Shifting the Breaking Point of Flow Matching for Multi-Instance Editing

TL;DR

This paper introduces Instance-Disentangled Attention to improve multi-instance editing in flow matching models, enabling independent, localized edits without interference, and demonstrates its effectiveness on natural images and infographics.

Contribution

It proposes a novel attention mechanism that disentangles instance-specific edits in flow-based models, addressing a key limitation of existing global conditioning methods.

Findings

Enhanced edit disentanglement and locality.

Preserved global coherence in multi-instance editing.

Effective on natural images and infographics.

Abstract

Flow matching models have recently emerged as an efficient alternative to diffusion, especially for text-guided image generation and editing, offering faster inference through continuous-time dynamics. However, existing flow-based editors predominantly support global or single-instruction edits and struggle with multi-instance scenarios, where multiple parts of a reference input must be edited independently without semantic interference. We identify this limitation as a consequence of globally conditioned velocity fields and joint attention mechanisms, which entangle concurrent edits. To address this issue, we introduce Instance-Disentangled Attention, a mechanism that partitions joint attention operations, enforcing binding between instance-specific textual instructions and spatial regions during velocity field estimation. We evaluate our approach on both natural image editing and a newly introduced benchmark of text-dense infographics with region-level editing instructions. Experimental results demonstrate that our approach promotes edit disentanglement and locality while preserving global output coherence, enabling single-pass, instance-level editing.