Pith. sign in

REVIEW 7 cited by

COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.16974 v2 pith:DGXSNWM5 submitted 2023-11-28 cs.CV

Peidong Jia , Chenxuan Li , Yuhui Yuan , Zeyu Liu , Yichao Shen , Bohan Chen , Xingru Chen , Yinglin Zheng
show 5 more authors
Dong Chen Ji Li Xiaodong Xie Shanghang Zhang Baining Guo
This is my paper
classification cs.CV
keywords designcolegenerationgraphicmodelsmulti-layeredsystemcomplex
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Graphic design, which has been evolving since the 15th century, plays a crucial role in advertising. The creation of high-quality designs demands design-oriented planning, reasoning, and layer-wise generation. Unlike the recent CanvaGPT, which integrates GPT-4 with existing design templates to build a custom GPT, this paper introduces the COLE system - a hierarchical generation framework designed to comprehensively address these challenges. This COLE system can transform a vague intention prompt into a high-quality multi-layered graphic design, while also supporting flexible editing based on user input. Examples of such input might include directives like ``design a poster for Hisaishi's concert.'' The key insight is to dissect the complex task of text-to-design generation into a hierarchy of simpler sub-tasks, each addressed by specialized models working collaboratively. The results from these models are then consolidated to produce a cohesive final output. Our hierarchical task decomposition can streamline the complex process and significantly enhance generation reliability. Our COLE system comprises multiple fine-tuned Large Language Models (LLMs), Large Multimodal Models (LMMs), and Diffusion Models (DMs), each specifically tailored for design-aware layer-wise captioning, layout planning, reasoning, and the task of generating images and text. Furthermore, we construct the DESIGNINTENTION benchmark to demonstrate the superiority of our COLE system over existing methods in generating high-quality graphic designs from user intent. Last, we present a Canva-like multi-layered image editing tool to support flexible editing of the generated multi-layered graphic design images. We perceive our COLE system as an important step towards addressing more complex and multi-layered graphic design generation tasks in the future.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

    cs.CV 2026-04 conditional novelty 7.0 of 10

    A 49-task layered-design benchmark shows frontier AI models leave most precision-heavy graphic design tasks unsolved, with only two tasks mostly solved.

  2. StructuredEdit: Constraint-Aware Graphic Design Editing via Differentiable Parameter Propagation

    cs.GR 2026-07 conditional novelty 6.0 of 10

    Differentiable Parameter Propagation trains VLMs to emit design-parameter patches under hard layout and typography constraints, reaching 89% constraint satisfaction versus 52% for GPT-4V.

  3. IGD: Instructional Graphic Design with Multimodal Layer Generation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    IGD generates editable multi-layer graphic designs (posters, slides, stickers) from text instructions using an MLLM for layout and a diffusion model for image assets.

  4. Rethinking Layered Graphic Design Generation with a Top-Down Approach

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Accordion decomposes AI-generated raster designs into editable background, object, and vectorized text layers using a VLM-driven top-down planning pipeline.

  5. CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A protocol model writes editable JSON layer specs, then a diffusion model fills in a matching background, producing multi-layer posters that beat several commercial tools in a small benchmark.

  6. PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A new open dataset and synthesis pipeline for high-quality multi-layer transparent images, plus a fine-tuned ART+ model that users preferred over the original ART in about 60 percent of comparisons.

  7. DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Design

    cs.CV 2025-07 conditional novelty 5.0 of 10

    DreamPoster fine-tunes Seedream3.0 with a deconstruction-recaptioning dataset pipeline and a three-stage curriculum to turn image-plus-text inputs into finished posters, reporting substantially higher usability than G...

Pith tools