# cloneofsimo/lora

Using Low-rank adaptation to quickly fine-tune diffusion models.

Repository: https://github.com/cloneofsimo/lora
Canonical: https://ross.abutalabs.com/products/cloneofsimo-lora
Homepage: https://arxiv.org/abs/2106.09685
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: diffusion, lora, stable-diffusion, dreambooth, fine-tuning
Last push: 2024-03-22T03:48:10+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 97
- inputs: {"age_days": 1365, "days_push": 894, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7550, forks 495 (observed 2026-08-28T04:10:01.543252+00:00)

## What it is
A Python library for applying Low-Rank Adaptation (LoRA) to quickly fine-tune text-to-image diffusion models like Stable Diffusion. It produces tiny (1-6MB) adapter checkpoints, supports merging LoRAs, pivotal tuning inversion, and is compatible with Hugging Face diffusers.

## Use cases
- fine-tune stable diffusion on my own images
- train a lora for a specific art style
- create small diffusion model adapters instead of full checkpoints
- merge multiple lora checkpoints together
- run dreambooth training faster and cheaper
- do pivotal tuning inversion with textual inversion plus lora
- fine-tune stable diffusion inpainting model

## When to choose
- you want fast, memory-efficient fine-tuning of Stable Diffusion with tiny shareable results
- you work with the Hugging Face diffusers ecosystem and want LoRA support
- you need to merge or compose multiple fine-tuned adapters

## When to avoid
- you need actively maintained tooling - LoRA is now integrated into diffusers and this repo sees limited updates
- you fine-tune models other than diffusion-based text-to-image models
- you want a GUI-only training experience

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-training, machine-learning, deep-learning, image-processing
- domain: machine-learning, deep-learning, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: lora, stable-diffusion, dreambooth, fine-tuning, diffusion-models, text-to-image, low-rank-adaptation, diffusers, gpu

## Member repositories
- cloneofsimo/lora (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:01.543252+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 2026-08-29T17:37:23.787154+00:00, confidence not recorded.
  - readme: https://github.com/cloneofsimo/lora (fetched 2026-08-28T04:10:01.543252+00:00, sha cd587a0f8e0c)
  - homepage: https://arxiv.org/abs/2106.09685 (fetched 2026-08-29T08:32:27.555005+00:00, sha c197a338f969)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T08:32:27.557612+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T08:32:27.560963+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T08:32:27.562833+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T08:32:27.559273+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.