参考生成视频
结合参考图、参考视频、音频和提示词方向，生成更可控的视频结果。
正在检查积分
AI 模型
Images
0/9参考视频
0/3 · detected 0.0s参考音频
0/3 · 0.0/15s提示词
0/5000
时长
s
4-15 seconds
画幅比例
分辨率
音频
205 积分720p · 5s · silent
AI 视频展示
查看电影感运动、角色一致性和多模态视频生成示例。
Multi Reference Guide
Seedance 2.0 supports text, image, video, and audio as input references. Combine multiple types of materials to guide AI video generation with greater precision and creative control.
Prompt Guide
Reference uploaded files in the prompt with names like @Image1, @Video1, or @Audio1.
This helps the model understand exactly which material should guide characters, motion, scenes, or sound.
Material Limits
- Up to 9 reference images
- Up to 3 reference videos, total duration <= 15 seconds
- Up to 3 reference audios, total duration <= 15 seconds
- Maximum 12 materials in total across all types
Supported Input Combinations
- Text + Image
- Text + Video
- Text + Image + Video
- Text + Image + Audio
- Text + Video + Audio
- Text + Image + Video + Audio
Note: Audio cannot be used alone with text. At least one image or video is required.