mlsanityData to 14 Oct 2026

Effective Real Image Editing with Accelerated Iterative Diffusion Inversion

arXiv 2309.04907 ↗First posted 10 Sep 2023cs.CV cs.AIcited by 79

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

Abstract (arXiv)

Despite all recent progress, it is still challenging to edit and manipulate natural images with modern generative models. When using Generative Adversarial Network (GAN), one major hurdle is in the inversion process mapping a real image to its corresponding noise vector in the latent space, since its necessary to be able to reconstruct an image to edit its contents. Likewise for Denoising Diffusion Implicit Models (DDIM), the linearization assumption in each inversion step makes the whole deterministic inversion process unreliable. Existing approaches that have tackled the problem of inversion stability often incur in significant trade-offs in computational efficiency. In this work we propose an Accelerated Iterative Diffusion Inversion method, dubbed AIDI, that significantly improves reconstruction accuracy with minimal additional overhead in space and time complexity. By using a novel blended guidance technique, we show that effective results can be obtained on a large range of image editing tasks without large classifier-free guidance in inversion. Furthermore, when compared with other diffusion inversion based works, our proposed process is shown to be more robust for fast image editing in the 10 and 20 diffusion steps' regimes.

Key facts. Cited by 79 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 39 of its 47 references that are in the map. First posted on arXiv 10 Sep 2023.

Builds on

39 of 47 references.

Closest ancestors · 9

Same direction, newest first

  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. 2022Imagic: Text-Based Real Image Editing with Diffusion Models17 Oct
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  6. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translation16 Mar
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec
  8. 2021Blended Diffusion for Text-driven Editing of Natural Images29 Nov
  9. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation6 Oct

Other references · 30

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  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. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  11. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  12. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
18 more
  1. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  2. 2016HyperNetworkscited by 1,027
  3. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  4. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  5. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  6. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 694
  7. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  8. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 544
  9. 2023Zero-shot Image-to-Image Translationcited by 505
  10. 2021GAN Inversion: A Surveycited by 367
  11. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  12. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 334
  13. 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 258
  14. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  15. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  16. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  17. 2021Using latent space regression to analyze and leverage compositionality in GANscited by 55
  18. 2021GAN Inversion for Out-of-Range Images with Geometric Transformationscited by 55

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 34; 2025: 25; 2026: 14.

79 papers.

Sort:

By area:

  1. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  2. 2024Semantic Image Inversion and Editing using Rectified Stochastic Differential Equationscited by 165
  3. 2024ReNoise: Real Image Inversion Through Iterative Noisingcited by 128
  4. 2024Stable Flow: Vital Layers for Training-Free Image Editingcited by 113
  5. 2024DITTO: Diffusion Inference-Time T-Optimization for Music Generationcited by 73
  6. 2024TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Modelscited by 64
  7. 2023Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Modelscited by 49
  8. 2023On Exact Inversion of DPM-Solverscited by 47
  9. 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimizationcited by 46
  10. 2025EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editingcited by 45
  11. 2024Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Modelscited by 43
  12. 2024Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editingcited by 39
38 more
  1. 2023Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Modelscited by 35
  2. 2024BrushEdit: All-In-One Image Inpainting and Editingcited by 31
  3. 2023HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Modelscited by 29
  4. 2024Conditional Image Synthesis with Diffusion Models: A Surveycited by 29
  5. 2023LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuningcited by 28
  6. 2024Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Modelscited by 22
  7. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 20
  8. 2025h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transformcited by 19
  9. 2024Where's Waldo: Diffusion Features for Personalized Segmentation and Retrievalcited by 18
  10. 2026ChordEdit: One-Step Low-Energy Transport for Image Editingcited by 18
  11. 2023Z^*: Zero-shot Style Transfer via Attention Rearrangementcited by 17
  12. 2024Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editingcited by 17
  13. 2025IntrinsicEdit: Precise generative image manipulation in intrinsic spacecited by 17
  14. 2025PICABench: How Far Are We from Physically Realistic Image Editing?cited by 16
  15. 2024DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactmentcited by 14
  16. 2024Doubly Abductive Counterfactual Inference for Text-based Image Editingcited by 13
  17. 2024FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Modelscited by 13
  18. 2024Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulationcited by 13
  19. 2025DreamVE: Unified Instruction-based Image and Video Editingcited by 11
  20. 2024EasyInv: Toward Fast and Better DDIM Inversioncited by 8
  21. 2024Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editingcited by 8
  22. 2025Image Editing with Diffusion Models: A Surveycited by 8
  23. 2024ObjectAdd: Adding Objects into Image via a Training-Free Diffusion Modification Fashioncited by 7
  24. 2025Tight Inversion: Image-Conditioned Inversion for Real Image Editingcited by 7
  25. 2024SynFER: Towards Boosting Facial Expression Recognition with Synthetic Datacited by 6
  26. 2024LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Paircited by 6
  27. 2025RegionE: Adaptive Region-Aware Generation for Efficient Image Editingcited by 6
  28. 2024Gradient-free Decoder Inversion in Latent Diffusion Modelscited by 5
  29. 2025Cora: Correspondence-aware image editing using few step diffusioncited by 5
  30. 2025DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editingcited by 5
  31. 2024ERDDCI: Exact Reversible Diffusion via Dual-Chain Inversion for High-Quality Image Editingcited by 4
  32. 2024Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversioncited by 4
  33. 2024Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Methodcited by 4
  34. 2024A3D: Does Diffusion Dream about 3D Alignment?cited by 3
  35. 2025REED-VAE: RE-Encode Decode Training for Iterative Image Editing with Diffusion Modelscited by 3
  36. 2025FlowOpt: Fast Optimization Through Whole Flow Processes for Training-Free Editingcited by 3
  37. 2024Ground-A-Score: Scaling Up the Score Distillation for Multi-Attribute Editingcited by 2
  38. 2024Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editingcited by 2

50 most cited of 79 All 79 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Image Inversion: A Survey from GANs to Diffusion and Beyond
  2. 2025DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models
  3. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration
  4. 2024TurboEdit: Instant text-based image editing
  5. 2023Inversion-Free Image Editing with Natural Language
  6. 2023Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models
  7. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
  8. 2023Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code