stable diffusion finetuned on weeb stuff

Go to file

Carlos Chavez d600078008 Add options and local inference Added options to: - Disable Inference (it consumes about 2gb of VRAM even when not active) - Disable wandb and: - if no hftoken is provided it just fills it with nothing so it doesn't argues - if wandb is not enabled, save the inference outputs to a local folder along with information about it		2022-11-14 22:08:16 -05:00
dataset	Add aesthetic	2022-11-10 13:01:11 -07:00
trainer	Add options and local inference	2022-11-14 22:08:16 -05:00
.gitmodules	relicense	2022-11-10 12:59:53 -07:00
Dockerfile	relicense	2022-11-10 12:59:53 -07:00
LICENSE	relicense	2022-11-10 12:59:53 -07:00
README.md	relicense	2022-11-10 12:59:53 -07:00
requirements.txt	relicense	2022-11-10 12:59:53 -07:00

README.md

Waifu Diffusion

Waifu Diffusion is the name for this project of finetuning Stable Diffusion on anime-styled images.

_{1girl, aqua eyes, baseball cap, blonde hair, closed mouth, earrings, green background, hat, hoop earrings, jewelry, looking at viewer, shirt, short hair, simple background, solo, upper body, yellow shirt}

Setup

pip install -r requirements.txt

Project Structure

├── dataset: Dataset preparation and utilities
│   ├── aesthetic: Aesthetic ranking
│   └── download: Downloading utilities
└── trainer: The actual training code

License

Training Code: AGPL-3.0 Model Weights: CreativeML Open RAIL-M