用大模型和扩散模型生成高质量可编辑的矢量图
Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
- 先用大模型生成基础几何模板，再用扩散模型优化路径
- 在隐空间中调整坐标，提升形状规则性和细节复杂度
- 支持自然语言编辑，普通人也能做专业矢量设计
可缩放矢量图形（SVG）已成为数字设计中的标准格式，具备分辨率无关性和对单个元素的精确控制。然而，高质量SVG内容的创作仍具挑战性，需专业软件技能与大量时间投入。现有文本到SVG生成方法在形状规则性、泛化能力与表达力方面仍存在局限。为此，我们提出Chat2SVG，一种融合大语言模型（LLM）与图像扩散模型的混合框架。该方法首先由LLM从基本几何原语生成语义合理的SVG模板；随后，在图像扩散模型引导下，通过双阶段优化流程在隐空间中精炼路径并调整点坐标，以增强几何复杂性。大量实验表明，Chat2SVG在视觉保真度、路径规则性与语义一致性方面均优于现有方法。此外，系统支持自然语言指令进行直观编辑，使专业级矢量图形创作对所有用户开放。
原文摘要 · Abstract (English)
Scalable Vector Graphics (SVG) has become the de facto standard for vector graphics in digital design, offering resolution independence and precise control over individual elements. Despite their advantages, creating high-quality SVG content remains challenging, as it demands technical expertise with professional editing software and a considerable time investment to craft complex shapes. Recent text-to-SVG generation methods aim to make vector graphics creation more accessible, but they still encounter limitations in shape regularity, generalization ability, and expressiveness. To address these challenges, we introduce Chat2SVG, a hybrid framework that combines the strengths of Large Language Models (LLMs) and image diffusion models for text-to-SVG generation. Our approach first uses an LLM to generate semantically meaningful SVG templates from basic geometric primitives. Guided by image diffusion models, a dual-stage optimization pipeline refines paths in latent space and adjusts point coordinates to enhance geometric complexity. Extensive experiments show that Chat2SVG outperforms existing methods in visual fidelity, path regularity, and semantic alignment. Additionally, our system enables intuitive editing through natural language instructions, making professional vector graphics creation accessible to all users.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。