#55 · Primary category: Image Generation
kohya-colab
Accessible Google Colab notebooks for Stable Diffusion Lora training, based on the work of kohya-ss and Linaqruf
Project last updated:08/25/26
GitHub Stars
814
Forks
135
Contributors
6
License
GPL-3.0
Why we included this project
Training your own Stable Diffusion LoRA models usually means wrestling with a GPU setup, but this collection of Colab notebooks skips that entirely. It wraps the kohya-ss training scripts into one-click notebooks that run on Colab's free T4 tier or faster A100 instances, with separate trainers for SD 1.5 and SDXL. The Dataset Maker notebook is worth a look on its own: it scrapes images from Gelbooru, removes duplicates with FiftyOne, auto-tags them with a Waifu Diffusion tagger, and generates BLIP captions, so you can put together a clean training set without leaving the browser. Everything saves to Google Drive by default, which keeps the whole workflow simple for hobbyists and small teams fine-tuning anime or character styles. If you want results without managing infrastructure, this is a solid place to start.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.