Search papers, labs, and topics across Lattice.
This paper introduces a human-centered framework for AI-driven font design using LLMs by mapping visual features from a ResNet encoder into the LLM's latent space via a Continuous Style Projector. This enables zero-shot style interpolation and fine-grained control over font attributes, moving beyond traditional pixel- or vector-based methods. The system incorporates a Mixture Density Network (MDN) head to model handwriting trajectories, allowing for interactive exploration and generation of typefaces in real-time.
Generate custom fonts in real-time with fine-grained control over stroke and serif attributes, no commercial license required.
This paper presents a human-centered, AI-driven framework for font design that reimagines typography generation as a collaborative process between humans and large language models (LLMs). Unlike conventional pixel- or vector-based approaches, our method introduces a Continuous Style Projector that maps visual features from a pre-trained ResNet encoder into the LLM’s latent space, enabling zero-shot style interpolation and fine-grained control of stroke and serif attributes. To model handwriting trajectories more effectively, we employ a Mixture Density Network (MDN) head, allowing the system to capture multi-modal stroke distributions beyond deterministic regression. Experimental results show that users can interactively explore, mix, and generate new typefaces in real time, making the system accessible for both experts and non-experts. The approach reduces reliance on commercial font licenses and supports a wide range of applications in education, design, and digital communication. Overall, this work demonstrates how LLM-based generative models can enhance creativity, personalization, and cultural expression in typography, contributing to the broader field of AI-assisted design.
