CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers

• URL: http://arxiv.org/abs/2604.19632v1
• Date: Tue, 21 Apr 2026 16:20:19 GMT
• Title: CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers
• Abstract summary: We propose a hybrid generative framework for rendering graphic design parsing.<n>It decomposes a design image into editable text, background, and sticker layers.<n>Text regions are parsed using a vision-language model into a text design protocol.<n>Background sticker layers are generated using a multi-branch diffusion architecture.
• Score: 48.779823303618734
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explicit layer structures, limiting downstream editing. Existing graphic design parsing methods typically rely on multi-stage pipelines combining layout prediction, matting, and inpainting, which suffer from error accumulation and limited controllability. We propose a hybrid generative framework for raster-to-layer graphic design parsing that decomposes a design image into editable text, background, and sticker layers. Text regions are parsed using a vision-language model into a text rendering protocol, enabling faithful reconstruction and flexible re-editing, while background and sticker layers are generated using a multi-branch diffusion architecture with RGBA support. We further introduce ParserReward and integrate it with Group Relative Policy Optimization to align generation quality with human design preferences. Extensive experiments on two challenging datasets, \emph{i.e.,} the Parser-40K and Crello datasets, demonstrate superior performance over existing methods, \emph{eg.,} achieving an overall average improvement of 23.7\% across all metrics.

Related papers

• 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)
• 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)
• MagicQuillV2: Precise and Interactive Image Editing with Layered Visual Cues [106.02577891104079]
  We propose MagicQuill V2, a novel system that introduces a textbflayered composition paradigm to generative image editing.<n>Our method deconstructs creative intent into a stack of controllable visual cues.
  arXiv  Detail & Related papers  (2025-12-02T18:59:58Z)
• IGD: Instructional Graphic Design with Multimodal Layer Generation [83.31320209596991]
  Two-stage methods that rely primarily on layout generation lack creativity and intelligence, making graphic design still labor-intensive.<n>We propose instructional graphic designer (IGD) to swiftly generate multimodal layers with editable flexibility with only natural language instructions.
  arXiv  Detail & Related papers  (2025-07-14T04:31:15Z)
• Rethinking Layered Graphic Design Generation with a Top-Down Approach [76.33538798060326]
  Graphic design is crucial for conveying ideas and messages. Designers usually organize their work into objects, backgrounds, and vectorized text layers to simplify editing.<n>With the rise of GenAI methods, an endless supply of high-quality graphic designs in pixel format has become more accessible.<n>Despite this, non-layered designs still inspire human designers, influencing their choices in layouts and text styles, ultimately guiding the creation of layered designs.<n>Motivated by this observation, we propose Accordion, a graphic design generation framework taking the first attempt to convert AI-generated designs into editable layered designs.
  arXiv  Detail & Related papers  (2025-07-08T02:26:08Z)
• CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation [13.354283356097563]
  CreatiPoster is a framework that generates editable, multilayer compositions from optional natural-language instructions or assets.<n>To further research, we release a copyright-free corpus of 100,000 multi-layer designs.
  arXiv  Detail & Related papers  (2025-06-12T16:54:39Z)
• 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.