Modern text-to-image generation systems have enabled the creation of remarkably realistic and high-quality visuals, yet they often falter when handling the inherent ambiguities in user prompts. In this work, we present Twin-Co, a framework that leverages synchronized, co-adaptive dialogue to progressively refine image generation. Instead of a static generation process, Twin-Co employs a dynamic, iterative workflow where an intelligent dialogue agent continuously interacts with the user. Initially, a base image is generated from the user's prompt. Then, through a series of synchronized dialogue exchanges, the system adapts and optimizes the image according to evolving user feedback. The co-adaptive process allows the system to progressively narrow down ambiguities and better align with user intent. Experiments demonstrate that Twin-Co not only enhances user experience by reducing trial-and-error iterations but also improves the quality of the generated images, streamlining the creative process across various applications.
View on arXiv@article{wang2025_2504.14868,
title={ Twin Co-Adaptive Dialogue for Progressive Image Generation },
author={ Jianhui Wang and Yangfan He and Yan Zhong and Xinyuan Song and Jiayi Su and Yuheng Feng and Hongyang He and Wenyu Zhu and Xinhang Yuan and Kuan Lu and Menghao Huo and Miao Zhang and Keqin Li and Jiaqi Chen and Tianyu Shi and Xueqian Wang },
journal={arXiv preprint arXiv:2504.14868},
year={ 2025 }
}