眼见为实：基于视觉锚点的提示重写对齐用于文本到图像生成
Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation
AI总结：
提出FaithRewriter框架，利用多模态大模型生成中间视觉线索，结合大语言模型生成视觉锚定的增强提示，再蒸馏至小模型，以缩小用户意图与生成图像之间的差距。
摘要：
尽管文本到图像（T2I）模型具有令人印象深刻的能力，但由于用户提示的简洁性和模糊性，意图-生成差距往往持续存在。现有方法主要优化提示的流畅性和可读性。然而，增强过程仍然缺乏视觉基础。因此，重写器可能过度推断缺失的细节，导致意图-生成差距。为了解决这一限制，我们提出了FaithRewriter，一种用于T2I生成的新型提示增强框架。具体来说，FaithRewriter首先利用多模态MLLM从原始提示生成图像作为中间视觉线索。然后将该线索与提示结合，输入大规模LLM，生成视觉锚定的增强，更好地反映预期内容在图像中应如何呈现。最后，将这些增强蒸馏到小规模LLM中以便高效部署，增强其生成有效T2I提示的能力。实验表明，与强基线相比，FaithRewriter生成的提示更忠实于用户意图且视觉上更合理，有助于缩小意图-生成差距。
英文摘要：
Despite the impressive capabilities of text-to-image (T2I) models, an intent-generation gap often persists due to the brevity and ambiguity of user prompts. Existing approaches primarily polish the prompt for fluency and readability. However, the enhancement process still lacks visual grounding. As a result, the rewriter may over-infer missing details, causing an intent-generation gap. To address this limitation, we propose FaithRewriter, a novel prompt-enhancement framework for T2I generation. Specifically, FaithRewriter first leverages a multimodal MLLM to generate an image from the original prompt as an intermediate visual cue. This cue is then combined with the prompt and fed into a large-scale LLM to produce visually grounded augmentations that better reflect how the intended content should appear in images. Finally, these augmentations are distilled into a small-scale LLM for efficient deployment, enhancing its ability to generate effective T2I prompts. Experiments show that FaithRewriter yields prompts that are more faithful to the user intent and more visually plausible than strong baselines, helping narrow the intent-generation gap.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
