# x-flux

Repository: https://github.com/XLabs-AI/x-flux
Canonical: https://ross.abutalabs.com/products/x-flux
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-11-08T10:11:45+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 54
- inputs: {"age_days": 758, "days_push": 663, "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 2229, forks 157 (observed 2026-08-28T04:06:29.009409+00:00)

## What it is
XLabs AI's training scripts for fine-tuning the FLUX.1 diffusion model with LoRA, ControlNet, and IP-Adapter adapters, using DeepSpeed and Accelerate. Includes a companion ComfyUI repository with workflows and pretrained checkpoints for inference.

## Use cases
- train a lora for flux.1 dev
- train a controlnet for flux
- fine-tune flux on my own images
- use flux controlnet in comfyui
- download pretrained flux ip-adapter checkpoints
- run flux lora inference

## When to choose
- you want to fine-tune FLUX.1 [dev] with LoRA or ControlNet
- you need pretrained Flux adapters (Canny, Depth, HED ControlNet, IP-Adapter, LoRAs)
- you want ComfyUI workflows for Flux adapters

## When to avoid
- you need training for models other than FLUX.1
- you lack a GPU or PyTorch 2.1+ environment
- you need actively maintained code - the last release was November 2024

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-training, stable-diffusion, machine-learning, deep-learning
- domain: machine-learning, deep-learning, image-processing, artificial-intelligence
- platform: python
- tags: flux, lora, controlnet, ip-adapter, deepspeed, diffusion-models, comfyui, fine-tuning, image-generation, gpu, linux

## Member repositories
- XLabs-AI/x-flux (main) score 23
- XLabs-AI/x-flux-comfyui (plugin) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.009409+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 2026-08-30T02:44:39.425096+00:00, confidence not recorded.
  - readme: https://github.com/XLabs-AI/x-flux (fetched 2026-08-28T04:06:29.009409+00:00, sha 942ab611684a)
- Data as of 2026-08-30T08:39:29.467469+00:00.