用新采样策略让图文生成故事更连贯
Consistent Story Generation: Unlocking the Potential of Zigzag Sampling
- zigzag交替提示+视觉共享，不需训练
- 在多个图像中保持主体特征一致
- 适合需要连贯视觉叙事的场景
文本到图像生成模型在高质量图像生成方面取得显著进展，但在多图连贯性方面仍存在挑战，这直接影响视觉叙事效果。现有方法要么依赖大规模故事可视化数据集微调模型（资源消耗大），要么采用无需训练的技术共享生成信息，但效果有限。本文提出一种新型无训练采样策略——异步提示与视觉共享的锯齿采样（Zigzag Sampling with Asymmetric Prompts and Visual Sharing），通过交替使用非对称提示保留主体特征，并利用视觉共享模块在生成图像间传递视觉线索，进一步强化一致性。实验结果表明，该方法在定量指标和定性评估中均显著优于现有方法，有效提升视觉故事的连贯性与一致性。代码已开源：https://github.com/Mingxiao-Li/Asymmetry-Zigzag-StoryDiffusion。
原文摘要 · Abstract (English)
Text-to-image generation models have made significant progress in producing high-quality images from textual descriptions, yet they continue to struggle with maintaining subject consistency across multiple images, a fundamental requirement for visual storytelling. Existing methods attempt to address this by either fine-tuning models on large-scale story visualization datasets, which is resource-intensive, or by using training-free techniques that share information across generations, which still yield limited success. In this paper, we introduce a novel training-free sampling strategy called Zigzag Sampling with Asymmetric Prompts and Visual Sharing to enhance subject consistency in visual story generation. Our approach proposes a zigzag sampling mechanism that alternates between asymmetric prompting to retain subject characteristics, while a visual sharing module transfers visual cues across generated images to %further enforce consistency. Experimental results, based on both quantitative metrics and qualitative evaluations, demonstrate that our method significantly outperforms previous approaches in generating coherent and consistent visual stories. The code is available at https://github.com/Mingxiao-Li/Asymmetry-Zigzag-StoryDiffusion.
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。