← 研踪 PaperTrailCVF · CVPR 2026:cvf:2b7d2d0075f0e3e5434522e770f5184d · 记录 #1
PromptEnhancer: Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward
Wang, LinqingXu, ZhiyongXing, XimingCheng, YijiZhao, ZhiyuanLi, DonghaoHang, TiankaiLi, ZhenxiTao, JialeWang, QixunLi, RuihuangChen, ComiLi, XinWu, MingruiDeng, XinchiGu, ShuyangWang, ChunyuLu, Qinglin 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-05 03:49
摘要
Recent text-to-image (T2I) diffusion models have achieved impressive progress in generating high-fidelity images, yet they often fail to faithfully follow complex user prompts, especially in attribute binding, negation, and compositional reasoning. To address this limitation, we propose PromptEnhancer, a universal prompt rewriting framework that improves prompt interpretability for any pre-trained T2I model. PromptEnhancer is trained through a multi-stage pipeline. We first perform supervised fine-tuning on chain-of-thought-style rewriting data to endow the rewriter with structured prompt analysis and rewriting capabilities. We then introduce AlignEvaluator, a task-specific reward model that provides explicit and fine-grained feedback based on a taxonomy of common T2I failure modes, and further optimize the rewriter with reinforcement learning. This design enables the rewriter to produce prompts that are more precise, semantically complete, and easier for T2I models to follow. To support evaluation, we also construct a comprehensive human-aligned benchmark covering diverse semantic and compositional challenges. Extensive experiments show that PromptEnhancer consistently improves image-text alignment across multiple T2I models and significantly enhances prompt fidelity on challenging cases.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
PromptEnhancer: Taming Your Rewriter for Text-to-Image Generation via Fine-Grained Reward
Recent text-to-image (T2I) diffusion models have achieved impressive progress in generating high-fidelity images, yet they often fail to faithfully follow complex user prompts, especially in attribute binding, negation, and compositional reasoning. To address this limitation, we propose PromptEnhancer, a universal prompt rewriting framework that improves prompt interpretability for any pre-trained T2I model. PromptEnhancer is trained through a multi-stage pipeline. We first perform supervised fine-tuning on chain-of-thought-style rewriting data to endow the rewriter with structured prompt analysis and rewriting capabilities. We then introduce AlignEvaluator, a task-specific reward model that provides explicit and fine-grained feedback based on a taxonomy of common T2I failure modes, and further optimize the rewriter with reinforcement learning. This design enables the rewriter to produce prompts that are more precise, semantically complete, and easier for T2I models to follow. To support evaluation, we also construct a comprehensive human-aligned benchmark covering diverse semantic and compositional challenges. Extensive experiments show that PromptEnhancer consistently improves image-text alignment across multiple T2I models and significantly enhances prompt fidelity on challenging cases.
查看此版本解读 →查看此版本原文 ↗