mlsanityData to 14 Oct 2026

UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models

arXiv 2504.13109 ↗First posted 17 Apr 2025cs.CVcited by 39

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

Abstract (arXiv)

Flow matching models have emerged as a strong alternative to diffusion models, but existing inversion and editing methods designed for diffusion are often ineffective or inapplicable to them. The straight-line, non-crossing trajectories of flow models pose challenges for diffusion-based approaches but also open avenues for novel solutions. In this paper, we introduce a predictor-corrector-based framework for inversion and editing in flow models. First, we propose Uni-Inv, an effective inversion method designed for accurate reconstruction. Building on this, we extend the concept of delayed injection to flow models and introduce Uni-Edit, a region-aware, robust image editing approach. Our methodology is tuning-free, model-agnostic, efficient, and effective, enabling diverse edits while ensuring strong preservation of edit-irrelevant regions. Extensive experiments across various generative models demonstrate the superiority and generalizability of Uni-Inv and Uni-Edit, even under low-cost settings. Project page: https://uniedit-flow.github.io/

Key facts. Cited by 39 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 83 of its 98 references that are in the map. First posted on arXiv 17 Apr 2025.

Builds on

83 of 98 references.

Closest ancestors · 34

Same direction, newest first

  1. 2025InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework16 Apr
  2. 2024Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection14 Dec
  3. 2024FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers12 Dec
  4. 2024FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing10 Dec
  5. 2024Stable Flow: Vital Layers for Training-Free Image Editing21 Nov
  6. 2024OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision11 Nov
  7. 2024SeedEdit: Align Image Re-Generation to Image Editing11 Nov
  8. 2024Taming Rectified Flow for Inversion and Editing7 Nov
  9. 2024Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations14 Oct
  10. 2024SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing16 Sep
  11. 2024TurboEdit: Instant text-based image editing14 Aug
  12. 2024RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance23 May
22 more
  1. 2024MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation17 Apr
  2. 2024ReNoise: Real Image Inversion Through Iterative Noising21 Mar
  3. 2023Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models19 Dec
  4. 2023Latent Space Editing in Transformer-Based Flow Matching17 Dec
  5. 2023Inversion-Free Image Editing with Natural Language7 Dec
  6. 2023LEDITS++: Limitless Image Editing using Text-to-Image Models28 Nov
  7. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models13 Aug
  8. 2023LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance2 Jul
  9. 2023Improving Tuning-Free Real Image Editing with Proximal Guidance8 Jun
  10. 2023FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention17 May
  11. 2023Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models8 May
  12. 2023An Edit Friendly DDPM Noise Space: Inversion and Manipulations12 Apr
  13. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation16 Feb
  14. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  15. 2022Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models16 Dec
  16. 2022InstructPix2Pix: Learning to Follow Image Editing Instructions17 Nov
  17. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov
  18. 2022DiffEdit: Diffusion-based semantic image editing with mask guidance20 Oct
  19. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  20. 2022Blended Latent Diffusion6 Jun
  21. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  22. 2021Blended Diffusion for Text-driven Editing of Natural Images29 Nov

Other references · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2022Scalable Diffusion Models with Transformerscited by 6,054
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  9. 2022Flow Matching for Generative Modelingcited by 5,702
  10. 2022Generative Adversarial Networkscited by 5,627
  11. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
37 more
  1. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  2. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  3. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  4. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  5. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  6. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  7. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
  8. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  9. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  10. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 906
  11. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  12. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  13. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  14. 2023Zero-shot Image-to-Image Translationcited by 505
  15. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 395
  16. 2024UltraEdit: Instruction-based Fine-Grained Image Editing at Scalecited by 268
  17. 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 258
  18. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Modelscited by 255
  19. 2024FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Modelscited by 217
  20. 2022Splicing ViT Features for Semantic Appearance Transfercited by 209
  21. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 194
  22. 2024HQ-Edit: A High-Quality Dataset for Instruction-based Image Editingcited by 193
  23. 2024PnP-Flow: Plug-and-Play Image Restoration with Flow Matchingcited by 97
  24. 2024Classifier-Free Guidance is a Predictor-Correctorcited by 84
  25. 2023Open-vocabulary Object Segmentation with Diffusion Modelscited by 82
  26. 2024Rectified Diffusion: Straightness Is Not Your Need in Rectified Flowcited by 61
  27. 2022FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Contextcited by 49
  28. 2023Exact Diffusion Inversion via Bi-directional Integration Approximationcited by 44
  29. 2024Steering Rectified Flow Models in the Vector Field for Controlled Image Generationcited by 39
  30. 2024Text-to-Image Rectified Flow as Plug-and-Play Priorscited by 38
  31. 2024BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Modelscited by 29
  32. 2024MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation modelscited by 23
  33. 2023MDP: A Generalized Framework for Text-Guided Image Editing by Manipulating the Diffusion Pathcited by 18
  34. 2024Stochastic Sampling from Deterministic Flow Modelscited by 18
  35. 2023LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detectioncited by 13
  36. 2023CCD-3DR: Consistent Conditioning in Diffusion for Single-Image 3D Reconstructioncited by 10
  37. 2024Leveraging Previous Steps: A Training-free Fast Solver for Flow Diffusioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 16; 2026: 23.

39 papers.

Sort:

By area:

  1. 2025Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editingcited by 17
  2. 2025SAEdit: Token-level control for continuous image editing via Sparse AutoEncodercited by 9
  3. 2025AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flowscited by 9
  4. 2025TrajFlow: Multi-modal Motion Prediction via Flow Matchingcited by 8
  5. 2025Zero-Shot Dynamic Concept Personalization with Grid-Based LoRAcited by 7
  6. 2025ConsistEdit: Highly Consistent and Precise Training-free Visual Editingcited by 6
  7. 2025ProEdit: Inversion-based Editing From Prompts Done Rightcited by 6
  8. 2026Object-WIPER : Training-Free Object and Associated Effect Removal in Videoscited by 6
  9. 2025Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformercited by 5
  10. 2026Improving Robotic Generalist Policies via Flow Reversal Steeringcited by 5
  11. 2025DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editingcited by 4
  12. 2025LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondencecited by 4
27 more
  1. 2025SONIC: Spectral Optimization of Noise for Inpainting with Consistencycited by 4
  2. 2025LORE: Latent Optimization for Precise Semantic Control in Rectified Flow-based Image Editingcited by 3
  3. 2025FlowOpt: Fast Optimization Through Whole Flow Processes for Training-Free Editingcited by 3
  4. 2026SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editingcited by 3
  5. 2025The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergycited by 2
  6. 2026Free Lunch for Stabilizing Rectified Flow Inversioncited by 2
  7. 2026StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generationcited by 2
  8. 2025FlowSteer: Conditioning Flow Field for Consistent Image Restorationcited by 1
  9. 2025ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attentioncited by 1
  10. 2026Recolour What Matters: Region-Aware Colour Editing via Token-Level Diffusioncited by 1
  11. 2026AdaEdit: Adaptive Temporal and Channel Modulation for Flow-Based Image Editingcited by 1
  12. 2026Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapescited by 1
  13. 2026FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editingcited by 1
  14. 2026Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Offcited by 0
  15. 20263DPhysVideo: Consistency-Guided Flow SDE for Video Generation via 3D Scene Reconstruction and Physical Simulationcited by 0
  16. 2026Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editingcited by 0
  17. 2026Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightnesscited by 0
  18. 2026h-Flow: Flexible Flow-based Image Editing via Doob's h-Transformcited by 0
  19. 2026Motion4Motion: Motion Transfer Across Subjects at Inferencecited by 0
  20. 2026SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversioncited by 0
  21. 2026RIDGE: Re-Noising with Internal Dynamic Guidance for Image Editingcited by 0
  22. 2026OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylizationcited by 0
  23. 2026Object-Aware Background-Controlled Editing via Weighted Velocity Guidancecited by 0
  24. 2026Paint-Anything: Unified Any-Color Control for Image Generation and Editingcited by 0
  25. 2026Constrained Edit Fields for Training-Free Flow Editingcited by 0
  26. 2026DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decouplingcited by 0
  27. 2026WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attackscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods
  2. 2025On Exact Editing of Flow-Based Diffusion Models
  3. 2026BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation
  4. 2025FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
  5. 2024Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
  6. 2026FlowBypass: Rectified Flow Trajectory Bypass for Training-Free Image Editing
  7. 2025FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems
  8. 2025Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models