LayerDiffusion: Layered Controlled Image Editing with Diffusion Models

TL;DR

LayerDiffusion introduces a layered diffusion approach for precise, multi-faceted image editing guided by text, enabling seamless attribute changes and background replacements while maintaining image consistency.

Contribution

The paper presents a novel layered diffusion framework that allows for controlled, multi-action image editing guided by text, improving coherence and attribute preservation.

Findings

Outperforms existing methods in image-text alignment accuracy.

Maintains high feature similarity to input images.

Enables complex, multi-action editing with seamless background integration.

Abstract

Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining consistency between the subject and the background remains challenging. In this paper, we propose LayerDiffusion, a semantic-based layered controlled image editing method. Our method enables non-rigid editing and attribute modification of specific subjects while preserving their unique characteristics and seamlessly integrating them into new backgrounds. We leverage a large-scale text-to-image model and employ a layered controlled optimization strategy combined with layered diffusion training. During the diffusion process, an iterative guidance strategy is used to generate a final image that aligns with the textual description. Experimental results demonstrate the effectiveness of our method in generating highly coherent images that closely align with the given textual description. The edited images maintain a high similarity to the features of the input image and surpass the performance of current leading image editing methods. LayerDiffusion opens up new possibilities for controllable image editing.