立即开始
HappyHorse video editing model supports style transformation and local replacement by combining input video with reference images (0-5) and text instructions. Input video duration: 3-60 seconds. Output video duration: 3-15 seconds (automatically truncates to first 15 seconds if input exceeds). Processing time: typically 1-5 minutes.
输入
Text instruction describing desired video editing operations, such as style transformation or local replacement. Supports any language input. Maximum length: 5000 non-Chinese characters or 2500 Chinese characters (automatically truncated if exceeded)
Audio control. auto: automatically controlled by the model; origin: preserve original audio from input video
auto
Input video URL (HTTP/HTTPS, must be publicly accessible). Video requirements: duration 3-60 seconds, format MP4/MOV (H.264 recommended), resolution: long side ≤2160px, short side ≥320px, aspect ratio: 1:2.5~2.5:1, file size ≤100MB, frame rate >8fps. Output video: 3-15 seconds (automatically truncates to first 15 seconds if input exceeds)
提示：可拖拽文件、从剪贴板粘贴（Ctrl/Cmd+V），或提供 URL。
Reference image URLs for style transfer or local replacement (optional, 0-5 images). Image requirements: format JPEG/JPG/PNG/WEBP, resolution: width and height ≥300px, aspect ratio: 1:2.5~2.5:1, file size ≤10MB
提示：可拖拽文件、从剪贴板粘贴（Ctrl/Cmd+V），或提供 URL。
Output video resolution tier
1080P
Random seed for reproducibility (0-2147483647). If not specified, system generates random seed. Fixed seed value can improve result reproducibility, but cannot guarantee completely identical results due to probabilistic nature of model generation
结果
暂无结果
运行模型后，结果将在这里显示。
