# KohakuBlueleaf/LyCORIS

Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

Repository: https://github.com/KohakuBlueleaf/LyCORIS
Canonical: https://ross.abutalabs.com/products/lycoris
Language: Python
License: Apache-2.0
License Family: permissive
Topics: finetune, stable-diffusion
Last push: 2026-07-23T10:49:50+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 35, longevity 91
- inputs: {"age_days": 1283, "days_push": 41, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2508, forks 181 (observed 2026-08-28T04:06:57.265085+00:00)

## What it is
LyCORIS is a Python library implementing parameter-efficient fine-tuning algorithms (LoRA/LoCon, LoHa, LoKr, IA3, DyLoRA, and more) for Stable Diffusion and similar diffusion models. It provides training utilities and integrations with popular Stable Diffusion UIs for creating compact model adaptations.

## Use cases
- train lora models for stable diffusion
- fine-tune stable diffusion with parameter-efficient methods
- create small adapter models for image generation
- compare loha vs lokr vs lora fine-tuning
- train stable diffusion adapters with limited gpu memory
- export lycoris models for use in a1111 webui

## When to choose
- you need alternatives to plain LoRA such as LoHa, LoKr, or DyLoRA for diffusion model fine-tuning
- you want compact fine-tuned adapters for Stable Diffusion with trade-off control over fidelity and flexibility
- you are training Stable Diffusion adaptations and need PyPI-installable tooling with webui integration

## When to avoid
- you need parameter-efficient fine-tuning for large language models rather than diffusion models
- you want full fine-tuning of all model weights without adapter methods
- you need a turnkey GUI training application rather than a library

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, llm-training, sdk
- domain: machine-learning, image-processing, deep-learning, artificial-intelligence
- platform: python, cross-platform
- tags: lora, stable-diffusion, parameter-efficient-fine-tuning, loha, lokr, dylora, diffusion-models, peft, gpu

## Member repositories
- KohakuBlueleaf/LyCORIS (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:57.265085+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:26:31.885103+00:00, confidence not recorded.
  - readme: https://github.com/KohakuBlueleaf/LyCORIS (fetched 2026-08-28T04:06:57.265085+00:00, sha 677ef6cada13)
- Data as of 2026-08-30T08:39:29.467469+00:00.