Evolutionary Token-Level Prompt Optimization for Diffusion Models
For users of diffusion models, this provides an automated, model-agnostic prompt optimization method that reduces manual trial and error.
This paper tackles prompt sensitivity in text-to-image diffusion models by evolving token vectors with a genetic algorithm, achieving up to 23.93% improvement in fitness over baselines like Promptist and random search on the Parti Prompts dataset.
Text-to-image diffusion models exhibit strong generative performance but remain highly sensitive to prompt formulation, often requiring extensive manual trial and error to obtain satisfactory results. This motivates the development of automated, model-agnostic prompt optimization methods that can systematically explore the conditioning space beyond conventional text rewriting. This work investigates the use of a Genetic Algorithm (GA) for prompt optimization by directly evolving the token vectors employed by CLIP-based diffusion models. The GA optimizes a fitness function that combines aesthetic quality, measured by the LAION Aesthetic Predictor V2, with prompt-image alignment, assessed via CLIPScore. Experiments on 36 prompts from the Parti Prompts (P2) dataset show that the proposed approach outperforms the baseline methods, including Promptist and random search, achieving up to a 23.93% improvement in fitness. Overall, the method is adaptable to image generation models with tokenized text encoders and provides a modular framework for future extensions, the limitations and prospects of which are discussed.