AI Model Fine-tuning Library
2.5k 2026-04-18

KohakuBlueleaf/LyCORIS

A library implementing various parameter-efficient fine-tuning (PEFT) algorithms, including advanced LoRA variants, for Stable Diffusion models to enhance image generation.

Core Features

Implements diverse PEFT algorithms (LoRA, LoHa, LoKr, etc.).
Seamless integration with popular Stable Diffusion UIs (A1111, ComfyUI).
Supports flexible training methods (kohya-ss scripts, standalone PyTorch).
Optimizes model size and training speed while maintaining quality.

Quick Start

pip install lycoris-lora

Detailed Introduction

LyCORIS is an advanced open-source project dedicated to parameter-efficient fine-tuning (PEFT) of Stable Diffusion models. It extends beyond conventional LoRA methods by integrating a suite of innovative rank adaptation implementations such as LoHa, LoKr, and DyLoRA. This project empowers users to efficiently customize Stable Diffusion models, achieving superior results in image generation with reduced computational overhead and model size. It integrates seamlessly with popular Stable Diffusion interfaces and training scripts, making advanced fine-tuning accessible to a broader community.

OSS Alternative

Explore the best open source alternatives to commercial software.

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