Kohya Colabs

Accessible Google Colab notebooks for Stable Diffusion Lora training, based on the work of kohya-ss and Linaqruf.

If you need support I now have a public Discord server

Able to scrape hundreds of images from the popular anime gallery Gelbooru, that match the conditions set by the user.
Finds duplicate images using the FiftyOne open-source software.
Displays the user's dataset back to them through the FiftyOne interface so that they may manually curate their images.
Able to generate tags for all your anime images using the Waifu Diffusion 1.4 Tagger model.
Able to generate captions for all your images using the BLIP model.
Gives you the ability to edit hundreds of text files at once, to add/remove/replace tags inside them dynamically.
Works inside your Google Drive by default.
Connects easily with Lora Trainer.

Can train LoRA and LoCon for Stable Diffusion 1.5, includes a few model options for anime.
One click to install and start training.
Offers all useful training parameters while keeping it simple and accessible.
Helpful parameter descriptions and runtime messages.
Allows you to optionally define multiple folders for training.
Uses the latest technologies to load and train quickly.
Works inside your Google Drive by default and connects easily with Dataset Maker.

Can train LoRA and LoCon for Stable Diffusion XL, includes a few model options for anime.
One click to install and start training.
Can work with multiple colab configurations, including T4 (free) and A100.
Offers most parameters while setting useful values behind the scenes to keep it simple.
Allows you to optionally define multiple folders for training.
Uses the latest technologies to load and train quickly.
Works inside your Google Drive by default and connects easily with Dataset Maker.

haje01 / kohya-colab Goto Github PK