SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.12760 · AAAI · 2024

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

Yan Wang, Zihao Wang, Wenqiang Zhang, Haofen Wang, Qianyu Guo, Nailei Hei

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 userinput prompts into model-preferred prompts. Specifically, we propose a prompt refiner that continually rewrites prompts to empower users to select results that align with their unique needs. Meanwhile, we integrate image-related loss functions from the text-to-image model into the training process of text generation to generate model-preferred prompts. Additionally, we propose an adaptive feature extraction module to ensure diversity in the generated results. Experiments demonstrate that our approach is capable of generating more visually appealing and diverse images than previous state-of-theart methods, achieving an average improvement of 5% across six quality and aesthetic metrics. Data and code are available at https://github.com/Naylenv/UF-FGTG.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.12760")
get_code_for_paper("2402.12760")
have("2402.12760")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.12760.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.12760.svg)](https://syntology.ai/paper/2402.12760)

Connect an agent — have() is free.