Evolve to Inspire: Novelty Search for Diverse Image Generation
This addresses the problem of low diversity in image generation for creative and exploratory applications, representing a novel method for a known bottleneck.
The paper tackles the limited output diversity in text-to-image diffusion models by introducing WANDER, a novelty search-based approach that uses LLMs for semantic evolution and CLIP embeddings to quantify novelty, significantly outperforming existing baselines in diversity metrics.
Text-to-image diffusion models, while proficient at generating high-fidelity images, often suffer from limited output diversity, hindering their application in exploratory and ideation tasks. Existing prompt optimization techniques typically target aesthetic fitness or are ill-suited to the creative visual domain. To address this shortcoming, we introduce WANDER, a novelty search-based approach to generating diverse sets of images from a single input prompt. WANDER operates directly on natural language prompts, employing a Large Language Model (LLM) for semantic evolution of diverse sets of images, and using CLIP embeddings to quantify novelty. We additionally apply emitters to guide the search into distinct regions of the prompt space, and demonstrate that they boost the diversity of the generated images. Empirical evaluations using FLUX-DEV for generation and GPT-4o-mini for mutation demonstrate that WANDER significantly outperforms existing evolutionary prompt optimization baselines in diversity metrics. Ablation studies confirm the efficacy of emitters.