# Linaqruf/kohya-trainer

Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning

Repository: https://github.com/Linaqruf/kohya-trainer
Canonical: https://ross.abutalabs.com/products/kohya-trainer
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2024-05-14T06:25:38+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 98
- inputs: {"age_days": 1382, "days_push": 841, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1899, forks 327 (observed 2026-08-28T04:05:51.432172+00:00)

## What it is
A collection of Jupyter/Colab notebooks adapting kohya-ss's sd-scripts for training Stable Diffusion models, including LoRA and Dreambooth methods. It packages the training scripts for easy one-click use in Google Colab.

## Use cases
- train a LoRA for stable diffusion
- fine-tune stable diffusion on my own images
- run dreambooth training in colab
- create a custom stable diffusion checkpoint
- train lora without a local gpu
- learn how kohya sd-scripts training works

## When to choose
- you want notebook-based, low-setup LoRA or Dreambooth training in Google Colab
- you are a beginner who prefers guided cells over CLI scripts
- you want to experiment with stable diffusion fine-tuning without installing anything locally

## When to avoid
- you need the latest upstream features or bug fixes from kohya-ss/sd-scripts
- you want a production training pipeline or CLI tooling
- you train models other than stable diffusion

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-training, machine-learning, deep-learning
- domain: machine-learning, deep-learning, image-processing
- platform: python, cloud
- tags: stable-diffusion, lora, dreambooth, jupyter-notebook, google-colab, fine-tuning, model-training, gpu

## Member repositories
- Linaqruf/kohya-trainer (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:51.432172+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 2026-08-30T03:12:06.930942+00:00, confidence not recorded.
  - readme: https://github.com/Linaqruf/kohya-trainer (fetched 2026-08-28T04:05:51.432172+00:00, sha 09ae91b4b266)
- Data as of 2026-08-30T08:39:29.467469+00:00.