# kohya-ss/sd-scripts

Repository: https://github.com/kohya-ss/sd-scripts
Canonical: https://ross.abutalabs.com/products/sd-scripts
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-02T07:14:15+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 77, longevity 96
- inputs: {"age_days": 1354, "days_push": 31, "days_rel": 79, "gap_med": 35, "n_releases_24m": 10}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7210, forks 1217 (observed 2026-08-28T04:09:56.653364+00:00)

## What it is
A collection of Python training, generation, and utility scripts for Stable Diffusion and other image generation models, most widely used for LoRA fine-tuning. It supports many diffusion model architectures and runs on Windows and Linux with GPU acceleration.

## Use cases
- train a lora for stable diffusion
- fine-tune an image generation model on my own images
- generate images with a trained diffusion checkpoint
- prepare and caption a dataset for diffusion model training
- train a controlnet llite model
- convert stable diffusion checkpoints between formats

## When to choose
- you want to fine-tune Stable Diffusion or similar models, especially LoRA training
- you need a battle-tested CLI workflow for dataset preparation, training, and generation
- you want broad support for many diffusion model architectures on consumer GPUs

## When to avoid
- you need a graphical training interface rather than command-line scripts
- you are training large language models or non-image models
- you want a simple one-click hosted service instead of local tooling

## Facets
- artifact type: cli-tool
- maturity: active
- function: llm-training, machine-learning, image-processing, gpu-computing, developer-tools
- domain: image-processing, machine-learning, deep-learning, artificial-intelligence
- platform: windows, python, cli
- tags: stable-diffusion, lora-training, fine-tuning, dreambooth, diffusion-models, image-generation, linux, gpu

## Member repositories
- kohya-ss/sd-scripts (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:56.653364+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 2026-08-29T17:39:50.558481+00:00, confidence not recorded.
  - readme: https://github.com/kohya-ss/sd-scripts (fetched 2026-08-28T04:09:56.653364+00:00, sha 89b6f939e6af)
- Data as of 2026-08-30T08:39:29.467469+00:00.