立即开始
Wan 2.6 Reference-to-Video model generates videos from reference URLs (images/videos) with multi-character interaction and role-playing capabilities. Generates silent videos by default.
输入
Negative prompt describing unwanted content
Video content description (supports Chinese and English, up to 1500 characters). Can reference characters using 'Character1/Character2' format
Video duration in seconds
5
Reference URLs array (images + videos ≤ 5)
提示：可拖拽文件、从剪贴板粘贴（Ctrl/Cmd+V），或提供 URL。
Random seed for reproducibility
Shot type (single-shot or multi-shot narrative)
single
Video resolution (format: width*height)
1920*1080
结果
暂无结果
运行模型后，结果将在这里显示。
