Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Shengming, Zhang, Zekai, Tang, Zecheng, Gao, Kaiyuan, Xu, Xiao, Yan, Kun, Li, Jiahao, Chen, Yilei, Chen, Yuxiang, Shum, Heung-Yeung, Ni, Lionel M., Zhou, Jingren, Lin, Junyang, Wu, Chenfei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911324409167872
author Yin, Shengming
Zhang, Zekai
Tang, Zecheng
Gao, Kaiyuan
Xu, Xiao
Yan, Kun
Li, Jiahao
Chen, Yilei
Chen, Yuxiang
Shum, Heung-Yeung
Ni, Lionel M.
Zhou, Jingren
Lin, Junyang
Wu, Chenfei
author_facet Yin, Shengming
Zhang, Zekai
Tang, Zecheng
Gao, Kaiyuan
Xu, Xiao
Yan, Kun
Li, Jiahao
Chen, Yilei
Chen, Yuxiang
Shum, Heung-Yeung
Ni, Lionel M.
Zhou, Jingren
Lin, Junyang
Wu, Chenfei
contents Recent visual generative models often struggle with consistency during image editing due to the entangled nature of raster images, where all visual content is fused into a single canvas. In contrast, professional design tools employ layered representations, allowing isolated edits while preserving consistency. Motivated by this, we propose \textbf{Qwen-Image-Layered}, an end-to-end diffusion model that decomposes a single RGB image into multiple semantically disentangled RGBA layers, enabling \textbf{inherent editability}, where each RGBA layer can be independently manipulated without affecting other content. To support variable-length decomposition, we introduce three key components: (1) an RGBA-VAE to unify the latent representations of RGB and RGBA images; (2) a VLD-MMDiT (Variable Layers Decomposition MMDiT) architecture capable of decomposing a variable number of image layers; and (3) a Multi-stage Training strategy to adapt a pretrained image generation model into a multilayer image decomposer. Furthermore, to address the scarcity of high-quality multilayer training images, we build a pipeline to extract and annotate multilayer images from Photoshop documents (PSD). Experiments demonstrate that our method significantly surpasses existing approaches in decomposition quality and establishes a new paradigm for consistent image editing. Our code and models are released on \href{https://github.com/QwenLM/Qwen-Image-Layered}{https://github.com/QwenLM/Qwen-Image-Layered}
format Preprint
id arxiv_https___arxiv_org_abs_2512_15603
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition
Yin, Shengming
Zhang, Zekai
Tang, Zecheng
Gao, Kaiyuan
Xu, Xiao
Yan, Kun
Li, Jiahao
Chen, Yilei
Chen, Yuxiang
Shum, Heung-Yeung
Ni, Lionel M.
Zhou, Jingren
Lin, Junyang
Wu, Chenfei
Computer Vision and Pattern Recognition
Recent visual generative models often struggle with consistency during image editing due to the entangled nature of raster images, where all visual content is fused into a single canvas. In contrast, professional design tools employ layered representations, allowing isolated edits while preserving consistency. Motivated by this, we propose \textbf{Qwen-Image-Layered}, an end-to-end diffusion model that decomposes a single RGB image into multiple semantically disentangled RGBA layers, enabling \textbf{inherent editability}, where each RGBA layer can be independently manipulated without affecting other content. To support variable-length decomposition, we introduce three key components: (1) an RGBA-VAE to unify the latent representations of RGB and RGBA images; (2) a VLD-MMDiT (Variable Layers Decomposition MMDiT) architecture capable of decomposing a variable number of image layers; and (3) a Multi-stage Training strategy to adapt a pretrained image generation model into a multilayer image decomposer. Furthermore, to address the scarcity of high-quality multilayer training images, we build a pipeline to extract and annotate multilayer images from Photoshop documents (PSD). Experiments demonstrate that our method significantly surpasses existing approaches in decomposition quality and establishes a new paradigm for consistent image editing. Our code and models are released on \href{https://github.com/QwenLM/Qwen-Image-Layered}{https://github.com/QwenLM/Qwen-Image-Layered}
title Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.15603