mlsanityData to 7 Oct 2026

The Latent Color Subspace: Emergent Order in High-Dimensional Chaos

arXiv 2603.12261 ↗First posted 12 Mar 2026cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Text-to-image generation models have advanced rapidly, yet achieving fine-grained control over generated images remains difficult, largely due to limited understanding of how semantic information is encoded. We develop an interpretation of the color representation in the Variational Autoencoder latent space of FLUX.1 [Dev], revealing a structure reflecting Hue, Saturation, and Lightness. We verify our Latent Color Subspace (LCS) interpretation by demonstrating that it can both predict and explicitly control color, introducing a fully training-free method in FLUX based solely on closed-form latent-space manipulation. Code is available at https://github.com/ExplainableML/LCS.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 57 references that are in the map. First posted on arXiv 12 Mar 2026.

Builds on

44 of 57 references.

References · 44

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2022Scalable Diffusion Models with Transformerscited by 5,931
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  8. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  9. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  10. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  11. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  12. 2025Qwen-Image Technical Reportcited by 973
32 more
  1. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  2. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  3. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  4. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 854
  5. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 696
  6. 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attentioncited by 233
  7. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 115
  8. 2023PathLDM: Text conditioned Latent Diffusion Model for Histopathologycited by 51
  9. 2025ConceptAttention: Diffusion Transformers Learn Highly Interpretable Featurescited by 48
  10. 2024Towards a Mechanistic Explanation of Diffusion Model Generalizationcited by 42
  11. 2023SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesiscited by 41
  12. 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Modelscited by 35
  13. 2024Control Color: Multimodal Diffusion-based Interactive Image Colorizationcited by 33
  14. 2024textitRevelio: Interpreting and leveraging semantic information in diffusion modelscited by 29
  15. 2024ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglementcited by 28
  16. 2025Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretabilitycited by 26
  17. 2025Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformerscited by 24
  18. 2025Story2Board: A Training-Free Approach for Expressive Storyboard Generationcited by 16
  19. 2025Color Alignment in Diffusioncited by 10
  20. 2025DCEdit: Dual-Level Controlled Image Editing via Precisely Localized Semanticscited by 9
  21. 2025Stable Diffusion Models are Secretly Good at Visual In-Context Learningcited by 8
  22. 2025Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Modelscited by 7
  23. 2025Generative AI for Urban Planning: Synthesizing Satellite Imagery via Diffusion Modelscited by 7
  24. 2025Interpreting Large Text-to-Image Diffusion Models with Dictionary Learningcited by 6
  25. 2025CDST: Color Disentangled Style Transfer for Universal Style Reference Customizationcited by 6
  26. 2025SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutionscited by 6
  27. 2023Dequantization and Color Transfer with Diffusion Modelscited by 4
  28. 2025Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Datacited by 4
  29. 2025Controllable-Continuous Color Editing in Diffusion Model via Color Mappingcited by 4
  30. 2025Color encoding in Latent Space of Stable Diffusion Modelscited by 3
  31. 2026Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformerscited by 3
  32. 2025Stitch: Training-Free Position Control in Multimodal Diffusion Transformerscited by 2

Built on by

Not cited yet.