mlsanityData to 14 Oct 2026

KV-Edit: Training-Free Image Editing for Precise Background Preservation

arXiv 2502.17363 ↗First posted 24 Feb 2025cs.CVcited by 49

On the map: Efficient LLM inference and serving → Fast autoregressive visual generation

Abstract (arXiv)

Background consistency remains a significant challenge in image editing tasks. Despite extensive developments, existing works still face a trade-off between maintaining similarity to the original image and generating content that aligns with the target. Here, we propose KV-Edit, a training-free approach that uses KV cache in DiTs to maintain background consistency, where background tokens are preserved rather than regenerated, eliminating the need for complex mechanisms or expensive training, ultimately generating new content that seamlessly integrates with the background within user-provided regions. We further explore the memory consumption of the KV cache during editing and optimize the space complexity to O(1) using an inversion-free method. Our approach is compatible with any DiT-based generative model without additional training. Experiments demonstrate that KV-Edit significantly outperforms existing approaches in terms of both background and image quality, even surpassing training-based methods. Project webpage is available at https://xilluill.github.io/projectpages/KV-Edit

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Placed in Fast autoregressive visual generation, one of 12 directions in Efficient LLM inference and serving. Builds on 63 of its 79 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

63 of 79 references.

References · 63

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2023GPT-4 Technical Reportcited by 18,396
  7. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  8. 2020Denoising Diffusion Implicit Modelscited by 9,781
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  10. 2023Visual Instruction Tuningcited by 7,869
  11. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  12. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
38 more
  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2023Qwen Technical Reportcited by 3,344
  7. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  8. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  9. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  10. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  11. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  12. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,179
  13. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  14. 2024DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Modelcited by 1,135
  15. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 906
  16. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  17. 2022Blended Latent Diffusioncited by 432
  18. 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 348
  19. 2023Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videoscited by 314
  20. 2022Rectified Flow: A Marginal Preserving Approach to Optimal Transportcited by 283
  21. 2024FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Modelscited by 217
  22. 2024Taming Rectified Flow for Inversion and Editingcited by 204
  23. 2024BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusioncited by 202
  24. 2023Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Modelscited by 174
  25. 2024Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animationcited by 174
  26. 2023A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpaintingcited by 169
  27. 2024Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streamscited by 169
  28. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 168
  29. 2024Semantic Image Inversion and Editing using Rectified Stochastic Differential Equationscited by 165
  30. 2024Stable Flow: Vital Layers for Training-Free Image Editingcited by 113
  31. 2024DiT4Edit: Diffusion Transformer for Image Editingcited by 101
  32. 2023Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Modelscited by 99
  33. 2024ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Modelscited by 89
  34. 2024VoCo-LLaMA: Towards Vision Compression with Large Language Modelscited by 79
  35. 2023StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editingcited by 68
  36. 2023MagicStick: Controllable Video Editing via Control Handle Transformationscited by 62
  37. 2023Open-Vocabulary Segmentation with Semantic-Assisted Calibrationcited by 49
  38. 2023Towards Accurate Post-training Quantization for Diffusion Modelscited by 47

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 25; 2026: 24.

49 papers.

Sort:

By area:

  1. 2025In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformercited by 204
  2. 2025Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editingcited by 61
  3. 2025EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editingcited by 45
  4. 2025VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Spacecited by 45
  5. 2025JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimizationcited by 31
  6. 2025Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Controlcited by 28
  7. 2025DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editingcited by 24
  8. 2025EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editingcited by 12
  9. 2026From Scale to Speed: Adaptive Test-Time Scaling for Image Editingcited by 8
  10. 2025Describe, Don't Dictate: Semantic Image Editing with Natural Language Intentcited by 7
  11. 2025SpotEdit: Selective Region Editing in Diffusion Transformerscited by 7
  12. 2025Beyond Textual CoT: Interleaved Text-Image Chains with Deep Confidence Reasoning for Image Editingcited by 6
37 more
  1. 2026Object-WIPER : Training-Free Object and Associated Effect Removal in Videoscited by 6
  2. 2026TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Expertscited by 6
  3. 2025DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editingcited by 4
  4. 2025LMP: Leveraging Motion Prior in Zero-Shot Video Generation with Diffusion Transformercited by 3
  5. 2025LORE: Latent Optimization for Precise Semantic Control in Rectified Flow-based Image Editingcited by 3
  6. 2026WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmarkcited by 3
  7. 2026SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editingcited by 3
  8. 2026Meta-CoT: Enhancing Granularity and Generalization in Image Editingcited by 3
  9. 2026SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulationcited by 3
  10. 2025The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusioncited by 2
  11. 2025CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editingcited by 2
  12. 2025Low-Resolution Editing is All You Need for High-Resolution Editingcited by 2
  13. 2025CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editingcited by 2
  14. 2025The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergycited by 2
  15. 2026GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editingcited by 1
  16. 2026Towards Training-Free Scene Text Editingcited by 1
  17. 2026DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editingcited by 1
  18. 2026FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editingcited by 1
  19. 2025RichControl: Structure- and Appearance-Rich Training-Free Spatial Control for Text-to-Image Generationcited by 0
  20. 2025Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generationcited by 0
  21. 2025Understanding the Implicit User Intention via Reasoning with Large Language Model for Image Editingcited by 0
  22. 2025Match-and-Fuse: Consistent Generation from Unstructured Image Setscited by 0
  23. 2025DirectSwap: Paired, Mask-Free Video Head Swapping with Full-Reference Evaluationcited by 0
  24. 2025EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removalcited by 0
  25. 2026FusionEdit: Semantic Fusion and Attention Modulation for Training-Free Image Editingcited by 0
  26. 2026When to Lock Attention: Training-Free KV Control in Video Diffusioncited by 0
  27. 2026LimeCross: Context-Conditioned Layered Image Editing with Structural Consistencycited by 0
  28. 2026Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editingcited by 0
  29. 2026Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customizationcited by 0
  30. 2026PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editingcited by 0
  31. 2026SR-Edit: Region-Aware Image Editing via Self-Refinementcited by 0
  32. 2026Object-Aware Background-Controlled Editing via Weighted Velocity Guidancecited by 0
  33. 2026Multi-History-Step SDE Inversion for Image Editing with Superior Regional Awarenesscited by 0
  34. 2026Edit-VAR: Taming Visual Autoregressive Model for Precise Video Editingcited by 0
  35. 2026Beyond Temporal Smoothing: Spatial Energy Budgets Stabilize One-Step Diffusion Editingcited by 0
  36. 2026DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decouplingcited by 0
  37. 2026No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026VeloEdit: Training-Free Consistent and Continuous Instruction-Based Image Editing via Velocity Field Decomposition
  2. 2026Edit2Restore:Few-Shot Image Restoration via Parameter-Efficient Adaptation of Pre-trained Editing Models
  3. 2026CoCoEdit: Content-Consistent Image Editing via Region Regularized Reinforcement Learning
  4. 2023KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editing
  5. 2026Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
  6. 2026VENUS: Visual Editing with Noise Inversion Using Scene Graphs
  7. 2025LUSD: Localized Update Score Distillation for Text-Guided Image Editing
  8. 2026Training-Free Multi-Concept Image Editing