返回全部动态
字节跳动发布Seedance 2.5：可生成带音频的30秒视频片段
原标题：ByteDance's Seedance 2.5 generates 30-second video clips with built-in audio
AI 摘要
字节跳动发布了其AI视频模型的新版本Seedance 2.5，该模型可一次性生成视频和音频，支持生成最长30秒的片段，并可多次扩展。用户可上传多达30张图片、10个视频片段和10个音频文件作为参考，以创建包含多个角色和摄像机角度的场景。该模型已上线即梦AI和豆包Pro，API访问将通过BytePlus ModelArk稍后提供。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
ByteDance's Seedance 2.5 generates 30-second video clips with built-in audio ByteDance shipped Seedance 2.5, a new version of its AI video model. It generates video and audio in one pass, producing clips up to 30 seconds long that can be extended multiple times. Google's Gemini Omni Flash tops out at about 10 seconds. Users can upload up to 30 images, 10 video clips, and 10 audio files as reference to create scenes with multiple characters and camera angles. Textures, lighting, and skin detail h
发布时间：2026-08-01 21:33
抓取时间：2026-08-02 00:28
来源机构：THE DECODER