AI and models · Independent · 21 Oct 2026

black-forest-labs/flux2

Official inference repo for FLUX.2 models

← AI and models
FLUX.2 Inference. Run frontier visual intelligence models locally.

In simple English

This is the official code to run FLUX.2 image generation and editing models. You can create new images from text descriptions or edit existing ones. It runs on your own server or computer if you have enough graphics hardware. Some models are free to use for any purpose, while larger ones forbid commercial use. You need large model weights and technical knowledge to get it running.

What it is

This repository provides Python code to run inference for FLUX.2 text-to-image and image editing models. It includes scripts to generate images using command-line tools.

What it is good for

Solo developers and researchers who want to generate or edit high-quality images locally using open-weight models without relying on a third-party API.

Stars2.8k
LicenceApache-2.0
LatestNo tagged releasechecked 21 Oct 2026
Last code change2026-03-12
Written inPython
Setup effort
4 / 5
Payoff
4 / 5
Good
  • Includes models that generate images in under a second on modern consumer graphics cards.
  • Supports both text-to-image generation and single or multi-reference image editing.
  • Smaller 4B models use the Apache 2.0 licence for commercial freedom.
Watch for
  • Larger models require high-end graphics cards with substantial memory or specialized server hardware.
  • Some model weights use a non-commercial licence that forbids business use.
  • Requires downloading very large model weight files before you can generate anything.
Replaces

Closed commercial image generation APIs

Works well with

PyTorch

Similar repositories
  • Comfy-Org/ComfyUI141k stars

    A node-based graphical interface for running Stable Diffusion and FLUX models locally.

  • huggingface/diffusers35k stars

    A standard Python library for loading and running diffusion models like FLUX.

Also reviewed on Repo Radar
  • ggml-org/llama.cpp132k stars

    A C and C++ library and command-line tool for running language models locally.

  • EleutherAI/lm-evaluation-harness14k stars

    Runs standard question sets against a language model and reports the scores.

  • mudler/LocalAI50k stars

    Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.

Install
python3.12 -m venv .venv
source .venv/bin/activate
pip install -e . --extra-index-url https://download.pytorch.org/whl/cu129 --no-cache-dir

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: AI & Automation › AI Models & Inference › Image Models.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.