PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation

TL;DR

PixelMan is a novel, efficient, inversion-free method for consistent object editing in images using diffusion models, achieving high-quality results with fewer inference steps compared to existing approaches.

Contribution

It introduces a training-free, pixel manipulation-based approach that ensures image consistency and outperforms state-of-the-art methods in fewer inference steps.

Findings

Outperforms existing methods in fewer steps

Maintains high image consistency during editing

Requires no training or inversion process

Abstract

Recent research explores the potential of Diffusion Models (DMs) for consistent object editing, which aims to modify object position, size, and composition, etc., while preserving the consistency of objects and background without changing their texture and attributes. Current inference-time methods often rely on DDIM inversion, which inherently compromises efficiency and the achievable consistency of edited images. Recent methods also utilize energy guidance which iteratively updates the predicted noise and can drive the latents away from the original image, resulting in distortions. In this paper, we propose PixelMan, an inversion-free and training-free method for achieving consistent object editing via Pixel Manipulation and generation, where we directly create a duplicate copy of the source object at target location in the pixel space, and introduce an efficient sampling approach to iteratively harmonize the manipulated object into the target location and inpaint its original location, while ensuring image consistency by anchoring the edited image to be generated to the pixel-manipulated image as well as by introducing various consistency-preserving optimization techniques during inference. Experimental evaluations based on benchmark datasets as well as extensive visual comparisons show that in as few as 16 inference steps, PixelMan outperforms a range of state-of-the-art training-based and training-free methods (usually requiring 50 steps) on multiple consistent object editing tasks.