ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention

TL;DR

ContextDrag introduces a novel in-context image editing framework that enables precise drag-based manipulation by injecting reference features into attention layers and aligning positional embeddings, avoiding inversion errors.

Contribution

It proposes Context-preserving Token Injection and Position-Aligned Attention to enhance drag-based image editing without inversion or fine-tuning.

Findings

Achieves state-of-the-art editing accuracy on DragBench datasets.

Preserves rich texture details through direct feature encoding.

Validates effectiveness via comprehensive ablations.

Abstract

Drag-based image editing enables intuitive visual manipulation through point-based drag operations. Existing methods mainly rely on diffusion inversion or pixel-space warping with inpainting. However, inversion inherently introduces approximation errors that degrade texture fidelity, whereas rigid pixel-space operations discard semantic context and produce unnatural deformations. To address these issues, we introduce ContextDrag, to our knowledge the first framework that brings drag-based manipulation into the in-context image editing paradigm. By leveraging the in-context capabilities of editing models (e.g., FLUX-Kontext), ContextDrag enables precise drag editing without inversion or fine-tuning. Specifically, we first propose Context-preserving Token Injection (CTI), which injects VAE-encoded reference features into attention layers at spatially aligned target positions, guided by latent-space correspondences estimated directly from user-specified control points. By operating on clean, directly encoded features rather than noisy inversion outputs, CTI preserves rich texture details and enables precise drag control. Second, we propose Position-Aligned Attention (PAA) to eliminate interference caused by spatial displacement of reference features. PAA re-encodes positional embeddings of displaced reference tokens to match their target locations, and masks overlapping regions between source and destination to prevent conflicting features from degrading visual consistency. Experiments on DragBench-SR and DragBench-DR demonstrate that ContextDrag achieves SOTA editing accuracy and overall quality, and comprehensive ablations validate the effectiveness of each proposed component. Code will be publicly available.