Demystifying Flux Architecture

TL;DR

This paper reverse-engineers the FLUX diffusion model to reveal its architecture, aiding future research despite the lack of official documentation, and demonstrates its state-of-the-art performance in text-to-image generation.

Contribution

It provides the first detailed technical analysis of FLUX's architecture through source code reverse-engineering, facilitating its adoption in research.

Findings

FLUX outperforms Midjourney, DALL-E 3, SD3, and SDXL in text-to-image tasks.

The report offers an unofficial, detailed architecture overview of FLUX.

It enables future research by clarifying the model's design despite limited official info.

Abstract

FLUX.1 is a diffusion-based text-to-image generation model developed by Black Forest Labs, designed to achieve faithful text-image alignment while maintaining high image quality and diversity. FLUX is considered state-of-the-art in text-to-image generation, outperforming popular models such as Midjourney, DALL-E 3, Stable Diffusion 3 (SD3), and SDXL. Although publicly available as open source, the authors have not released official technical documentation detailing the model's architecture or training setup. This report summarizes an extensive reverse-engineering effort aimed at demystifying FLUX's architecture directly from its source code, to support its adoption as a backbone for future research and development. This document is an unofficial technical report and is not published or endorsed by the original developers or their affiliated institutions.