字节跳动发布Seedance 2.5视频生成模型，支持30秒长叙事与多模态参考
原标题：One-take Creation, Flexible Referencing: Introducing Seedance 2.5
AI 摘要
字节跳动旗下Seed Research正式发布新一代视频生成模型Seedance 2.5，支持单次生成30秒高质量音视频片段，并可通过多轮扩展生成数分钟的长视频。该模型在多模态参考（最多30张图片、10个视频和10个音频片段）和编辑能力（如时间戳级控制、绿幕、镜头视角）上实现重大升级，旨在提升长叙事、创意控制和生产力。Seedance 2.5已在即梦AI、豆包Pro等平台上线，API即将通过BytePlus ModelArk提供。
正文节选
Today, we are officially launching Seedance 2.5, the new-generation video creation model. Since the release of Seedance 2.0, we have noticed a shift in what users expect from video creation models: from merely generating a clip to completing a creative work. Building on the unified multimodal audio-video joint-generation architecture of Seedance 2.0, Seedance 2.5 centers on foundational generation and reference-based generation, delivering major breakthroughs in long-form storytelling, multimoda