# Evolutionary Token-Level Prompt Optimization for Diffusion Models

Source: [Evolutionary Token-Level Prompt Optimization for Diffusion Models](<https://www.sota2.com/research/paper/69ddc9e07d0172140ec797b6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-15T05:00:04.591Z

Authors: Dom\\'icio Pereira Neto, Jo\\~ao Correia, Penousal Machado

Published: 2026-04-10T19:43:06.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Prompt-embedding Optimization on Parti Prompts (36)](<https://www.sota2.com/research/sota/prompt-embedding-optimization-on-parti-prompts-36.md>): Prompt-embedding Optimization; Parti Prompts (36); LAION Aesthetic V2 Average Score: 7.45.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.09861>)

[PDF](<https://arxiv.org/pdf/2604.09861.pdf>)
