通过正交化提示嵌入，解决文本生成连贯故事时的视觉混淆问题。
DeCorStory: Gram-Schmidt Prompt Embedding Decorrelation for Consistent Storytelling
- 用格拉姆-施密特方法正交化各帧提示嵌入，减少语义干扰。
- 在扩散过程中保持角色身份一致，提升图像多样性与提示对齐度。
- 无需训练或修改模型，可直接接入现有生成流程。
在文本到图像的故事生成中，保持跨帧的视觉与语义一致性是关键挑战。现有无训练方法如One-Prompt-One-Story将所有提示拼接为单一序列，常引发强烈嵌入相关性，导致颜色泄露、背景混合和身份漂移。本文提出DeCorStory，一种无训练的推理阶段框架，显式降低帧间语义干扰。该方法通过格拉姆-施密特提示嵌入正交化实现帧级语义解耦，结合奇异值重加权强化提示特异性信息，并采用保持身份的交叉注意力机制稳定角色特征。该方法无需模型修改或微调，可无缝集成至现有扩散流水线。实验表明，其在提示-图像对齐、身份一致性与视觉多样性方面均有显著提升，达到无训练基线中的最先进水平。代码已公开：https://github.com/YuZhenyuLindy/DeCorStory。
原文摘要 · Abstract (English)
Maintaining visual and semantic consistency across frames is a key challenge in text-to-image storytelling. Existing training-free methods, such as One-Prompt-One-Story, concatenate all prompts into a single sequence, which often induces strong embedding correlation and leads to color leakage, background blending, and identity drift. We propose DeCorStory, a training-free inference-time framework that explicitly reduces inter-frame semantic interference. DeCorStory applies Gram-Schmidt prompt embedding decorrelation to orthogonalize frame-level semantics, followed by singular value reweighting to strengthen prompt-specific information and identity-preserving cross-attention to stabilize character identity during diffusion. The method requires no model modification or fine-tuning and can be seamlessly integrated into existing diffusion pipelines. Experiments demonstrate consistent improvements in prompt-image alignment, identity consistency, and visual diversity, achieving state-of-the-art performance among training-free baselines. Code is available at: https://github.com/YuZhenyuLindy/DeCorStory
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。