MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale

• URL: http://arxiv.org/abs/2605.27235v1
• Date: Tue, 26 May 2026 16:16:19 GMT
• Title: MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale
• Abstract summary: Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content.<n>We present MRT, a 20B- parameter masked region diffusion model tailored for multi-layer transparent image generation and editing.<n>We unify three complementary tasks including text-to-layers, image-to-layers, and layers-to-layers within a shared masked region diffusion framework.
• Score: 32.89343828792041
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editing in natural language. Despite its importance, this remains an underexplored area at scale. To address this gap, we present MRT, a 20B-parameter masked region diffusion model tailored for multi-layer transparent image generation and editing, trained on over 10M multilingual design samples spanning diverse aspect ratios and textual prompts. To fully leverage this scale, we make two key technical contributions. First, we unify three complementary tasks including text-to-layers, image-to-layers, and layers-to-layers within a shared masked region diffusion framework, where selective token masking enables flexible layer-wise generation and editing. Second, to enable overflow layer generation, we introduce an overflow-aware canvas layer that handles boundary inconsistencies and supports semi-transparent background synthesis, enabling complete editable layers extending beyond visible canvas boundaries. Additionally, we apply diffusion distillation to achieve 8-step, real-time multi-layer generation with minimal quality degradation. Extensive experiments demonstrate that our framework substantially outperforms prior state-of-the-art approaches, including various commercial systems, across all three tasks, establishing a new benchmark for multi-layer transparent image generation. Notably, our model significantly outperforms the concurrent Qwen-Image-Layered model in image-to-layers quality according to user-study results, while achieving 10-100\times faster inference and reducing activation GPU memory consumption by 50-90\% during image-to-layer inference.

Related papers

• Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition [73.43121650616804]
  We propose textbfQwen-Image-Layered, an end-to-end diffusion model that decomposes a single RGB image into multiple semantically disentangled RGBA layers.<n>Our method significantly surpasses existing approaches in decomposition quality and establishes a new paradigm for consistent image editing.
  arXiv  Detail & Related papers  (2025-12-17T17:12:42Z)
• LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas [47.5187068545227]
  We present LayerComposer, an interactive framework for personalized, multi-subject text-to-image generation.<n>The proposed layered canvas allows users to place, resize, or lock input subjects through intuitive layer manipulation.<n>Our locking mechanism requires no architectural changes, relying instead on inherent positional embeddings combined with a new complementary data sampling strategy.
  arXiv  Detail & Related papers  (2025-10-23T17:59:55Z)
• Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation [63.50827603618498]
  We propose Lavida-O, a unified Masked Diffusion Model (MDM) for multimodal understanding and generation.<n>Lavida-O presents a single framework that enables image-level understanding, object grounding, image editing, and high-resolution text-to-image synthesis.<n>Lavida-O achieves state-of-the-art performance on a wide range of benchmarks including RefCOCO object grounding, GenEval text-to-image generation, and ImgEdit image editing.
  arXiv  Detail & Related papers  (2025-09-23T17:05:46Z)
• PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment [23.67447416568964]
  Transparent image layer generation plays a significant role in digital art and design.<n>Existing methods typically decompose transparent layers from a single RGB image using a set of tools or generate multiple transparent layers sequentially.<n>We propose PSDiffusion, a unified diffusion framework that leverages image composition priors from pre-trained image diffusion model for simultaneous multi-layer text-to-image generation.
  arXiv  Detail & Related papers  (2025-05-16T17:23:35Z)
• DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Mode [47.32061459437175]
  We introduce DreamLayer, a framework that enables coherent text-driven generation of multiple image layers.<n>By explicitly modeling the relationship between transparent foreground and background layers, DreamLayer builds inter-layer connections.<n>Experiments and user studies demonstrate that DreamLayer generates more coherent and well-aligned layers.
  arXiv  Detail & Related papers  (2025-03-17T05:34:11Z)
• ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation [108.69315278353932]
  We introduce the Anonymous Region Transformer (ART), which facilitates the direct generation of variable multi-layer transparent images.<n>By enabling precise control and scalable layer generation, ART establishes a new paradigm for interactive content creation.
  arXiv  Detail & Related papers  (2025-02-25T16:57:04Z)
• LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors [38.47462111828742]
  Layered content generation is crucial for creative fields like graphic design, animation, and digital art.<n>We propose a novel image generation pipeline based on Latent Diffusion Models (LDMs) that generates images with two layers.<n>We show significant improvements in visual coherence, image quality, and layer consistency compared to baseline methods.
  arXiv  Detail & Related papers  (2024-12-05T18:59:18Z)
• Generative Image Layer Decomposition with Visual Effects [49.75021036203426]
  LayerDecomp is a generative framework for image layer decomposition.<n>It produces clean backgrounds and high-quality transparent foregrounds with faithfully preserved visual effects.<n>Our method achieves superior quality in layer decomposition, outperforming existing approaches in object removal and spatial editing tasks.
  arXiv  Detail & Related papers  (2024-11-26T20:26:49Z)
• DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing [22.855660721387167]
  We transform the spatial-aware image editing task into a combination of two sub-tasks: multi-layered latent decomposition and multi-layered latent fusion. We show that our approach consistently surpasses the latest spatial editing methods, including Self-Guidance and DiffEditor.
  arXiv  Detail & Related papers  (2024-03-21T15:35:42Z)
• LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model [70.14953942532621]
  Layer-collaborative diffusion model, named LayerDiff, is designed for text-guided, multi-layered, composable image synthesis. Our model can generate high-quality multi-layered images with performance comparable to conventional whole-image generation methods. LayerDiff enables a broader range of controllable generative applications, including layer-specific image editing and style transfer.
  arXiv  Detail & Related papers  (2024-03-18T16:28:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.