Our LLM4SVG is designed to: (a) Understand the semantics of SVG (Scalable Vector Graphics) source code and directly extract the meanings conveyed by vector images; (b) Generate corresponding structured SVG representations from textual prompts and decode them into SVG source code that accurately reflects the described content.

llm4svg是一个创新项目，旨在利用大型语言模型（llm）来理解和生成复杂的矢量图形（svg）。 该项目通过将LLM技术应用于SVG领域，实现了从文本描述直接生成SVG图形，并能解析SVG代码的语义，提取图形的含义。

2024年12月15日 · LLM4SVG facilitates a deeper understanding of SVG components through learnable semantic tokens, which precisely encode these tokens and their corresponding properties to generate semantically aligned SVG outputs.

2023年6月9日 · To enable the LLM to process images, we convert them into a representation given by Scalable Vector Graphics (SVG). To study what the LLM can do with this XML-based textual description of images, we test the LLM on three broad computer vision tasks: (i) visual reasoning and question answering, (ii) image classification under distribution shift ...

2024年5月9日 · 方法：StarVector 是一种多模态SVG生成模型，它有效地集成了代码生成大型语言模型（CodeLLMs）和视觉模型。 从以下对比中可以看出， StarVector 和 GPT-4 V 有类似的 SVG 生成 功能。

🥨 Lobe Icons - Popular AI / LLM Model Brand SVG Logo and Icon Collection. 📊 Lobe Charts - React modern charts components built on recharts

2024年5月8日 · 研究目标 ：提出一种多模态大型语言模型（mllm），能够直接从图像和文本指令生成可缩放矢量图形代码（svg），在图像矢量化和文本驱动的 svg 生成任务中实现更优性能。

LLM4SVG facilitates a deeper understanding of SVG components through learnable semantic tokens, which precisely encode these tokens and their corresponding properties to generate semantically aligned SVG outputs.

Introducing LLM4SVG: Advancing LLM Capabilities for SVG Understanding and Generation. We present LLM4SVG, a pioneering model designed to bridge the gap in SVG generation within large language models (LLMs), addressing challenges in accurately predicting vector primitives and managing occlusions.

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.