通过几何方法解耦文本嵌入，实现单提示词生成连贯视觉故事
Geometric Disentanglement of Text Embeddings for Subject-Consistent Text-to-Image Generation using A Single Prompt
- 从几何角度优化文本嵌入，抑制无关语义干扰
- 在多个生成样本中显著提升主体一致性和文本对齐度
- 无需训练和微调，适合快速生成连贯图像序列
文本到图像的扩散模型在根据自然语言生成高质量图像方面表现优异，但往往无法在多张输出间保持主体一致性，限制了其在视觉叙事中的应用。现有方法依赖模型微调或图像条件控制，计算成本高且需针对每个主体单独优化。1Prompt1Story 是一种无训练方法，将所有场景描述拼接为单一提示词并重缩放标记嵌入，但存在语义泄漏问题，导致不同帧间的嵌入纠缠，引发文本错位。本文提出一种简单而有效的无训练方法，从几何视角出发，通过精炼文本嵌入来抑制非预期语义，解决语义纠缠问题。大量实验证明，该方法在主体一致性和文本对齐度上均显著优于现有基线。
原文摘要 · Abstract (English)
Text-to-image diffusion models excel at generating high-quality images from natural language descriptions but often fail to preserve subject consistency across multiple outputs, limiting their use in visual storytelling. Existing approaches rely on model fine-tuning or image conditioning, which are computationally expensive and require per-subject optimization. 1Prompt1Story, a training-free approach, concatenates all scene descriptions into a single prompt and rescales token embeddings, but it suffers from semantic leakage, where embeddings across frames become entangled, causing text misalignment. In this paper, we propose a simple yet effective training-free approach that addresses semantic entanglement from a geometric perspective by refining text embeddings to suppress unwanted semantics. Extensive experiments prove that our approach significantly improves both subject consistency and text alignment over existing baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。