立即开始
Wan 2.7 Reference-to-Video model generates videos from reference media (images and videos) with prompts. Requires at least one media parameter (reference_images, reference_videos, or first_frame_image). Supports multi-subject references, storyboard generation, and custom audio for voice cloning.
输入
Negative prompt describing unwanted content
Video content description (supports Chinese and English, up to 5000 characters). Can reference media using 'Image1/Image2' or 'Video1/Video2' format
Reference video URLs. At least one media parameter (reference_images, reference_videos, or first_frame_image) must be provided. Combined with reference_images, max 5 total
Video duration in seconds. Dynamic range: [2,10] when reference_videos is present, [2,15] when only reference_images
5
First frame image URL. At least one media parameter (reference_images, reference_videos, or first_frame_image) must be provided. Max 1, not counted in the 5-item limit
提示：可拖拽文件、从剪贴板粘贴（Ctrl/Cmd+V），或提供 URL。
Enable intelligent prompt rewriting
Video aspect ratio (auto-ignored when first_frame_image is present)
16:9
Reference image URLs. At least one media parameter (reference_images, reference_videos, or first_frame_image) must be provided. Combined with reference_videos, max 5 total
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
结果
暂无结果
运行模型后，结果将在这里显示。
