CreatiPoster：迈向可编辑与可控的多层次平面设计生成
CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation
June 12, 2025
作者: Zhao Zhang, Yutao Cheng, Dexiang Hong, Maoke Yang, Gonglei Shi, Lei Ma, Hui Zhang, Jie Shao, Xinglong Wu
cs.AI
摘要
在商业与个人领域，平面设计均扮演着至关重要的角色。然而，创作出高质量、可编辑且视觉美观的平面作品，对于初学者而言，仍是一项耗时且需专业技能的任务。现有AI工具虽能自动化部分工作流程，但在准确整合用户提供的素材、保持可编辑性以及实现专业视觉吸引力方面仍面临挑战。诸如Canva Magic Design等商业系统依赖庞大的模板库，这在实际应用中难以复制。本文中，我们提出了CreatiPoster框架，它能够根据可选的自然语言指令或素材生成可编辑的多层设计作品。首先，一个协议模型——RGBA大型多模态模型，生成一份JSON规范，详细描述每一层（文本或素材）的精确布局、层级、内容与样式，并附带简洁的背景提示。随后，一个条件背景模型基于这些渲染的前景层合成出协调的背景。我们构建了一个包含自动化评估指标的平面设计生成基准，并展示了CreatiPoster在超越领先的开源方法及专有商业系统方面的优势。为促进进一步研究，我们公开了一个包含10万份多层设计的无版权语料库。CreatiPoster支持多种应用场景，如画布编辑、文字叠加、响应式缩放、多语言适配及动态海报制作，推动了AI辅助平面设计的普及化进程。项目主页：https://github.com/graphic-design-ai/creatiposter。
English
Graphic design plays a crucial role in both commercial and personal contexts,
yet creating high-quality, editable, and aesthetically pleasing graphic
compositions remains a time-consuming and skill-intensive task, especially for
beginners. Current AI tools automate parts of the workflow, but struggle to
accurately incorporate user-supplied assets, maintain editability, and achieve
professional visual appeal. Commercial systems, like Canva Magic Design, rely
on vast template libraries, which are impractical for replicate. In this paper,
we introduce CreatiPoster, a framework that generates editable, multi-layer
compositions from optional natural-language instructions or assets. A protocol
model, an RGBA large multimodal model, first produces a JSON specification
detailing every layer (text or asset) with precise layout, hierarchy, content
and style, plus a concise background prompt. A conditional background model
then synthesizes a coherent background conditioned on this rendered foreground
layers. We construct a benchmark with automated metrics for graphic-design
generation and show that CreatiPoster surpasses leading open-source approaches
and proprietary commercial systems. To catalyze further research, we release a
copyright-free corpus of 100,000 multi-layer designs. CreatiPoster supports
diverse applications such as canvas editing, text overlay, responsive resizing,
multilingual adaptation, and animated posters, advancing the democratization of
AI-assisted graphic design. Project homepage:
https://github.com/graphic-design-ai/creatiposter