Seedance 2.5
Multimodal modelSeedance 2.5
Parameters
Not disclosed
Context length
No data
Chinese support
Supported
Reasoning ability
Seedance 2.5 是字节跳动 Seed 团队于 2026 年 6 月 23 日在火山引擎 FORCE 原动力大会正式发布的新一代视频生成模型，支持单段 30 秒原生视频直出、最多 50 个全模态参考素材联合生成，以及保持画面一致性的局部视频编辑；当前处于企业内测阶段，预计 2026 年 7 月初面向公众全面开放。
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Seedance 2.5
Model basics
Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
No data
Max output length
30秒 tokens
Model type
Multimodal model
Modality (in / out)
Text, Image, Audio, Video → Audio, Video
Release date
2026-06-23
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Seedance 2.5
Open source & experience
Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
Seedance 2.5
Official resources
Paper
No paper available
DataLearnerAI blog
No blog post yet
Seedance 2.5
API details
API speed
3/5
No public API pricing yet.
Seedance 2.5
Benchmark Results
No benchmark data to show.
Compare with other models
No curated comparisons for this model yet.
Want a custom combination? Open the compare tool
Seedance 2.5
Publisher
字节跳动Seed团队
View publisher details Seedance 2.5
Model Overview
Seedance 2.5 是字节跳动 Seed 团队于 2026 年 6 月 23 日在火山引擎 FORCE 原动力大会正式发布的新一代视频生成模型，支持单段 30 秒原生视频直出、最多 50 个全模态参考素材联合生成，以及保持画面一致性的局部视频编辑；当前处于企业内测阶段，预计 2026 年 7 月初面向公众全面开放。
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
