AmbiGen: Generating Ambigrams from Pre-trained Diffusion Model
This addresses the challenge of creating ambigrams for artists and designers, but it is incremental as it builds on existing diffusion models.
The paper tackled the problem of generating ambigrams, which are calligraphic designs with different meanings from different orientations, by distilling a pre-trained diffusion model to optimize letter outlines for legibility. The result showed an 11.6% increase in word accuracy and at least a 41.9% reduction in edit distance on common English words compared to existing methods.
Ambigrams are calligraphic designs that have different meanings depending on the viewing orientation. Creating ambigrams is a challenging task even for skilled artists, as it requires maintaining the meaning under two different viewpoints at the same time. In this work, we propose to generate ambigrams by distilling a large-scale vision and language diffusion model, namely DeepFloyd IF, to optimize the letters' outline for legibility in the two viewing orientations. Empirically, we demonstrate that our approach outperforms existing ambigram generation methods. On the 500 most common words in English, our method achieves more than an 11.6% increase in word accuracy and at least a 41.9% reduction in edit distance.