mlsanityData to 7 Oct 2026

FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing

arXiv 2509.22244 ↗First posted 26 Sep 2025cs.CVcited by 4

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

Abstract (arXiv)

Text-guided image editing with diffusion models has achieved remarkable quality but often suffers from prohibitive latency. We introduce FlashEdit, a real-time localized image editing framework for the standard inversion-based editing setting. Its efficiency and precision stem from three key innovations: (1) a Cycle-Consistent One-Step Inversion (COSI) pipeline that encourages manifold-aligned one-step inversion through cycle consistency; (2) a Background Shield (BG-Shield) technique that improves preservation of non-edited regions via structural self-attention intervention; and (3) a Sparsified Spatial Cross-Attention (SSCA) mechanism that promotes precise edits by suppressing semantic leakage. Experiments on PIE-Bench demonstrate a strong preservation-efficiency trade-off, with edits completed in under 0.2 seconds and an over 150× speedup over DDIM-based multi-step editing. Our code will be made publicly available at urlhttps://github.com/JunyiWuCode/FlashEdit.

Key facts. Cited by 4 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 47 of its 54 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

47 of 54 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025Image Editing with Diffusion Models: A Survey17 Apr
  2. 2024SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion5 Dec
  3. 2024TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models1 Aug
  4. 2024MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation8 Apr
  5. 2024ReNoise: Real Image Inversion Through Iterative Noising21 Mar
  6. 2023SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation8 Dec
  7. 2023Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code2 Oct
  8. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models13 Aug
  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. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  12. 2022InstructPix2Pix: Learning to Follow Image Editing Instructions17 Nov
2 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

Other references · 33

  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. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2022Scalable Diffusion Models with Transformerscited by 5,931
  7. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  8. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  9. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  10. 2023Zero-shot Image-to-Image Translationcited by 503
  11. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  12. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
21 more
  1. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  2. 2023DeepCache: Accelerating Diffusion Models for Freecited by 346
  3. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 224
  4. 2024FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Modelscited by 214
  5. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 203
  6. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  7. 2025From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeerscited by 124
  8. 2025Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generationcited by 64
  9. 2017DeepCache: Principled Cache for Mobile Deep Visioncited by 57
  10. 2024SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teachercited by 45
  11. 2025SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruningcited by 39
  12. 2024Large Language Model Inference Acceleration: A Comprehensive Hardware Perspectivecited by 36
  13. 2024OSDFace: One-Step Diffusion Model for Face Restorationcited by 33
  14. 2024ARB-LLM: Alternating Refined Binarizations for Large Language Modelscited by 30
  15. 2025SpecEE: Accelerating Large Language Model Inference with Speculative Early Exitingcited by 23
  16. 2025QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generationcited by 20
  17. 2025ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibrationcited by 16
  18. 2025DVD-Quant: Data-free Video Diffusion Transformers Quantizationcited by 14
  19. 2023Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantizationcited by 13
  20. 2025Progressive Binarization with Semi-Structured Pruning for LLMscited by 5
  21. 2025SpecDiff: Accelerating Diffusion Model Inference with Self-Speculationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantizationcited by 4
  2. 2026GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstructioncited by 2
  3. 2026Consistent-Inversion: Reverse Consistency Guidance for Structure-Preserving Visual Editingcited by 0
  4. 2026CAST: Reconstruction-Coupled Acceleration of Interactive World Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow
  2. 2023Inversion-Free Image Editing with Natural Language
  3. 2024TurboEdit: Instant text-based image editing
  4. 2026WhereEdit: Mask-aware Local Latent Editing for One-Step Image Editing
  5. 2026ResetEdit: Precise Text-guided Editing of Generated Image via Resettable Starting Latent
  6. 2023BARET : Balanced Attention based Real image Editing driven by Target-text Inversion
  7. 2023LEDITS++: Limitless Image Editing using Text-to-Image Models
  8. 2025Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models