mlsanityData to 7 Oct 2026

Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

arXiv 2411.07232 ↗First posted 11 Nov 2024cs.CV cs.AI cs.GRcited by 42

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

Abstract (arXiv)

Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integrating the new object in a fitting location. Despite extensive efforts, existing models often struggle with this balance, particularly with finding a natural location for adding an object in complex scenes. We introduce Add-it, a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources: the scene image, the text prompt, and the generated image itself. Our weighted extended-attention mechanism maintains structural consistency and fine details while ensuring natural object placement. Without task-specific fine-tuning, Add-it achieves state-of-the-art results on both real and generated image insertion benchmarks, including our newly constructed "Additing Affordance Benchmark" for evaluating object placement plausibility, outperforming supervised methods. Human evaluations show that Add-it is preferred in over 80% of cases, and it also demonstrates improvements in various automated metrics.

Key facts. Cited by 42 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 37 of its 51 references that are in the map. First posted on arXiv 11 Nov 2024.

Builds on

37 of 51 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models1 Aug
  2. 2024DiffUHaul: A Training-Free Method for Object Dragging in Images3 Jun
  3. 2024ReNoise: Real Image Inversion Through Iterative Noising21 Mar
  4. 2023Inversion-Free Image Editing with Natural Language7 Dec
  5. 2023LEDITS++: Limitless Image Editing using Text-to-Image Models28 Nov
  6. 2023Effective Real Image Editing with Accelerated Iterative Diffusion Inversion10 Sep
  7. 2023LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance2 Jul
  8. 2023An Edit Friendly DDPM Noise Space: Inversion and Manipulations12 Apr
  9. 2022InstructPix2Pix: Learning to Follow Image Editing Instructions17 Nov
  10. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov
  11. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers2 Nov
  12. 2022Imagic: Text-Based Real Image Editing with Diffusion Models17 Oct
3 more
  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  3. 2021Blended Diffusion for Text-driven Editing of Natural Images29 Nov

Other references · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  6. 2016Improved Techniques for Training GANscited by 2,938
  7. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  9. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  10. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  11. 2018Demystifying MMD GANscited by 1,268
  12. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
10 more
  1. 2023MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editingcited by 615
  2. 2023Emu Edit: Precise Image Editing via Recognition and Generation Taskscited by 321
  3. 2022Text2LIVE: Text-Driven Layered Image and Video Editingcited by 312
  4. 2022EDICT: Exact Diffusion Inversion via Coupled Transformationscited by 256
  5. 2023Style Aligned Image Generation via Shared Attentioncited by 214
  6. 2023Cross-Image Attention for Zero-Shot Appearance Transfercited by 135
  7. 2024Training-Free Consistent Text-to-Image Generationcited by 123
  8. 2023OBJECT 3DIT: Language-guided 3D-aware Image Editingcited by 62
  9. 2024Paint by Inpaint: Learning to Add Image Objects by Removing Them Firstcited by 39
  10. 2024EraseDraw: Learning to Draw Step-by-Step via Erasing Objects from Imagescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 28; 2026: 11.

42 papers.

Sort:

By area:

  1. 2024FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editingcited by 66
  2. 2024Number it: Temporal Grounding Videos like Flipping Mangacited by 65
  3. 2025KV-Edit: Training-Free Image Editing for Precise Background Preservationcited by 47
  4. 2025OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpaintingcited by 38
  5. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 30
  6. 2025FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editingcited by 21
  7. 2025FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generationcited by 21
  8. 2025Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Modelscited by 10
  9. 2025DynVFX: Augmenting Real Videos with Dynamic Contentcited by 9
  10. 2025FreeBlend: Advancing Concept Blending with Staged Feedback-Driven Interpolation Diffusioncited by 8
  11. 2025LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorizationcited by 8
  12. 2025Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventionscited by 7
30 more
  1. 2025Product of Experts for Visual Generationcited by 6
  2. 2025GenHSI: Controllable Generation of Human-Scene Interaction Videoscited by 6
  3. 2025ProEdit: Inversion-based Editing From Prompts Done Rightcited by 5
  4. 2026Spanning the Visual Analogy Space with a Weight Basis of LoRAscited by 4
  5. 2025LMP: Leveraging Motion Prior in Zero-Shot Video Generation with Diffusion Transformercited by 3
  6. 2025FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformerscited by 3
  7. 2026Versatile Editing of Video Content, Actions, and Dynamics without Trainingcited by 3
  8. 2024Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledgecited by 2
  9. 2025Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidancecited by 2
  10. 2025Causal-Entity Reflected Egocentric Traffic Accident Video Synthesiscited by 2
  11. 2025CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editingcited by 2
  12. 2025Teleportraits: Training-Free People Insertion into Any Scenecited by 2
  13. 2025Zero-Shot Video Deraining with Video Diffusion Modelscited by 2
  14. 2025EditGarment: An Instruction-Based Garment Editing Dataset Constructed with Automated MLLM Synthesis and Semantic-Aware Evaluationcited by 1
  15. 2025StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonizationcited by 1
  16. 2025EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shiftcited by 1
  17. 2026GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editingcited by 1
  18. 2025Controllable Coupled Image Generation via Diffusion Modelscited by 0
  19. 2025RichControl: Structure- and Appearance-Rich Training-Free Spatial Control for Text-to-Image Generationcited by 0
  20. 2025AURAD: Anatomy-Pathology Unified Radiology Synthesis with Progressive Representationscited 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. 2026HiddenObjects: Scalable Diffusion-Distilled Spatial Priors for Object Placementcited by 0
  24. 2026AD-Relight: Training-Free Banner Relighting via Illumination Translation with Diffusion Priorscited by 0
  25. 2026AdaEraser: Training-Free Object Removal via Adaptive Attention Suppressioncited by 0
  26. 2026BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfercited by 0
  27. 2026Injecting Image Guidance into Text-Conditioned Diffusion Models at Inferencecited by 0
  28. 2026CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferencescited by 0
  29. 2026Conditioning Matters: Stabilizing Inversion and Attention in Diffusion Image Editingcited by 0
  30. 2026SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Add-SD: Rational Generation without Manual Reference
  2. 2025PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models
  3. 2025FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors
  4. 2022Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting
  5. 2024Towards Small Object Editing: A Benchmark Dataset and A Training-Free Approach
  6. 2025InstructUDrag: Joint Text Instructions and Object Dragging for Interactive Image Editing
  7. 2023Learning to Follow Object-Centric Image Editing Instructions Faithfully
  8. 2025Insert Anything: Image Insertion via In-Context Editing in DiT