[2402.12760] A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis

Computer Science > Multimedia arXiv:2402.12760 (cs) [Submitted on 20 Feb 2024 (v1), last revised 25 Mar 2026 (this version, v2)] Title:A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis Authors:Nailei Hei, Qianyu Guo, Zihao Wang, Yan Wang, Haofen Wang, Wenqiang Zhang View a PDF of the paper titled A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis, by Nailei Hei and 5 other authors View PDF HTML (experimental) Abstract:Well-designed prompts have demonstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve the desired results by manually entering prompts due to a discrepancy between novice-user-input prompts and the model-preferred prompts. To bridge the distribution gap between user input behavior and model training datasets, we first construct a novel Coarse-Fine Granularity Prompts dataset (CFP) and propose a novel User-Friendly Fine-Grained Text Generation framework (UF-FGTG) for automated prompt optimization. For CFP, we construct a novel dataset for text-to-image tasks that combines coarse and fine-grained prompts to facilitate the development of automated prompt generation methods. For UF-FGTG, we propose a novel framework that automatically translates user-input prompts into model-preferred prompts. Specifically, we propose a prompt refin...