InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences

TL;DR

InstantSwap introduces a fast, efficient method for customized concept swapping in images that maintains consistency despite sharp shape differences, using attention-based object extraction and semantic-enhanced representations.

Contribution

The paper presents InstantSwap, a novel CCS approach that handles large shape disparities efficiently by combining attention-based object extraction, background preservation, and periodic gradient computation.

Findings

Outperforms existing methods in speed and consistency.

Effectively maintains foreground and background integrity during swapping.

Demonstrates versatility across diverse image scenarios.

Abstract

Recent advances in Customized Concept Swapping (CCS) enable a text-to-image model to swap a concept in the source image with a customized target concept. However, the existing methods still face the challenges of inconsistency and inefficiency. They struggle to maintain consistency in both the foreground and background during concept swapping, especially when the shape difference is large between objects. Additionally, they either require time-consuming training processes or involve redundant calculations during inference. To tackle these issues, we introduce InstantSwap, a new CCS method that aims to handle sharp shape disparity at speed. Specifically, we first extract the bbox of the object in the source image automatically based on attention map analysis and leverage the bbox to achieve both foreground and background consistency. For background consistency, we remove the gradient outside the bbox during the swapping process so that the background is free from being modified. For foreground consistency, we employ a cross-attention mechanism to inject semantic information into both source and target concepts inside the box. This helps learn semantic-enhanced representations that encourage the swapping process to focus on the foreground objects. To improve swapping speed, we avoid computing gradients at each timestep but instead calculate them periodically to reduce the number of forward passes, which improves efficiency a lot with a little sacrifice on performance. Finally, we establish a benchmark dataset to facilitate comprehensive evaluation. Extensive evaluations demonstrate the superiority and versatility of InstantSwap. Project Page: https://instantswap.github.io/