cs.AI updates on arXiv.org 8小时前
StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出一种无监督文本生成视觉故事图像的新方法,通过引入掩码跨图像注意力共享和区域特征调和,实现预训练扩散模型的动态对齐和细节优化,有效生成一致主体特征。

arXiv:2508.03735v1 Announce Type: cross Abstract: Generating a coherent sequence of images that tells a visual story, using text-to-image diffusion models, often faces the critical challenge of maintaining subject consistency across all story scenes. Existing approaches, which typically rely on fine-tuning or retraining models, are computationally expensive, time-consuming, and often interfere with the model's pre-existing capabilities. In this paper, we follow a training-free approach and propose an efficient consistent-subject-generation method. This approach works seamlessly with pre-trained diffusion models by introducing masked cross-image attention sharing to dynamically align subject features across a batch of images, and Regional Feature Harmonization to refine visually similar details for improved subject consistency. Experimental results demonstrate that our approach successfully generates visually consistent subjects across a variety of scenarios while maintaining the creative abilities of the diffusion model.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

文本生成 视觉故事 扩散模型 无监督学习 图像生成
相关文章