paper-with-me

Papers

PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization

2025-09-15 · Dawei Xiang, Wenyan Xu, Kexin Chu, Tianqi Ding, Zixu Shen, Yiming Zeng, Jianchang Su, Wei Zhang arxiv

The rapid advancement of generative AI has democratized access to powerful tools such as Text-to-Image models. However, to generate high-quality images, users must still craft detailed prompts specifying scene, style, and context-often through multiple rounds of refinement. We propose PromptSculptor, a novel multi-agent framework that automates this iterative prompt optimization process. Our system decomposes the task into four specialized agents that work collaboratively to transform a short, vague user prompt into a comprehensive, refined prompt. By leveraging Chain-of-Thought reasoning, our framework effectively infers hidden context and enriches scene and background details. To iteratively refine the prompt, a self-evaluation agent aligns the modified prompt with the original input, while a feedback-tuning agent incorporates user feedback for further refinement. Experimental results demonstrate that PromptSculptor significantly enhances output quality and reduces the number of iterations needed for user satisfaction. Moreover, its model-agnostic design allows seamless integration with various T2I models, paving the way for industrial applications.

📄 PDF Abstract BibTeX arXiv:2509.12446

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents

2025-10-05 · Yanjie Li, Yiming Cao, Dong Wang, Bin Xiao arxiv

Multimodal agents built on large vision-language models (LVLMs) are increasingly deployed in open-world settings but remain highly vulnerable to prompt injection, especially through visual inputs. We introduce AgentTypo,…

Continual Learning

Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts

2024-06-04 · Haodong Hong, Sen Wang, Zi Huang, Qi Wu 외

Current Vision-and-Language Navigation (VLN) tasks mainly employ textual instructions to guide agents. However, being inherently abstract, the same textual instruction can be associated with different visual signals, cau…

NavigateVision and Language Navigation

Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation

2024-01-28 · Zhenyu Wang, Enze Xie, Aoxue Li, Zhongdao Wang 외

Despite significant advancements in text-to-image models for generating high-quality images, these methods still struggle to ensure the controllability of text prompts over images in the context of complex text prompts, …

AttributeImage GenerationLanguage ModellingLarge Language Model+3

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents

2025-10-01 · Yinuo Liu, Ruohan Xu, Xilong Wang, Yuqi Jia 외 arxiv

Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for w…

T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation

2025-07-28 · Chieh-Yun Chen, Min Shi, Gong Zhang, Humphrey Shi arxiv

Text-to-Image (T2I) generative models have revolutionized content creation but remain highly sensitive to prompt phrasing, often requiring users to repeatedly refine prompts multiple times without clear feedback. While t…

Prompt Engineering