Pith. sign in

REVIEW 25 cited by

DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.02421 v2 pith:3TUJQ6VG submitted 2023-07-05 cs.CV

classification cs.CV
keywords editingdiffusiondragondiffusionguidanceimageimagesmodelmodels
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 25 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors

    cs.CV 2025-01 conditional novelty 7.0 of 10

    Interactive image editing can be cast as image-to-video generation: initializing from Stable Video Diffusion plus a new matching attention mechanism yields high-quality sketch, drag, and coarse-edit results with far l...

  2. MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer

    cs.CV 2026-07 conditional novelty 6.0 of 10

    MagicMakeup transfers makeup onto specified facial regions while preserving identity, using token-aligned attention gating and cross-modal concept guidance, and reports state-of-the-art results on a new high-resolutio...

  3. Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Drag-based editing becomes pixel-space bidirectional warping plus inpainting, giving real-time previews and 0.3s final edits at 512x512.

  4. Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing

    cs.CV 2025-07 conditional novelty 6.0 of 10

    X-Planner, an MLLM-based planner, decomposes complex image-editing instructions into localized sub-edits with masks and boxes, improving editing quality on standard and new complex benchmarks.

  5. AttentionDrag: Exploiting Latent Correlation Knowledge in Pre-trained Diffusion Models for Image Editing

    cs.CV 2025-06 conditional novelty 6.0 of 10

    AttentionDrag is a one-step, training-free drag-editing method that uses diffusion self-attention to move regions, generate masks, and fill gaps.

  6. Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A reference-based video editing pipeline that guides cross-image attention with diffusion correspondence, then trains a per-video restoration model to clean up the zero-shot output.

  7. Semantic Correspondence: Unified Benchmarking and a Strong Baseline

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Fine-tuning the last layers of DINOv2, optionally with a lightweight cost aggregator, yields state-of-the-art semantic correspondence accuracy, and a new survey and benchmark consolidate the field's results.

  8. DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model

    cs.CV 2025-05 conditional novelty 6.0 of 10

    DragLoRA improves drag-based image editing by online-optimizing LoRA adapters with a dual drag and score-distillation loss, adaptive mode switching, and input feature adaptation.

  9. 3D-Fixup: Advancing Photo Editing with 3D Priors

    cs.CV 2025-05 conditional novelty 6.0 of 10

    3D-Fixup performs 3D-aware photo editing, such as object rotation and translation, by conditioning a diffusion model on guidance rendered from a reconstructed 3D mesh.

  10. Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting

    cs.GR 2025-01 conditional novelty 6.0 of 10

    DYG edits 3D Gaussian scenes by dragging masked regions to target points, using a triplane positional scaffold and a drag-based latent diffusion score-distillation loss.

  11. DragScene: Interactive 3D Scene Editing with Single-view Drag Instructions

    cs.CV 2024-12 conditional novelty 6.0 of 10

    DragScene propagates a single-view drag edit across multiple views by reconstructing a coarse point cloud with the edit's latent features, then reconstructing the edited 3D scene.

  12. InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A single-step diffusion-based face restoration model uses reference-image attention to preserve identity in about 0.5 seconds per image, with no per-identity tuning.

  13. DreamBlend: Advancing Personalized Fine-tuning of Text-to-Image Diffusion Models

    cs.CV 2024-11 conditional novelty 6.0 of 10

    DreamBlend guides an overfit fine-tuned checkpoint with cross-attention maps from an underfit checkpoint, improving subject fidelity, prompt fidelity, and diversity in personalized text-to-image generation.

  14. Generating Compositional Scenes via Text-to-image RGBA Instance Generation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A multi-stage text-to-image approach that generates individual objects as RGBA images and composes them scene-by-scene via noise blending, enabling fine-grained layout and attribute control.

  15. GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object Generation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A point-cloud-structured latent space with cascaded flow matching enables high-quality text- and image-conditioned 3D object generation and interactive editing.

  16. CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Coupling a global latent code with a 3D feature volume lets off-the-shelf 3D generators perform local semantic edits — copy, delete, resize, mix, and drag — across object categories while preserving unedited regions.

  17. FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields

    cs.GR 2025-07 conditional novelty 5.0 of 10

    FlowDrag combines 3D mesh deformation with diffusion-based drag editing, using the resulting 2D vector flow to steer the denoising process, and adds a ground-truth benchmark built from video frames.

  18. Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning

    cs.CV 2025-06 reject novelty 5.0 of 10

    A new micro-edit dataset and fine-tuning recipe appear to help multimodal LLMs notice small visual changes, but the central 'feature consistency loss' claim is not present in the method.

  19. ARAP-GS: Drag-driven As-Rigid-As-Possible 3D Gaussian Splatting Editing with Diffusion Prior

    cs.GR 2025-04 conditional novelty 5.0 of 10

    A drag-driven 3DGS editing method that applies as-rigid-as-possible deformation directly to Gaussian centers and then fine-tunes appearance with a diffusion super-resolution prior.

  20. Exploring the latent space of diffusion models directly through singular value decomposition

    cs.CV 2025-02 reject novelty 5.0 of 10

    The authors report that singular value decomposition of diffusion latent codes reveals stable, order-mobile attribute directions and propose Attribute Vector Integration, a per-pair MLP-based editor that transfers tex...

  21. PEMF-VTO: Point-Enhanced Video Virtual Try-on via Mask-free Paradigm

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A mask-free video virtual try-on model that uses sparse point correspondences between garment and frames, plus frame-to-frame tracking, to improve garment transfer and temporal coherence.

  22. Motion Prompting: Controlling Video Generation with Motion Trajectories

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A single-stage ControlNet on the Lumiere video model, conditioned only on dense point tracks, generalizes to sparse and dense trajectory control for object, camera, and transferred motions.

  23. MagicQuill: An Intelligent Interactive Image Editing System

    cs.CV 2024-11 conditional novelty 5.0 of 10

    MagicQuill combines brush-based edge and color control with an MLLM that guesses user intent, enabling fast interactive image edits without typing prompts.

  24. 2D Instance Editing in 3D Space

    cs.CV 2025-07 reject novelty 4.0 of 10

    A 2D-to-3D-to-2D editing system that segments an object, reconstructs it as 3D Gaussians, deforms it under a rigidity constraint, and inpaints it back into the original image.

  25. Unsupervised Region-Based Image Editing of Denoising Diffusion Models

    cs.CV 2024-12 conditional novelty 4.0 of 10

    A masking and Jacobian projection technique discovers unsupervised semantic directions in diffusion model latent space, enabling region-local editing without fine-tuning.

Pith tools