APE: Agentic Prompt Enhancer for Image Generation and Editing
This work addresses the prompt sensitivity problem in text-guided visual systems for practitioners who need efficient, deployable prompt enhancement without dependence on large proprietary models.
APE proposes a lightweight framework that post-trains small language models as prompt-enhancement agents for image generation and editing, achieving improved visual alignment and prompt following without relying on large proprietary LLMs. Experiments show that post-trained small prompt enhancers reliably outperform their base counterparts and narrow the gap to closed-source enhancers, with MAPE excelling on complex compositional tasks.
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.