ByteDance releases Seedance 2.5: 30-second video in a single generation, multimodal references and precise editing
Original title:一镜成片,随心参考|Seedance 2.5 正式发布
AI summary
ByteDance today officially released its next-generation video creation model Seedance 2.5, increasing single-generation video duration from 15 seconds to 30 seconds and supporting multi-round extension to produce minutes of coherent content. The model supports up to 30 images, 10 videos, and 10 audio clips as reference material in a single input, and upgrades white-model reference, motion reference, green-screen editing, and timestamp-based precise editing. Seedance 2.5 has rolled out on platforms including Jimeng AI and Doubao Professional, with API service coming soon to Volcano Ark.
Key Takeaways
- ByteDance today officially released its next-generation video creation model Seedance 2.
- 5,increasing single-generation video duration from 15 seconds to 30 seconds and supporting…
- The model supports up to 30 images,10 videos,and 10 audio clips as reference material in a single…
- Seedance 2.
- 5 has rolled out on platforms including Jimeng AI and Doubao Professional,with API service coming…
Quick Facts
- Published
- Updated
- Category
- Model Releases
- AI score
- 80
Seedance 2.5 把单次生成拉到 30 秒,加上多模态参考和精准编辑,让视频创作从片段拼凑变成完整叙事。对国内创作者来说,这是即梦和豆包里能马上用到的最强视频模型。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: ByteDance releases Seedance 2.5: 30-second video in a single generation, multimodal references and precise editing. July 31, 2026. https://new.nat6.net/en/news/cms8f7n9q0bezrot06im88lqu/