字节跳动发布Seedance 2.0视频生成模型，支持多模态输入与复杂场景生成

AI 摘要

字节跳动旗下Seed研究团队发布了新一代视频生成模型Seedance 2.0，采用统一的多模态音视频联合生成架构，支持文本、图像、音频和视频四种输入模态，并具备多模态参考和编辑能力。相比1.5版本，该模型在复杂交互和运动场景的生成可用性、物理准确性、视觉真实感和可控性方面有显著提升，支持15秒多镜头音视频输出和双声道音频。官方称其在多主体交互和复杂运动场景中达到行业领先的SOTA水平。

正文节选

We recently launched Seedance 2.0, our next-generation video creation model. Built with a unified multimodal audio-video joint generation architecture, Seedance 2.0 supports four input modalities: text, image, audio, and video. It integrates the industry's most comprehensive set of multimodal content references and editing capabilities available today. Compared with Version 1.5, Seedance 2.0 delivers a substantial leap in generation quality. It achieves a higher usability rate for complex intera

发布时间：—

抓取时间：2026-09-04 12:54

来源机构：ByteDance Seed