mlsanityData to 7 Oct 2026

Improving Tuning-Free Real Image Editing with Proximal Guidance

arXiv 2306.05414 ↗First posted 8 Jun 2023cs.CVcited by 87

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

Abstract (arXiv)

DDIM inversion has revealed the remarkable potential of real image editing within diffusion-based methods. However, the accuracy of DDIM reconstruction degrades as larger classifier-free guidance (CFG) scales being used for enhanced editing. Null-text inversion (NTI) optimizes null embeddings to align the reconstruction and inversion trajectories with larger CFG scales, enabling real image editing with cross-attention control. Negative-prompt inversion (NPI) further offers a training-free closed-form solution of NTI. However, it may introduce artifacts and is still constrained by DDIM reconstruction quality. To overcome these limitations, we propose proximal guidance and incorporate it to NPI with cross-attention control. We enhance NPI with a regularization term and reconstruction guidance, which reduces artifacts while capitalizing on its training-free nature. Additionally, we extend the concepts to incorporate mutual self-attention control, enabling geometry and layout alterations in the editing process. Our method provides an efficient and straightforward approach, effectively addressing real image editing tasks with minimal computational overhead.

Key facts. Cited by 87 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 72 of its 86 references that are in the map. First posted on arXiv 8 Jun 2023.

Builds on

72 of 86 references.

Closest ancestors · 21

Same direction, newest first

  1. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds1 Jun
  2. 2023The Hidden Language of Diffusion Models1 Jun
  3. 2023Real-World Image Variation by Aligning Diffusion Inversion Chain30 May
  4. 2023LayerDiffusion: Layered Controlled Image Editing with Diffusion Models30 May
  5. 2023Text-to-image Editing by Image Information Removal27 May
  6. 2023Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models26 May
  7. 2023Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models23 May
  8. 2023An Edit Friendly DDPM Noise Space: Inversion and Manipulations12 Apr
  9. 2023StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing28 Mar
  10. 2023SVDiff: Compact Parameter Space for Diffusion Fine-Tuning20 Mar
  11. 2023Editing Implicit Assumptions in Text-to-Image Diffusion Models14 Mar
  12. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models16 Feb
9 more
  1. 2023GLIGEN: Open-Set Grounded Text-to-Image Generation17 Jan
  2. 2022SINE: SINgle Image Editing with Text-to-Image Diffusion Models8 Dec
  3. 2022Multi-Concept Customization of Text-to-Image Diffusion8 Dec
  4. 2022Diffusion Guided Domain Adaptation of Image Generators8 Dec
  5. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov
  6. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  8. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 51

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
38 more
  1. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  2. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  3. 2023Consistency Modelscited by 1,778
  4. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  5. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  6. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
  7. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  8. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  9. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  10. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
  11. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  12. 2023FateZero: Fusing Attentions for Zero-shot Text-based Video Editingcited by 462
  13. 2023ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generationcited by 414
  14. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  15. 2023InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuningcited by 343
  16. 2019DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesiscited by 308
  17. 2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
  18. 2023P+: Extended Textual Conditioning in Text-to-Image Generationcited by 242
  19. 2023Break-A-Scene: Extracting Multiple Concepts from a Single Imagecited by 230
  20. 2023StyleDrop: Text-to-Image Generation in Any Stylecited by 197
  21. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 131
  22. 2023Delta Denoising Scorecited by 120
  23. 2023AvatarCraft: Transforming Text into Neural Human Avatars with Parameterized Shape and Pose Controlcited by 84
  24. 2021CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directionscited by 78
  25. 2023DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generationcited by 75
  26. 2021Improving Text-to-Image Synthesis Using Contrastive Learningcited by 62
  27. 2023Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunitycited by 54
  28. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  29. 2023HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attentioncited by 44
  30. 2022Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioningcited by 37
  31. 2023Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokenscited by 35
  32. 2022Multiresolution Textual Inversioncited by 33
  33. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shapecited by 29
  34. 2021Disentangled Recurrent Wasserstein Autoencodercited by 22
  35. 2023Soundini: Sound-Guided Diffusion for Natural Video Editingcited by 14
  36. 2019Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisonscited by 9
  37. 2021Dual Projection Generative Adversarial Networks for Conditional Image Generationcited by 8
  38. 2020Unbiased Auxiliary Classifier GANs with MINEcited by 7

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 32; 2025: 31; 2026: 17.

87 papers.

Sort:

By area:

  1. 2024FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Modelscited by 214
  2. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  3. 2023Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Codecited by 145
  4. 2024ReNoise: Real Image Inversion Through Iterative Noisingcited by 127
  5. 2024Stable Flow: Vital Layers for Training-Free Image Editingcited by 111
  6. 2023AVID: Any-Length Video Inpainting with Diffusion Modelcited by 81
  7. 2023Relightful Harmonization: Lighting-aware Portrait Background Replacementcited by 56
  8. 2023FaceStudio: Put Your Face Everywhere in Secondscited by 53
  9. 2023Contrastive Denoising Score for Text-guided Latent Diffusion Image Editingcited by 49
  10. 2024The Double-Ellipsoid Geometry of CLIPcited by 42
  11. 2024Score-Guided Diffusion for 3D Human Recoverycited by 39
  12. 2024Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editingcited by 38
38 more
  1. 2025UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Modelscited by 38
  2. 2024FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editingcited by 31
  3. 2024BrushEdit: All-In-One Image Inpainting and Editingcited by 31
  4. 2024Conditional Image Synthesis with Diffusion Models: A Surveycited by 29
  5. 2024BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Modelscited by 29
  6. 2023LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuningcited by 28
  7. 2025IMAGHarmony: Controllable Image Editing with Consistent Object Quantity and Layoutcited by 28
  8. 2024VIVID-10M: A Dataset and Baseline for Versatile and Interactive Video Local Editingcited by 24
  9. 2024Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Modelscited by 23
  10. 2025RORem: Training a Robust Object Remover with Human-in-the-Loopcited by 23
  11. 2023IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Modelscited by 20
  12. 2024DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editingcited by 19
  13. 2024Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Functioncited by 19
  14. 2025ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motionscited by 19
  15. 2025h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transformcited by 18
  16. 2024Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editingcited by 17
  17. 2025LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptationcited by 17
  18. 2025DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Modecited by 17
  19. 2025VINCIE: Unlocking In-context Image Editing from Videocited by 17
  20. 2026ChordEdit: One-Step Low-Energy Transport for Image Editingcited by 17
  21. 2024Layout Agnostic Scene Text Image Synthesis with Diffusion Modelscited by 14
  22. 2025Improved Training Technique for Latent Consistency Modelscited by 13
  23. 2024Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editingcited by 11
  24. 2024Instruction-based Image Manipulation by Watching How Things Movecited by 11
  25. 2024PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editingcited by 9
  26. 2024Edicho: Consistent Image Editing in the Wildcited by 9
  27. 2025Charts Are Not Images: On the Challenges of Scientific Chart Editingcited by 9
  28. 2024Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editingcited by 8
  29. 2025Image Editing with Diffusion Models: A Surveycited by 8
  30. 2025SAEdit: Token-level control for continuous image editing via Sparse AutoEncodercited by 8
  31. 2024Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidancecited by 7
  32. 2025LUCAS: Layered Universal Codec Avatarscited by 7
  33. 2025Tight Inversion: Image-Conditioned Inversion for Real Image Editingcited by 7
  34. 2025InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flowcited by 7
  35. 2024F2FLDM: Latent Diffusion Models with Histopathology Pre-Trained Embeddings for Unpaired Frozen Section to FFPE Translationcited by 6
  36. 2025StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidancecited by 6
  37. 2025EditInfinity: Image Editing with Binary-Quantized Generative Modelscited by 6
  38. 2024ERDDCI: Exact Reversible Diffusion via Dual-Chain Inversion for High-Quality Image Editingcited by 4

50 most cited of 87 All 87 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Wavelet-Guided Acceleration of Text Inversion in Diffusion-Based Image Editing
  2. 2024Noise Map Guidance: Inversion with Spatial Context for Real Image Editing
  3. 2023Tuning-Free Inversion-Enhanced Control for Consistent Image Editing
  4. 2024SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing
  5. 2025DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing
  6. 2023Inversion-Free Image Editing with Natural Language
  7. 2024TurboEdit: Instant text-based image editing
  8. 2023Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models