Wan 2.7 Video Editing
[Core Function] Wan 2.7 Video Editing is an instruction-based video modification model. [Strengths] It supports complex video editing tasks like content replacement using reference images, and replicating actions, effects, and camera movements. [Best For] Highly recommended for: modifying existing video footage, style transfer on videos, and targeted element replacement. [Limitations] Do NOT use this model to generate a brand new video from scratch; it requires an input video. [Routing] Use this model by default whenever a user wants to edit, alter, or restyle an existing video.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Input video URL (HTTP/HTTPS/OSS) or Base64 encoded data (required)
"https://example.com/input.mp4"
Text prompt describing desired video modifications (supports Chinese and English, up to 5000 characters)
1 - 5000"Transform the entire scene into clay style"
Reference image URLs for style transfer (optional, max 4). Combined with video_url, the total media count must be ≤ 5
4Negative prompt describing unwanted content
500"blurry, distorted, low quality"
Video resolution tier
720P, 1080P "1080P"
Video aspect ratio (defaults to input video ratio if not specified)
16:9, 9:16, 1:1, 4:3, 3:4 "16:9"
Video duration in seconds (2-10 = truncate to specified length)
2, 3, 4, 5, 6, 7, 8, 9, 10 5
Audio handling mode (auto: intelligent decision based on prompt, origin: preserve original audio)
auto, origin "auto"
Enable intelligent prompt rewriting (improves quality for short prompts but increases processing time)
true
Random seed for reproducibility (note: results may vary even with same seed)
0 <= x <= 214748364742