PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909801498279936 |
|---|---|
| author | Wang, Linqing Xing, Ximing Cheng, Yiji Zhao, Zhiyuan Li, Donghao Hang, Tiankai Tao, Jiale Wang, Qixun Li, Ruihuang Chen, Comi Li, Xin Wu, Mingrui Deng, Xinchi Gu, Shuyang Wang, Chunyu Lu, Qinglin |
| author_facet | Wang, Linqing Xing, Ximing Cheng, Yiji Zhao, Zhiyuan Li, Donghao Hang, Tiankai Tao, Jiale Wang, Qixun Li, Ruihuang Chen, Comi Li, Xin Wu, Mingrui Deng, Xinchi Gu, Shuyang Wang, Chunyu Lu, Qinglin |
| contents | Recent advancements in text-to-image (T2I) diffusion models have demonstrated remarkable capabilities in generating high-fidelity images. However, these models often struggle to faithfully render complex user prompts, particularly in aspects like attribute binding, negation, and compositional relationships. This leads to a significant mismatch between user intent and the generated output. To address this challenge, we introduce PromptEnhancer, a novel and universal prompt rewriting framework that enhances any pretrained T2I model without requiring modifications to its weights. Unlike prior methods that rely on model-specific fine-tuning or implicit reward signals like image-reward scores, our framework decouples the rewriter from the generator. We achieve this by training a Chain-of-Thought (CoT) rewriter through reinforcement learning, guided by a dedicated reward model we term the AlignEvaluator. The AlignEvaluator is trained to provide explicit and fine-grained feedback based on a systematic taxonomy of 24 key points, which are derived from a comprehensive analysis of common T2I failure modes. By optimizing the CoT rewriter to maximize the reward from our AlignEvaluator, our framework learns to generate prompts that are more precisely interpreted by T2I models. Extensive experiments on the HunyuanImage 2.1 model demonstrate that PromptEnhancer significantly improves image-text alignment across a wide range of semantic and compositional challenges. Furthermore, we introduce a new, high-quality human preference benchmark to facilitate future research in this direction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04545 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting Wang, Linqing Xing, Ximing Cheng, Yiji Zhao, Zhiyuan Li, Donghao Hang, Tiankai Tao, Jiale Wang, Qixun Li, Ruihuang Chen, Comi Li, Xin Wu, Mingrui Deng, Xinchi Gu, Shuyang Wang, Chunyu Lu, Qinglin Computer Vision and Pattern Recognition Recent advancements in text-to-image (T2I) diffusion models have demonstrated remarkable capabilities in generating high-fidelity images. However, these models often struggle to faithfully render complex user prompts, particularly in aspects like attribute binding, negation, and compositional relationships. This leads to a significant mismatch between user intent and the generated output. To address this challenge, we introduce PromptEnhancer, a novel and universal prompt rewriting framework that enhances any pretrained T2I model without requiring modifications to its weights. Unlike prior methods that rely on model-specific fine-tuning or implicit reward signals like image-reward scores, our framework decouples the rewriter from the generator. We achieve this by training a Chain-of-Thought (CoT) rewriter through reinforcement learning, guided by a dedicated reward model we term the AlignEvaluator. The AlignEvaluator is trained to provide explicit and fine-grained feedback based on a systematic taxonomy of 24 key points, which are derived from a comprehensive analysis of common T2I failure modes. By optimizing the CoT rewriter to maximize the reward from our AlignEvaluator, our framework learns to generate prompts that are more precisely interpreted by T2I models. Extensive experiments on the HunyuanImage 2.1 model demonstrate that PromptEnhancer significantly improves image-text alignment across a wide range of semantic and compositional challenges. Furthermore, we introduce a new, high-quality human preference benchmark to facilitate future research in this direction. |
| title | PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.04545 |