{"ID":2828130,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.15603","arxiv_id":"2512.15603","title":"Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition","abstract":"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}","short_abstract":"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. Motivate...","url_abs":"https://arxiv.org/abs/2512.15603","url_pdf":"https://arxiv.org/pdf/2512.15603v1","authors":"[\"Shengming Yin\",\"Zekai Zhang\",\"Zecheng Tang\",\"Kaiyuan Gao\",\"Xiao Xu\",\"Kun Yan\",\"Jiahao Li\",\"Yilei Chen\",\"Yuxiang Chen\",\"Heung-Yeung Shum\",\"Lionel M. Ni\",\"Jingren Zhou\",\"Junyang Lin\",\"Chenfei Wu\"]","published":"2025-12-17T17:12:42Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Variational Autoencoder\"]","has_code":false,"code_links":[{"ID":605853,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2828130,"paper_url":"https://arxiv.org/abs/2512.15603","paper_title":"Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition","repo_url":"https://github.com/QwenLM/Qwen-Image-Layered","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}