Towards Diverse and Consistent Typography Generation
This addresses the need for automated, diverse typography generation in design workflows, though it appears incremental as it builds on existing autoregressive models.
The paper tackles the problem of generating diverse typographic styling for graphic documents by formulating it as fine-grained attribute generation and using an autoregressive model with a sampling approach for consistency. The result is a model that successfully generates diverse typographic designs while preserving consistent typographic structure, as shown in empirical studies.
In this work, we consider the typography generation task that aims at producing diverse typographic styling for the given graphic document. We formulate typography generation as a fine-grained attribute generation for multiple text elements and build an autoregressive model to generate diverse typography that matches the input design context. We further propose a simple yet effective sampling approach that respects the consistency and distinction principle of typography so that generated examples share consistent typographic styling across text elements. Our empirical study shows that our model successfully generates diverse typographic designs while preserving a consistent typographic structure.