立即开始
Wan 2.7 text-to-video model generates high-quality videos from text prompts using the new protocol (resolution+ratio instead of size). Supports multi-shot narrative, automatic dubbing, custom audio, 720P/1080P resolutions, and 2–15 second durations.
输入
Negative prompt describing unwanted content
Text prompt describing the desired video content. Supports Chinese and English
Custom audio URL (supports wav/mp3, 2–30 seconds, ≤15MB)
提示：可拖拽文件、从剪贴板粘贴（Ctrl/Cmd+V），或提供 URL。
Video duration in seconds (integer)
5
Enable prompt intelligent rewriting to enhance generation quality
Specifies the aspect ratio for the generated video
16:9
Specifies the resolution tier for the generated video
1080P
Random number seed for reproducibility. Note: identical seeds cannot guarantee completely identical results due to model probabilistic nature
结果
暂无结果
运行模型后，结果将在这里显示。
