KohakuBlueleaf/LyCORIS - OSS Alternative - Discover Top Open Source Alternatives to Popular Software
AI Model Fine-tuning Library
2.5k 2026-05-01

KohakuBlueleaf/LyCORIS

LyCORIS is a library implementing various parameter-efficient fine-tuning (PEFT) algorithms for Stable Diffusion, extending beyond conventional LoRA methods to enhance model adaptation.

Core Features

Offers diverse PEFT algorithms including LoRA, LoHa, LoKr, (IA)^3, and DyLoRA.
Seamless integration with popular Stable Diffusion UIs like AUTOMATIC1111's webui and ComfyUI.
Supports flexible training via kohya-ss/sd-scripts, Naifu-Diffusion, or standalone PyTorch wrappers.
Provides comparative insights into algorithm performance across key metrics.

Quick Start

pip install lycoris-lora

Detailed Introduction

LyCORIS, an evolution from the LoCon project, is a crucial open-source initiative aimed at advancing parameter-efficient fine-tuning for Stable Diffusion models. It addresses the limitations of traditional LoRA by integrating and comparing a spectrum of advanced algorithms like LoHa and LoKr. This project empowers users to achieve superior model adaptation, offering greater flexibility, fidelity, and diversity in AI art generation while optimizing model size and training efficiency. Its broad compatibility with existing Stable Diffusion ecosystems makes it an indispensable tool for researchers and creators alike.

OSS Alternative

Explore the best open source alternatives to commercial software.

© 2026 OSS Alternative. hotgithub.com - All rights reserved.