# Akegarasu/lora-scripts

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

Repository: https://github.com/Akegarasu/lora-scripts
Canonical: https://ross.abutalabs.com/products/lora-scripts
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: dreambooth, finetune, lora, stable-diffusion
Last push: 2026-08-21T16:02:55+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 8, longevity 94
- inputs: {"age_days": 1319, "days_push": 12, "days_rel": 697, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6110, forks 696 (observed 2026-08-28T04:09:35.981599+00:00)

## What it is
SD-Trainer is a GUI application and set of scripts for training LoRA and Dreambooth fine-tunes of Stable Diffusion diffusion models, wrapping kohya-ss's sd-scripts. It provides a one-click training environment with a web UI including Tensorboard, WD14 tagger, and tag editor.

## Use cases
- train a lora for stable diffusion
- fine-tune stable diffusion models with dreambooth
- gui for kohya sd-scripts training
- one-click lora training environment
- caption training images with wd14 tagger
- monitor training with tensorboard

## When to choose
- you want to train LoRA or Dreambooth models for Stable Diffusion without writing scripts
- you want an integrated GUI with tagging and Tensorboard in one place
- you are on Windows or Linux and want automated environment setup

## When to avoid
- you need to train models other than Stable Diffusion diffusion models
- you need a headless or fully scripted training pipeline without a GUI
- you want to train LLMs or non-image models

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, llm-training, gui, image-processing, developer-tools
- domain: machine-learning, deep-learning, image-processing, artificial-intelligence
- platform: windows, python
- tags: stable-diffusion, lora-training, dreambooth, kohya-ss, fine-tuning, diffusion-models, training-gui, tensorboard, linux, gpu

## Member repositories
- Akegarasu/lora-scripts (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:35.981599+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 2026-08-29T17:48:11.858266+00:00, confidence not recorded.
  - readme: https://github.com/Akegarasu/lora-scripts (fetched 2026-08-28T04:09:35.981599+00:00, sha 7efe131b0e26)
- Data as of 2026-08-30T08:39:29.467469+00:00.