mlsanityData to 14 Oct 2026

FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers

arXiv 2412.09611 ↗First posted 12 Dec 2024cs.CVcited by 27

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

Abstract (arXiv)

Rectified flow models have emerged as a dominant approach in image generation, showcasing impressive capabilities in high-quality image synthesis. However, despite their effectiveness in visual generation, rectified flow models often struggle with disentangled editing of images. This limitation prevents the ability to perform precise, attribute-specific modifications without affecting unrelated aspects of the image. In this paper, we introduce FluxSpace, a domain-agnostic image editing method leveraging a representation space with the ability to control the semantics of images generated by rectified flow transformers, such as Flux. By leveraging the representations learned by the transformer blocks within the rectified flow models, we propose a set of semantically interpretable representations that enable a wide range of image editing tasks, from fine-grained image editing to artistic creation. This work offers a scalable and effective image editing approach, along with its disentanglement capabilities.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 15 of its 45 references that are in the map. First posted on arXiv 12 Dec 2024.

Builds on

15 of 45 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIP1 Jun
  2. 2024Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Models28 Mar
  3. 2024Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions25 Mar
  4. 2023Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models20 Nov
  5. 2023SEGA: Instructing Text-to-Image Models using Semantic Guidance28 Jan
  6. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov

Other references · 9

  1. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  2. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  3. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  4. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  5. 2022Diffusion Models already have a Semantic Latent Spacecited by 328
  6. 2018DeepFakes: a New Threat to Face Recognition? Assessment and Detectioncited by 209
  7. 2023NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Modelscited by 47
  8. 2015Sparse Overcomplete Word Vector Representationscited by 44
  9. 2024Interpreting the Weight Space of Customized Diffusion Modelscited by 36

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 14; 2026: 13.

27 papers.

Sort:

By area:

  1. 2025ConceptAttention: Diffusion Transformers Learn Highly Interpretable Featurescited by 52
  2. 2025EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editingcited by 45
  3. 2025UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Modelscited by 39
  4. 2025Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editingcited by 17
  5. 2025WordCon: Word-level Typography Control in Scene Text Renderingcited by 16
  6. 2025LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformerscited by 12
  7. 2025PairEdit: Learning Semantic Variations for Exemplar-based Image Editingcited by 8
  8. 2025Flow Straight and Fast in Hilbert Space: Functional Rectified Flowcited by 6
  9. 2026The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steeringcited by 6
  10. 2025Taming Flow-based I2V Models for Creative Video Editingcited by 5
  11. 2026Continuous Control of Editing Models via Adaptive-Origin Guidancecited by 5
  12. 2025DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editingcited by 4
15 more
  1. 2026TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Modelscited by 4
  2. 2025SEED: A Benchmark Dataset for Sequential Facial Attribute Editing with Diffusion Modelscited by 3
  3. 2026On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformerscited by 3
  4. 2026Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generationcited by 3
  5. 2025Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field Samplingcited by 2
  6. 2025The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusioncited by 2
  7. 2025RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image Alignmentcited by 1
  8. 2026FusionEdit: Semantic Fusion and Attention Modulation for Training-Free Image Editingcited by 0
  9. 2026Rethinking Global Text Conditioning in Diffusion Transformerscited by 0
  10. 2026Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulationcited by 0
  11. 2026Token-to-Token Alignment of Text Embeddings for Semantic Blendingcited by 0
  12. 2026Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Modelscited by 0
  13. 2026AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flowcited by 0
  14. 2026SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editingcited by 0
  15. 2026Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllerscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
  2. 2024Latent Space Disentanglement in Diffusion Transformers Enables Zero-shot Fine-grained Semantic Editing
  3. 2025SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
  4. 2024Latent Space Disentanglement in Diffusion Transformers Enables Precise Zero-shot Semantic Editing
  5. 2026DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
  6. 2025LORE: Latent Optimization for Precise Semantic Control in Rectified Flow-based Image Editing
  7. 2023Latent Space Editing in Transformer-Based Flow Matching
  8. 2026SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editing