||
kohya_gui.py | ||
kohya.cmd | ||
README_dreambooth.md | ||
README_finetune.md | ||
README.md | ||
requirements.txt | ||
setup.py | ||
style.css | ||
train_db.py | ||
upgrade.bat | ||
utilities.cmd |
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
Change history
-
12/21 (v18.6.1) update:
- fix issue with dataset balancing when the number of detected images in the folder is 0
-
12/21 (v18.6) update:
- add optional GUI authentication support via:
python fine_tune.py --username=<name> --password=<password>
- add optional GUI authentication support via: