mlsanityData to 7 Oct 2026

FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing

arXiv 2412.07517 ↗First posted 10 Dec 2024cs.CVcited by 66

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

Abstract (arXiv)

Though Rectified Flows (ReFlows) with distillation offers a promising way for fast sampling, its fast inversion transforms images back to structured noise for recovery and following editing remains unsolved. This paper introduces FireFlow, a simple yet effective zero-shot approach that inherits the startling capacity of ReFlow-based models (such as FLUX) in generation while extending its capabilities to accurate inversion and editing in 8 steps. We first demonstrate that a carefully designed numerical solver is pivotal for ReFlow inversion, enabling accurate inversion and reconstruction with the precision of a second-order solver while maintaining the practical efficiency of a first-order Euler method. This solver achieves a 3× runtime speedup compared to state-of-the-art ReFlow inversion and editing techniques, while delivering smaller reconstruction errors and superior editing results in a training-free mode. The code is available at hrefhttps://github.com/HolmesShuan/FireFlowthis URL.

Key facts. Cited by 66 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 30 of its 34 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

30 of 34 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models11 Nov
  2. 2024Taming Rectified Flow for Inversion and Editing7 Nov
  3. 2024Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing24 Oct
  4. 2024Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations14 Oct
  5. 2024TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models1 Aug
  6. 2024Noise Map Guidance: Inversion with Spatial Context for Real Image Editing7 Feb
  7. 2023Inversion-Free Image Editing with Natural Language7 Dec
  8. 2023LEDITS++: Limitless Image Editing using Text-to-Image Models28 Nov
  9. 2023Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models26 May
  10. 2023Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models8 May
  11. 2023An Edit Friendly DDPM Noise Space: Inversion and Manipulations12 Apr
  12. 2022InstructPix2Pix: Learning to Follow Image Editing Instructions17 Nov
3 more
  1. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov
  2. 2022DiffEdit: Diffusion-based semantic image editing with mask guidance20 Oct
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 15

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  7. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  8. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  9. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  10. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
  11. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  12. 2023Zero-shot Image-to-Image Translationcited by 503
3 more
  1. 2023A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captionscited by 107
  2. 2023Generative Modeling with Phase Stochastic Bridgescited by 24
  3. 2024Constant Acceleration Flowcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 37; 2026: 29.

66 papers.

Sort:

By area:

  1. 2025UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Modelscited by 38
  2. 2025DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editingcited by 29
  3. 2025DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editingcited by 22
  4. 2025HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidancecited by 21
  5. 2025Multi-turn Consistent Image Editingcited by 17
  6. 2025Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editingcited by 16
  7. 2025FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Modelscited by 15
  8. 2025ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptationcited by 15
  9. 2025SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editingcited by 15
  10. 2025Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flowcited by 10
  11. 2025Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methodscited by 5
  12. 2025Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformercited by 5
38 more
  1. 2025FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editingcited by 5
  2. 2025ProEdit: Inversion-based Editing From Prompts Done Rightcited by 5
  3. 2026Improving Robotic Generalist Policies via Flow Reversal Steeringcited by 5
  4. 2025A Training-Free Style-aligned Image Generation with Scale-wise Autoregressive Modelcited by 4
  5. 2025Delta Rectified Flow Sampling for Text-to-Image Editingcited by 4
  6. 2025LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondencecited by 3
  7. 2025Target-aware Image Editing via Cycle-consistent Constraintscited by 3
  8. 2025FlowOpt: Fast Optimization Through Whole Flow Processes for Training-Free Editingcited by 3
  9. 2026FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matchingcited by 3
  10. 2026FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inferencecited by 3
  11. 2026SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editingcited by 3
  12. 2025FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generationcited by 2
  13. 2025Don't Forget your Inverse DDIM for Image Editingcited by 2
  14. 2025The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusioncited by 2
  15. 2025CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editingcited by 2
  16. 2025AutoEdit: Automatic Hyperparameter Tuning for Image Editingcited by 2
  17. 2025Training-Free Reward-Guided Image Editing via Trajectory Optimal Controlcited by 2
  18. 2025EditTrack: Detecting and Attributing AI-assisted Image Editingcited by 2
  19. 2025The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergycited by 2
  20. 2026Free Lunch for Stabilizing Rectified Flow Inversioncited by 2
  21. 2026StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generationcited by 2
  22. 2025Reference-free Human-Object Interaction Editingcited by 1
  23. 2025IE-Critic-R1: Advancing the Explanatory Measurement of Text-Driven Image Editing for Human Perception Alignmentcited by 1
  24. 2025FlowSteer: Conditioning Flow Field for Consistent Image Restorationcited by 1
  25. 2025NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localizationcited by 1
  26. 2025On Exact Editing of Flow-Based Diffusion Modelscited by 1
  27. 2026See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesiscited by 1
  28. 2026AdaEdit: Adaptive Temporal and Channel Modulation for Flow-Based Image Editingcited by 1
  29. 2026BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generationcited by 1
  30. 2026DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editingcited by 1
  31. 2026FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editingcited by 1
  32. 2026EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learningcited by 1
  33. 2025Single Image Iterative Subject-driven Generation and Editingcited by 0
  34. 2025Semantic Editing with Coupled Stochastic Differential Equationscited by 0
  35. 2025MusRec: Zero-Shot Text-to-Music Editing via Rectified Flow and Diffusion Transformerscited by 0
  36. 2025Inversion-Free Style Transfer with Dual Rectified Flowscited by 0
  37. 2025Reversible Inversion for Training-Free Exemplar-guided Image Editingcited by 0
  38. 2026Sissi: Zero-shot Style-guided Image Synthesis via Semantic-style Integrationcited by 0

50 most cited of 66 All 66 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Score-Guided Proximal Projection: A Unified Geometric Framework for Rectified Flow Editing
  2. 2024FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models
  3. 2025Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models
  4. 2025FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
  5. 2025InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow
  6. 2024TurboEdit: Instant text-based image editing
  7. 2024Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
  8. 2023Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code