AI Based Font Pair Suggestion Modelling For Graphic Design

TL;DR

This paper introduces a scalable AI system for recommending font pairs in graphic design, utilizing visual embeddings, a font category dataset, and a lightweight language model to enhance design suggestions.

Contribution

It presents a novel, scalable approach combining font embeddings, a font category dataset, and a mini language model for effective font pair recommendations.

Findings

Developed font visual embeddings and stroke width algorithm

Created a font category to font mapping dataset

Implemented a lightweight language model for recommendations

Abstract

One of the key challenges of AI generated designs in Microsoft Designer is selecting the most contextually relevant and novel fonts for the design suggestions. Previous efforts involved manually mapping design intent to fonts. Though this was high quality, this method does not scale for a large number of fonts (3000+) and numerous user intents for graphic design. In this work we create font visual embeddings, a font stroke width algorithm, a font category to font mapping dataset, an LLM-based category utilization description and a lightweight, low latency knowledge-distilled mini language model (Mini LM V2) to recommend multiple pairs of contextual heading and subheading fonts for beautiful and intuitive designs. We also utilize a weighted scoring mechanism, nearest neighbor approach and stratified sampling to rank the font pairs and bring novelty to the predictions.