UniWorld-Design: From Pixel Generation to Layer-Native Design

• URL: http://arxiv.org/abs/2608.03971v1
• Date: Tue, 04 Aug 2026 17:39:37 GMT
• Title: UniWorld-Design: From Pixel Generation to Layer-Native Design
• Abstract summary: We introduce UniWorld-Design, a framework that redefines image generation from flat pixel synthesis to structured visual composition.<n>Our key insight is that pixels define how an image is rendered, whereas layers define how an image is created, understood, and edited.
• Score: 33.991198949217164
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce UniWorld-Design, a framework that redefines image generation from flat pixel synthesis to structured visual composition, with semantic RGBA layers as the atomic units of generation, understanding, and editing. Our key insight is that pixels define how an image is rendered, whereas layers define how an image is created, understood, and edited. Just as human designers create and manipulate visual content through layers rather than raw pixels, UniWorld-Design equips multimodal generative models with a layer-native design space. UniWorld-Design comprises two models. The Text-to-RGBA (T2RGBA) model generates standalone RGBA assets directly from text. The Image-to-Layer (I2L) model conditions on a finished image, a global instruction and per-layer prompts, and jointly produces ordered, complete semantic RGBA layers. Its instruction interface supports top-level decomposition, recursive decomposition and targeted extraction, making layering an instruction-addressable operation for agentic editing. Because I2L learns complete semantic objects rather than visible-pixel partitions, its layers stay usable when moved or removed. On the Crello benchmark, I2L reduces per-layer RGB L1 error by 37% and achieves a 34% relative improvement in Alpha Soft IoU over Qwen-Image-Layered. Separately, T2RGBA achieves the highest CLIP Score, outperforming LayerDiffuse and OmniAlpha.

Related papers

• Bunraku: Turning a Single Illustration into an Editable Live2D Character [25.17979482882208]
  We present the first system that generates all the structured information a Live2D runtime consumes.<n>Stage 1 casts layered decomposition as a layered diffusion process under a Live2D-aware organ-level taxonomy.<n>Stage 2 builds a content-conforming triangle mesh for each layer from its alpha channel alone, then predicts the keypose displacement field of all layers jointly.
  arXiv  Detail & Related papers  (2026-07-29T18:06:17Z)
• LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition [4.794064830289192]
  We propose LaDe, a latent diffusion framework that generates a flexible number of semantically meaningful layers.<n>LaDe combines three components: an LLM-based prompt expander that transforms a short user intent into structured per-layer descriptions.<n>By conditioning on layer samples during training, our unified framework supports three tasks: text-to-image generation, text-to-layers media design generation, and media design decomposition.
  arXiv  Detail & Related papers  (2026-03-18T17:34:07Z)
• Referring Layer Decomposition [25.128453386102887]
  We introduce the Referring Layer Decomposition (RLD) task, which predicts complete RGBA layers from a single RGB image.<n>At the core is the RefLade, a large-scale dataset comprising 1.11M image-layer-prompt triplets produced by our scalable data engine.<n>We present RefLayer, a simple baseline designed for prompt-conditioned layer decomposition, achieving high visual fidelity and semantic alignment.
  arXiv  Detail & Related papers  (2026-02-22T22:05:17Z)
• Controllable Layered Image Generation for Real-World Editing [49.81321254149423]
  LASAGNA is a novel, unified framework that generates an image jointly with its composing layers.<n>We introduce LASAGNA-48K, a new dataset composed of clean backgrounds and RGBA foregrounds with physically grounded visual effects.<n>We demonstrate that LASAGNA excels in generating highly consistent and coherent results across multiple image layers simultaneously.
  arXiv  Detail & Related papers  (2026-01-21T22:29:33Z)
• 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)
• UniModel: A Visual-Only Framework for Unified Multimodal Understanding and Generation [51.31795451147935]
  We present a unified generative model that supports visual understanding and visual generation within a single pixel-to-pixel diffusion framework.<n>Our goal is to achieve unification along three axes: the model, the tasks, and the representations.<n> Experiments on text-to-image synthesis and image-to-text understanding demonstrate strong cross-modal alignment.
  arXiv  Detail & Related papers  (2025-11-21T03:02:10Z)
• RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration [94.49712266736141]
  RAM++ is a two-stage framework for all-in-one image restoration.<n>It integrates high-level semantic understanding with low-level texture generation.<n>It addresses the limitations of existing degradation-oriented methods in extreme scenarios.
  arXiv  Detail & Related papers  (2025-09-15T15:24:15Z)
• MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation [54.64194935409982]
  We introduce MuLAn: a novel dataset comprising over 44K MUlti-Layer-wise RGBA decompositions. MuLAn is the first photorealistic resource providing instance decomposition and spatial information for high quality images. We aim to encourage the development of novel generation and editing technology, in particular layer-wise solutions.
  arXiv  Detail & Related papers  (2024-04-03T14:58:00Z)

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.