Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Wen, Liu, Zhaocheng, Gui, Yuwei, Yuan, Tingyu, Su, Yunyue, Fang, Bowen, Zhao, Chaoyang, Liu, Qiang, Wang, Liang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.07217
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911198692245504
author Ye, Wen
Liu, Zhaocheng
Gui, Yuwei
Yuan, Tingyu
Su, Yunyue
Fang, Bowen
Zhao, Chaoyang
Liu, Qiang
Wang, Liang
author_facet Ye, Wen
Liu, Zhaocheng
Gui, Yuwei
Yuan, Tingyu
Su, Yunyue
Fang, Bowen
Zhao, Chaoyang
Liu, Qiang
Wang, Liang
contents Text-to-image synthesis has made remarkable progress, yet accurately interpreting complex and lengthy prompts remains challenging, often resulting in semantic inconsistencies and missing details. Existing solutions, such as fine-tuning, are model-specific and require training, while prior automatic prompt optimization (APO) approaches typically lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness. Meanwhile, test-time scaling methods operate on fixed prompts and on noise or sample numbers, limiting their interpretability and adaptability. To solve these, we introduce a flexible and efficient test-time prompt optimization strategy that operates directly on the input text. We propose a plug-and-play multi-agent system called GenPilot, integrating error analysis, clustering-based adaptive exploration, fine-grained verification, and a memory module for iterative optimization. Our approach is model-agnostic, interpretable, and well-suited for handling long and complex prompts. Simultaneously, we summarize the common patterns of errors and the refinement strategy, offering more experience and encouraging further exploration. Experiments on DPG-bench and Geneval with improvements of up to 16.9% and 5.7% demonstrate the strong capability of our methods in enhancing the text and image consistency and structural coherence of generated images, revealing the effectiveness of our test-time prompt optimization strategy. The code is available at https://github.com/27yw/GenPilot.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07217
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation
Ye, Wen
Liu, Zhaocheng
Gui, Yuwei
Yuan, Tingyu
Su, Yunyue
Fang, Bowen
Zhao, Chaoyang
Liu, Qiang
Wang, Liang
Computer Vision and Pattern Recognition
Artificial Intelligence
Text-to-image synthesis has made remarkable progress, yet accurately interpreting complex and lengthy prompts remains challenging, often resulting in semantic inconsistencies and missing details. Existing solutions, such as fine-tuning, are model-specific and require training, while prior automatic prompt optimization (APO) approaches typically lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness. Meanwhile, test-time scaling methods operate on fixed prompts and on noise or sample numbers, limiting their interpretability and adaptability. To solve these, we introduce a flexible and efficient test-time prompt optimization strategy that operates directly on the input text. We propose a plug-and-play multi-agent system called GenPilot, integrating error analysis, clustering-based adaptive exploration, fine-grained verification, and a memory module for iterative optimization. Our approach is model-agnostic, interpretable, and well-suited for handling long and complex prompts. Simultaneously, we summarize the common patterns of errors and the refinement strategy, offering more experience and encouraging further exploration. Experiments on DPG-bench and Geneval with improvements of up to 16.9% and 5.7% demonstrate the strong capability of our methods in enhancing the text and image consistency and structural coherence of generated images, revealing the effectiveness of our test-time prompt optimization strategy. The code is available at https://github.com/27yw/GenPilot.
title GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.07217