立即开始
Wan 2.7 Video Editing model supports video style modification and video editing with multi-modal inputs (text/image/video). Processing time: 1-5 minutes.
输入
Negative prompt describing unwanted content
Text prompt describing desired video modifications (supports Chinese and English, up to 5000 characters)
Audio handling mode (auto: intelligent decision based on prompt, origin: preserve original audio)
auto
Video duration in seconds (2-10 = truncate to specified length)
5
Enable intelligent prompt rewriting (improves quality for short prompts but increases processing time)
Video aspect ratio (defaults to input video ratio if not specified)
ratio
Reference image URLs for style transfer (optional, max 4). Combined with video_url, the total media count must be ≤ 5
提示：可拖拽文件、从剪贴板粘贴（Ctrl/Cmd+V），或提供 URL。
Video resolution tier
1080P
Random seed for reproducibility (note: results may vary even with same seed)
Input video URL (HTTP/HTTPS/OSS) or Base64 encoded data (required)
提示：可拖拽文件、从剪贴板粘贴（Ctrl/Cmd+V），或提供 URL。
结果
暂无结果
运行模型后，结果将在这里显示。
