The ultimate training toolkit for finetuning diffusion models
Go to file
Jaret Burkett 3f4f429c4a Reworked the balancing and swapping of the lora during training to make it much more stable when trained 2023-07-22 14:13:39 -06:00
config/examples Removed train config, updating it, and added my llvae as pytorch model 2023-07-20 14:12:28 -06:00
jobs Reworked the balancing and swapping of the lora during training to make it much more stable when trained 2023-07-22 14:13:39 -06:00
repositories Made a very basic vae trainer. 2023-07-17 19:03:50 -06:00
scripts WIP implementing training 2023-07-12 08:23:46 -06:00
testing Handle conversions back to ldm for saving 2023-07-18 19:34:35 -06:00
toolkit Base for loopback lora training setup, still working on proper sliders 2023-07-21 18:26:02 -06:00
.gitignore Initial commit 2023-07-05 16:44:58 -06:00
.gitmodules Made a very basic vae trainer. 2023-07-17 19:03:50 -06:00
README.md WIP implementing training 2023-07-12 08:23:46 -06:00
info.py Reworked so everything is in classes for easy expansion. Single entry point for all config files now. 2023-07-08 09:51:42 -06:00
requirements.txt Base for loopback lora training setup, still working on proper sliders 2023-07-21 18:26:02 -06:00
run.py Fixed issues with vgg19 preprocessing. Added yaml support on config file 2023-07-19 06:12:57 -06:00

README.md

AI Toolkit by Ostris

WIP for now, but will be a collection of tools for AI tools as I need them.

Installation

I will try to update this to be more beginner-friendly, but for now I am assuming a general understanding of python, pip, pytorch, and using virtual environments:

Linux:

git submodule update --init --recursive
pythion3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
cd requirements/sd-scripts
pip install --no-deps -e .
cd ../..

Windows:

git submodule update --init --recursive
pythion3 -m venv venv
venv\Scripts\activate
pip install -r requirements.txt
cd requirements/sd-scripts
pip install --no-deps -e .
cd ../..

Current Tools

LyCORIS extractor

It is similar to the LyCORIS tool, but adding some QOL features. It all runs off a config file, which you can find an example of in config/examples/locon_config.example.json. Just copy that file, into the config folder, and rename it to whatever_you_want.json. Then you can edit the file to your liking. and call it like so:

python3 run.py "whatever_you_want"

You can also put a full path to a config file, if you want to keep it somewhere else.

python3 run.py "/home/user/whatever_you_want.json"

File name is auto generated and dumped into the output folder. You can put whatever meta you want in the meta section of the config file, and it will be added to the metadata of the output file. I just have some recommended fields in the example file. The script will add some other useful metadata as well.

process is an array or different processes to run on the conversion to test. You will normally just need one though.

Will update this later.