# kijai/ComfyUI-FluxTrainer

Repository: https://github.com/kijai/ComfyUI-FluxTrainer
Canonical: https://ross.abutalabs.com/products/comfyui-fluxtrainer
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-04-02T07:35:46+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 14, release rhythm 35, longevity 53
- inputs: {"age_days": 748, "days_push": 518, "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 1160, forks 107 (observed 2026-08-28T04:03:49.156165+00:00)

## What it is
A ComfyUI custom node plugin that wraps kohya's sd-scripts to enable LoRA, LyCORIS, and full fine-tune training of FLUX models directly inside ComfyUI workflows. It lets users train with the same models and Python environment they already use for inference.

## Use cases
- train a flux lora from my own image dataset
- fine-tune stable diffusion models inside comfyui
- create lycoris training workflows with a node interface
- compare training settings using comfyui workflows
- run kohya sd-scripts training without leaving comfyui

## When to choose
- you already use ComfyUI and want to train FLUX LoRAs in the same environment
- you want to build training workflows alongside inference with the same models
- you want a node-based wrapper around kohya's training scripts

## When to avoid
- you need stable, well-tested training tooling - the project is explicitly experimental
- you want training support or guidance - the author explicitly does not provide training advice
- you don't use ComfyUI and prefer standalone training scripts

## Facets
- artifact type: plugin
- maturity: experimental
- function: llm-training, machine-learning, ui-components
- domain: machine-learning, image-processing, developer-tools
- platform: python, cross-platform
- tags: comfyui, stable-diffusion, flux, lora-training, lycoris, fine-tuning, kohya, custom-nodes, gpu

## Member repositories
- kijai/ComfyUI-FluxTrainer (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:49.156165+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 2026-08-30T06:31:48.745521+00:00, confidence not recorded.
  - readme: https://github.com/kijai/ComfyUI-FluxTrainer (fetched 2026-08-28T04:03:49.156165+00:00, sha 17755b66e503)
- Data as of 2026-08-30T08:39:29.467469+00:00.