InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow

TL;DR

InstantEdit is a rapid text-guided image editing method that preserves content and detail through a novel piecewise rectified flow approach, outperforming existing methods in speed and quality.

Contribution

The paper introduces InstantEdit, a novel few-step image editing framework utilizing RectifiedFlow with specialized inversion and guidance techniques for improved coherence and efficiency.

Findings

Outperforms state-of-the-art methods in qualitative assessments.

Achieves faster editing with comparable or better quality.

Demonstrates effectiveness on the PIE dataset.

Abstract

We propose a fast text-guided image editing method called InstantEdit based on the RectifiedFlow framework, which is structured as a few-step editing process that preserves critical content while following closely to textual instructions. Our approach leverages the straight sampling trajectories of RectifiedFlow by introducing a specialized inversion strategy called PerRFI. To maintain consistent while editable results for RectifiedFlow model, we further propose a novel regeneration method, Inversion Latent Injection, which effectively reuses latent information obtained during inversion to facilitate more coherent and detailed regeneration. Additionally, we propose a Disentangled Prompt Guidance technique to balance editability with detail preservation, and integrate a Canny-conditioned ControlNet to incorporate structural cues and suppress artifacts. Evaluation on the PIE image editing dataset demonstrates that InstantEdit is not only fast but also achieves better qualitative and quantitative results compared to state-of-the-art few-step editing methods.