# Evolve to Inspire: Novelty Search for Diverse Image Generation

arXiv: https://arxiv.org/abs/2511.00686 · HTML: https://mlsanity.com/paper/2511.00686/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 1 Nov 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022)
- [Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts](https://mlsanity.com/paper/2402.16822/) (2024)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [Language Model Crossover: Variation through Few-Shot Prompting](https://mlsanity.com/paper/2302.12170/) (2023)
- [Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space](https://mlsanity.com/paper/1912.02400/) (2019)
- [Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models](https://mlsanity.com/paper/2304.09337/) (2023)
- [Forcing Diffuse Distributions out of Language Models](https://mlsanity.com/paper/2404.10859/) (2024)
- [Modern Evolution Strategies for Creativity: Fitting Concrete Images and Abstract Concepts](https://mlsanity.com/paper/2109.08857/) (2021)
- [Quality-Diversity through AI Feedback](https://mlsanity.com/paper/2310.13032/) (2023)
- [Universal Prompt Optimizer for Safe Text-to-Image Generation](https://mlsanity.com/paper/2402.10882/) (2024)
- [Prompt Expansion for Adaptive Text-to-Image Generation](https://mlsanity.com/paper/2312.16720/) (2023)
- [Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting](https://mlsanity.com/paper/2310.08129/) (2023)
- [Diversity-Rewarded CFG Distillation](https://mlsanity.com/paper/2410.06084/) (2024)
- [Diversity and Diffusion: Observations on Synthetic Image Distributions with Stable Diffusion](https://mlsanity.com/paper/2311.00056/) (2023)

## Built on by (most cited first, 1 of 1)

- [Uncovering the Generative Landscape of Diffusion Models: A Spectral-Guided Quality-Diversity Diffusion Framework](https://mlsanity.com/paper/2610.15724/) (2026)

## Abstract (arXiv)

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.