arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.01434cs.CV
收藏

StoryDiffusion:用于长程图像与视频生成的一致性自注意力

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

Nankai University(南开大学);ByteDance Inc.(字节跳动公司);Nankai International Advanced Research Institute (Shenzhen Futian)(南开大学国际高级研究院(深圳福田))

Yupeng Zhou, Daquan Zhou, Ming-Ming Cheng, Jiashi Feng, Qibin Hou

AI总结:

本文提出StoryDiffusion框架,通过一致性自注意力与语义运动预测器实现长程图像和视频生成中的内容一致性,并以零样本方式增强现有扩散模型。

摘要:

对于近期基于扩散的生成模型而言,在一系列生成图像中保持一致内容,尤其是包含主体和复杂细节的图像,是一项重大挑战。本文提出一种新的自注意力计算方式,称为一致性自注意力(Consistent Self-Attention),它显著提升生成图像之间的一致性,并以零样本方式增强现有预训练扩散文本到图像模型。为将方法扩展到长程视频生成,我们进一步引入一个新颖的语义空间时序运动预测模块,名为语义运动预测器(Semantic Motion Predictor)。该模块经过训练,可在语义空间中估计两幅给定图像之间的运动条件。该模块将生成的图像序列转换为具有平滑过渡和一致主体的视频,与仅基于潜在空间的模块相比,显著更加稳定,尤其是在长视频生成场景中。通过融合这两个新组件,我们的框架称为StoryDiffusion,能够以一致的图像或视频描述基于文本的故事,涵盖丰富多样的内容。所提出的StoryDiffusion包含视觉故事生成中图像与视频呈现方面的开创性探索,我们希望这能从架构修改的角度激发更多研究。代码已公开于 https://github.com/HVision-NKU/StoryDiffusion。

英文摘要:

For recent diffusion-based generative models, maintaining consistent content across a series of generated images, especially those containing subjects and complex details, presents a significant challenge. In this paper, we propose a new way of self-attention calculation, termed Consistent Self-Attention, that significantly boosts the consistency between the generated images and augments prevalent pretrained diffusion-based text-to-image models in a zero-shot manner. To extend our method to long-range video generation, we further introduce a novel semantic space temporal motion prediction module, named Semantic Motion Predictor. It is trained to estimate the motion conditions between two provided images in the semantic spaces. This module converts the generated sequence of images into videos with smooth transitions and consistent subjects that are significantly more stable than the modules based on latent spaces only, especially in the context of long video generation. By merging these two novel components, our framework, referred to as StoryDiffusion, can describe a text-based story with consistent images or videos encompassing a rich variety of contents. The proposed StoryDiffusion encompasses pioneering explorations in visual story generation with the presentation of images and videos, which we hope could inspire more research from the aspect of architectural modifications. Our code is made publicly available at https://github.com/HVision-NKU/StoryDiffusion.

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。

↑