ByteDance Seed· @ByteDanceSeed_ · X·· 2026-08-07精选AI 评分78
AI 导读
Dreamina Seedance 2.5 的 API 服务已在 BytePlus ModelArk 上线，同时可在 Dreamina、CapCut 等平台体验。该模型支持单次生成 30 秒高质量音视频片段，单次最多输入 30 张图片、10 段视频和 10 段音频作为参考素材，并提供时间戳级别的音视频定向编辑控制。
推荐理由
Seedance 2.5 的 API 上线 BytePlus ModelArk，读者可据此了解单次生成 30 秒音视频与多模态参考的能力边界。
正文
The API service of Dreamina Seedance 2.5 is now available on BytePlus ModelArk. You can also try it on Dreamina、CapCut and other platforms . We invite you to give it a try and share your feedback.
Introducing Seedance 2.5, our new-generation video creation model! With advancements in long-form storytelling, multimodal reference, and editing, Seedance 2.5 goes beyond longer single-pass video generation, delivering the journey from idea to finished video with greater control. Key highlights include: 1. Users can generate high-quality, 30-second audio-video clips in a single pass, bringing a complete story to life in one take. 2. Users can input up to 30 images, 10 video clips, and 10 audio clips as reference materials in a single pass. 3. Seedance 2.5 offers timestamp-level control for targeted editing of audio and video content, notably improving efficiency and controllability. Visit project homepage learn more： https://seed.bytedance.com/seedance2_5在 X 查看被引用的帖子
来源：ByteDance Seed · x.com