Pith. sign in

REVIEW 9 cited by

DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

Chong Mou , Xintao Wang , Jiechong Song , Ying Shan , Jian Zhang This is my paper · ORCID
classification cs.CV
keywords editingdiffusiondragondiffusionguidanceimageimagesmodelmodels
verification ladder T0 review T1 audit T2 compute T3 formal
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 9 Pith papers

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

  1. 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.

  2. 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.

  3. 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.

  4. 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.

  5. 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.

  6. 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.

  7. 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.

  8. 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.

  9. 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.

Pith tools