mlsanityData to 7 Oct 2026

Demystifying Flux Architecture

arXiv 2507.09595 ↗First posted 13 Jul 2025cs.CVcited by 9

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 22 of its 26 references that are in the map. First posted on arXiv 13 Jul 2025.

Builds on

22 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  7. 2022Generative Adversarial Networkscited by 5,603
  8. 2022Flow Matching for Generative Modelingcited by 5,426
  9. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  10. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  11. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  12. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
9 more
  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  3. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  5. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  6. 2023Adversarial Diffusion Distillationcited by 741
  7. 2022On Distillation of Guided Diffusion Modelscited by 721
  8. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 276
  9. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 8.

9 papers.

  1. 2026LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generationcited by 6
  2. 2026MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animationcited by 3
  3. 2026Let It Be Simple: One-Step Action Generation for Vision-Language-Action Modelscited by 3
  4. 2025When and Where do Events Switch in Multi-Event Video Generation?cited by 1
  5. 2026VIAFormer: Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinementcited by 1
  6. 2026Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selectioncited by 0
  7. 2026UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generationcited by 0
  8. 2026TAMF-VTON: Texture-Aware Mask-Free Virtual Try-On via High-Fidelity Image Synthesiscited by 0
  9. 2026CompileRover: Revolutionizing Virtual Machine Compiler Optimization with a Tri-Role LLM-Driven Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Generative Modeling with Flux Matching
  2. 2024Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models
  3. 2025FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark
  4. 2025Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration
  5. 2025Few-Step Distillation for Text-to-Image Generation: A Practical Guide
  6. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?
  7. 2023SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation
  8. 2025FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing