KohakuBlueleaf/LyCORIS
Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.
This project helps artists, designers, and hobbyists who work with Stable Diffusion models to customize image generation. It takes a base Stable Diffusion model and specific images or concepts you want to teach it, then outputs a small, efficient add-on file. This file allows your Stable Diffusion setup to generate images with new styles, characters, or objects you've trained it on, without needing to retrain the entire large model.
2,488 stars. Actively maintained with 1 commit in the last 30 days.
Use this if you want to fine-tune Stable Diffusion to produce highly specific image content, styles, or subjects with better fidelity and flexibility than standard methods, and require compact model files.
Not ideal if you primarily use older image generation interfaces that may not support the latest LyCORIS model types, or if you only need very basic, broad image modifications.
Stars
2,488
Forks
173
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 12, 2026
Commits (30d)
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/KohakuBlueleaf/LyCORIS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related models
tsiendragon/qwen-image-finetune
Repo for Qwen Image Finetune
Akegarasu/lora-scripts
SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.
PRITHIVSAKTHIUR/Qwen-Image-Edit-2511-LoRAs-Fast-Lazy-Load
Demonstration for the Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters for advanced...
cloneofsimo/lora
Using Low-rank adaptation to quickly fine-tune diffusion models.
RedRayz/Kohya_lora_param_gui
GUI for kohya-ss sd-scripts