mlsanityData to 14 Oct 2026

DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models

arXiv 2307.02421 ↗First posted 5 Jul 2023cs.CVcited by 195

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

Abstract (arXiv)

Despite the ability of existing large-scale text-to-image (T2I) models to generate high-quality images from detailed textual descriptions, they often lack the ability to precisely edit the generated or real images. In this paper, we propose a novel image editing method, DragonDiffusion, enabling Drag-style manipulation on Diffusion models. Specifically, we construct classifier guidance based on the strong correspondence of intermediate features in the diffusion model. It can transform the editing signals into gradients via feature correspondence loss to modify the intermediate representation of the diffusion model. Based on this guidance strategy, we also build a multi-scale guidance to consider both semantic and geometric alignment. Moreover, a cross-branch self-attention is added to maintain the consistency between the original image and the editing result. Our method, through an efficient design, achieves various editing modes for the generated or real images, such as object moving, object resizing, object appearance replacement, and content dragging. It is worth noting that all editing and content preservation signals come from the image itself, and the model does not require fine-tuning or additional modules. Our source code will be available at https://github.com/MC-E/DragonDiffusion.

Key facts. Cited by 195 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 41 of its 42 references that are in the map. First posted on arXiv 5 Jul 2023.

Builds on

41 of 42 references.

Closest ancestors · 14

Same direction, newest first

  1. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing26 Jun
  2. 2023Emergent Correspondence from Image Diffusion6 Jun
  3. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models16 Feb
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  5. 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis9 Dec
  6. 2022High-Fidelity Guided Image Synthesis with Latent Diffusion Models30 Nov
  7. 2022Sketch-Guided Text-to-Image Diffusion Models24 Nov
  8. 2022InstructPix2Pix: Learning to Follow Image Editing Instructions17 Nov
  9. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov
  10. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers2 Nov
  11. 2022Imagic: Text-Based Real Image Editing with Diffusion Models17 Oct
  12. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
2 more
  1. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec
  2. 2021Blended Diffusion for Text-driven Editing of Natural Images29 Nov

Other references · 27

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  10. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  12. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
15 more
  1. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  2. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  3. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 961
  4. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  5. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited 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. 2023Universal Guidance for Diffusion Modelscited by 437
  9. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  10. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  11. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Modelcited by 294
  12. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  13. 2023Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldcited by 219
  14. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  15. 2023Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Modelscited by 137

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 23; 2024: 83; 2025: 68; 2026: 21.

195 papers.

Sort:

By area:

  1. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  2. 2024Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modelingcited by 211
  3. 2024Motion Prompting: Controlling Video Generation with Motion Trajectoriescited by 178
  4. 2023Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Codecited by 145
  5. 2023Cross-Image Attention for Zero-Shot Appearance Transfercited by 136
  6. 2024GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editingcited by 133
  7. 2023State of the Art on Diffusion Models for Visual Computingcited by 127
  8. 2024Training-Free Consistent Text-to-Image Generationcited by 125
  9. 2023Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfercited by 124
  10. 2024MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesiscited by 124
  11. 2024GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editingcited by 115
  12. 2023Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusioncited by 114
38 more
  1. 2024FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Modelscited by 113
  2. 2024Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advancescited by 110
  3. 2024DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editingcited by 88
  4. 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 86
  5. 2025DreamO: A Unified Framework for Image Customizationcited by 83
  6. 2023VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondencecited by 69
  7. 2024SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generationcited by 68
  8. 2023The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editingcited by 62
  9. 2024Video Diffusion Models are Training-free Motion Interpreter and Controllercited by 61
  10. 2023Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraintscited by 60
  11. 2024DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalizationcited by 60
  12. 2023Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3Dcited by 59
  13. 2024360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Modelcited by 58
  14. 2023MotionEditor: Editing Video Motion via Content-Aware Diffusioncited by 57
  15. 2024LightIt: Illumination Modeling and Control for Diffusion Modelscited by 57
  16. 2023Readout Guidance: Learning Control from Diffusion Featurescited by 52
  17. 2024Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagationcited by 51
  18. 2023Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Modelscited by 49
  19. 2024LCM-Lookahead for Encoder-based Text-to-Image Personalizationcited by 48
  20. 2024Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Modelcited by 45
  21. 2024Diffusion Model-Based Video Editing: A Surveycited by 44
  22. 2024Wear-Any-Way: Manipulable Virtual Try-on via Sparse Correspondence Alignmentcited by 43
  23. 2024Efficient Diffusion Models: A Comprehensive Survey from Principles to Practicescited by 41
  24. 2023DragVideo: Interactive Drag-style Video Editingcited by 40
  25. 2024Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimatorscited by 39
  26. 2023Amodal Completion via Progressive Mixed Context Diffusioncited by 38
  27. 2024Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videoscited by 38
  28. 2024EditWorld: Simulating World Dynamics for Instruction-Following Image Editingcited by 38
  29. 2024Diffusion Feedback Helps CLIP See Bettercited by 38
  30. 2024LLMs Meet Multimodal Generation and Editing: A Surveycited by 35
  31. 2024Stable-Hair: Real-World Hair Transfer via Diffusion Modelcited by 35
  32. 2024GoodDrag: Towards Good Practices for Drag Editing with Diffusion Modelscited by 34
  33. 2024GeoDiffuser: Geometry-Based Image Editing with Diffusion Modelscited by 34
  34. 2024DragAPart: Learning a Part-Level Motion Prior for Articulated Objectscited by 32
  35. 2024RegionDrag: Fast Region-Based Image Editing with Diffusion Modelscited by 32
  36. 2024Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Modelscited by 30
  37. 2024MagicQuill: An Intelligent Interactive Image Editing Systemcited by 30
  38. 2025ObjectMover: Generative Object Movement with Video Priorcited by 30

50 most cited of 195 All 195 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024DiffUHaul: A Training-Free Method for Object Dragging in Images
  2. 2023LayerDiffusion: Layered Controlled Image Editing with Diffusion Models
  3. 2023Towards Real-time Text-driven Image Manipulation with Unconditional Diffusion Models
  4. 2026Reproducing DragDiffusion: Interactive Point-Based Editing with Diffusion Models
  5. 2023On Manipulating Scene Text in the Wild with Diffusion Models
  6. 2023PFB-Diff: Progressive Feature Blending Diffusion for Text-driven Image Editing
  7. 2022DiffEdit: Diffusion-based semantic image editing with mask guidance
  8. 2023Region-Aware Diffusion for Zero-shot Text-driven Image Editing