DOGS: Design-Space Sampling for Prompt-Driven Logo Generation

2026-10-07

AI Summary

This study addresses the limitations of text prompts in structured logo generation, specifically their difficulty in encoding relational priors and susceptibility to trademark infringement. To overcome these challenges, this work proposes a graph-structured design space sampling paradigm that reformulates logo generation as a sampling process. The approach mines graph-based design grammars and employs a closed vocabulary. A Generative Flow Network (GFlowNet) serves as the generator, optimized via multi-objective rewards encompassing recognizability, aesthetics, and originality. By operating at the structural level, this framework inherently mitigates trademark infringement risks. Experimental results demonstrate that the proposed method significantly outperforms baselines on open-source renderers, producing logos with high recognizability, aesthetic quality, and diversity while substantially reducing the probability of infringement.

Abstract

Prompt optimization for text-to-image (T2I) generation has been pursued almost entirely as text rewriting, in which a short user brief is expanded into a longer, model-preferred token sequence. We argue that such a language-space formulation is ill-suited to structured visual design tasks such as logo creation, where a one-line brief leaves most design decisions unspecified. These decisions depend on relational priors that a linear sequence cannot encode, and they leave an uncontrolled channel through which protected marks may be reproduced. We therefore recast logo prompting as sampling within a structured design space, and instantiate this idea as DOGS (Design-space prompting with an Originality-aware GFlowNet Sampler). From a large corpus of real-world logos, we mine a typed, graph-structured design grammar whose edges record empirical co-occurrence. A GFlowNet sampler then generates design graphs with probability proportional to a terminal reward that combines recognizability, aesthetics, and corpus-relative originality. Every slot draws only from a closed design-level vocabulary, and any infringement-inducing or harmful token is removed during parsing. The originality reward further penalizes proximity to existing logos, thereby incorporating infringement avoidance into the method by construction. On two open-source renderers and against nine baselines, DOGS produces logos that are more recognizable and aesthetic, substantially more diverse, and far less prone to trademark infringement.

Problem

• Prompt-driven logo generation
• Text-to-image generation
• Structured visual design
• Trademark infringement
• Design-space sampling

Innovation

• Design-space sampling
• GFlowNet
• Graph-structured design grammar
• Prompt-driven logo generation
• Originality-aware reward