SVGen: Interpretable Vector Graphics Generation with Large Language Models
By: Feiyu Wang , Zhiyuan Zhao , Yuandong Liu and more
Potential Business Impact:
Turns words into perfect computer drawings.
Scalable Vector Graphics (SVG) is widely used in front-end development and UI/UX design due to its scalability, editability, and rendering efficiency. However, turning creative ideas into precise vector graphics remains a time-consuming challenge. To address this, we introduce SVG-1M, a large-scale dataset of high-quality SVGs paired with natural language descriptions. Through advanced data augmentation and annotation, we create well-aligned Text to SVG training pairs, including a subset with Chain of Thought annotations for enhanced semantic guidance. Based on this dataset, we propose SVGen, an end-to-end model that generates SVG code from natural language inputs. Our approach ensures semantic accuracy and structural completeness, supported by curriculum learning and reinforcement learning optimization. Experiments show that SVGen outperforms general large models and traditional rendering methods in both effectiveness and efficiency. Code, model, and dataset are available on GitHub.
Similar Papers
UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models
CV and Pattern Recognition
AI learns to draw and understand pictures made of lines.
OmniSVG: A Unified Scalable Vector Graphics Generation Model
CV and Pattern Recognition
Creates complex, editable pictures from words.
SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation
CV and Pattern Recognition
Helps computers draw better pictures from words.