APE: Agentic Prompt Enhancer for Image Generation and Editing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Zijian, Wu, Jay Zhangjie, Wang, Zian, Cao, Tianshi, Chen, Jiasi, Fidler, Sanja, Ling, Huan, Ren, Xuanchi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913174786146304
author Huang, Zijian
Wu, Jay Zhangjie
Wang, Zian
Cao, Tianshi
Chen, Jiasi
Fidler, Sanja
Ling, Huan
Ren, Xuanchi
author_facet Huang, Zijian
Wu, Jay Zhangjie
Wang, Zian
Cao, Tianshi
Chen, Jiasi
Fidler, Sanja
Ling, Huan
Ren, Xuanchi
contents Natural language has become a powerful interface for image generation and editing, yet text-guided visual systems remain highly sensitive to prompt formulation. Semantically similar requests can produce different outputs depending on wording, specificity, and how explicitly visual constraints are stated, motivating prompt enhancement as a trainable component rather than a peripheral user choice. Existing strong enhancers often rely on large, proprietary LLMs such as ChatGPT or Gemini, adding cost, latency, and deployment dependence to the visual generation pipeline. We propose Agentic Prompt Enhancer (APE), a lightweight framework that post-trains small language models (SLMs) as prompt-enhancement agents. APE supports both single-agent rewriting and role-specialized multi-agent enhancement. Its single-agent instantiation, SAPE, rewrites the prompt in one pass, while its multi-agent instantiation, MAPE, decomposes enhancement into a router--rewriter--composer process for handling compositional constraints over objects, attributes, spatial relations, and edits. With task-aware rewards and post-training protocols, APE improves visual alignment and prompt following without modifying the downstream visual model. Experiments on challenging image generation and editing benchmarks demonstrate that post-trained small prompt enhancers reliably outperform their base counterparts, narrowing the gap to closed-source prompt enhancers; in addition, MAPE proves particularly strong on complex compositional tasks within these benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2606_00204
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle APE: Agentic Prompt Enhancer for Image Generation and Editing
Huang, Zijian
Wu, Jay Zhangjie
Wang, Zian
Cao, Tianshi
Chen, Jiasi
Fidler, Sanja
Ling, Huan
Ren, Xuanchi
Computer Vision and Pattern Recognition
Natural language has become a powerful interface for image generation and editing, yet text-guided visual systems remain highly sensitive to prompt formulation. Semantically similar requests can produce different outputs depending on wording, specificity, and how explicitly visual constraints are stated, motivating prompt enhancement as a trainable component rather than a peripheral user choice. Existing strong enhancers often rely on large, proprietary LLMs such as ChatGPT or Gemini, adding cost, latency, and deployment dependence to the visual generation pipeline. We propose Agentic Prompt Enhancer (APE), a lightweight framework that post-trains small language models (SLMs) as prompt-enhancement agents. APE supports both single-agent rewriting and role-specialized multi-agent enhancement. Its single-agent instantiation, SAPE, rewrites the prompt in one pass, while its multi-agent instantiation, MAPE, decomposes enhancement into a router--rewriter--composer process for handling compositional constraints over objects, attributes, spatial relations, and edits. With task-aware rewards and post-training protocols, APE improves visual alignment and prompt following without modifying the downstream visual model. Experiments on challenging image generation and editing benchmarks demonstrate that post-trained small prompt enhancers reliably outperform their base counterparts, narrowing the gap to closed-source prompt enhancers; in addition, MAPE proves particularly strong on complex compositional tasks within these benchmarks.
title APE: Agentic Prompt Enhancer for Image Generation and Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2606.00204