Demystifying Flux.1

An unofficial documentation of FLUX.1 text-to-image architecture

Or Greenberg^1,2   

¹ General Motors R&D  |  ² Hebrew University of Jerusalem, Israel

⚠️ This is an unofficial and reverse-engineered documentation project. It is not affiliated with the original authors or organizations behind FLUX.1.

If you find this work useful, please cite our technical report and give this repo a star ⭐

---

📄 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

---

@article{greenebrg2025demystifying,
    title     = {Demystifying Flux Architecture}, 
    author    = {Or Greenebrg},
    eprint    = {2507.09595},
    archivePrefix      = {2025},
    booktitle = {arXiv}
}