# cocktailpeanut/fluxgym

Dead simple FLUX LoRA training UI with LOW VRAM support

Repository: https://github.com/cocktailpeanut/fluxgym
Canonical: https://ross.abutalabs.com/products/fluxgym
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-28T05:07:19+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 35, longevity 51
- inputs: {"age_days": 727, "days_push": 36, "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 3246, forks 371 (observed 2026-08-28T04:07:50.655237+00:00)

## What it is
FluxGym is a simple web UI for training FLUX LoRA models with low VRAM support (12GB/16GB/20GB). It combines the AI-Toolkit Gradio frontend with Kohya sd-scripts as the training backend.

## Use cases
- train a flux lora with a simple ui
- fine-tune flux on low vram gpu
- train image model lora without command line
- train custom character lora for stable diffusion
- publish trained lora to huggingface

## When to choose
- you have 12-20GB VRAM and want to train FLUX LoRAs
- you want a simple UI over Kohya sd-scripts
- you want automatic model downloads and Huggingface publishing

## When to avoid
- you need to train models other than FLUX-family image models
- you need multi-GPU or large-scale training infrastructure
- you prefer fully scriptable headless training pipelines

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, llm-training, gui, image-processing
- domain: machine-learning, image-processing, artificial-intelligence
- platform: python, self-hosted, cross-platform
- tags: flux, lora-training, stable-diffusion, gradio, low-vram, kohya, fine-tuning, webui, docker, gpu

## Member repositories
- cocktailpeanut/fluxgym (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:50.655237+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 2026-08-30T07:24:28.410616+00:00, confidence not recorded.
  - readme: https://github.com/cocktailpeanut/fluxgym (fetched 2026-08-28T04:07:50.655237+00:00, sha 2eda75279588)
- Data as of 2026-08-30T08:39:29.467469+00:00.