Layers have become indispensable tools for professional artists, allowing them to build a hierarchical structure that enables independent control over individual visual elements. In this paper, we propose LayeringDiff, a novel pipeline for the synthesis of layered images, which begins by generating a composite image using an off-the-shelf image generative model, followed by disassembling the image into its constituent foreground and background layers.
By extracting layers from a composite image, rather than generating them from scratch, LayeringDiff bypasses the need for large-scale training to develop generative capabilities for individual layers. Furthermore, by utilizing a pretrained off-the-shelf generative model, our method can produce diverse contents and object scales in synthesized layers. For effective layer decomposition, we adapt a large-scale pretrained generative prior to estimate foreground and background layers. We also propose high-frequency alignment modules to refine the fine details of the estimated layers. Our comprehensive experiments demonstrate that our approach effectively synthesizes layered images and supports various practical applications.
An off-the-shelf text-to-image model synthesizes a diverse, high-quality composite image without task-specific fine-tuning.
The foreground prompt guides detection, segmentation, and matting to estimate the foreground region and alpha mask.
The FBDD and high-frequency alignment modules recover detailed foreground and background layers using a pretrained generative prior.
@article{kang2025layeringdiff,
title = {LayeringDiff: Layered Image Synthesis via Generation,
then Disassembly with Generative Knowledge},
author = {Kang, Kyoungkook and Sim, Gyujin and Kim, Geonung and
Kim, Donguk and Nam, Seungho and Cho, Sunghyun},
journal = {arXiv preprint arXiv:2501.01197},
year = {2025}
}