Wan-AI/Wan2.7-R2V
Accurately preserve the look and voice of people or objects from a reference video, supporting multi-reference co-creation.
Try the model with a sample request using the same API shape shown in the reference page.
List of reference media. Must contain at least one reference_image or reference_video. The total of reference_image + reference_video must be <= 5. At most one first_frame is allowed.
Aspect ratio of the generated video. Default 16:9. Ignored if a first_frame is provided (the first frame's ratio is used).
Duration of the generated video in seconds. If media contains a reference_video: 2-10. Otherwise: 2-15. Default 5. (Default: empty, 2 ≤ duration ≤ 15)
Whether to add AI Generated watermark. Default is false
Whether to enable prompt rewriting for better quality. Default is true
Resolution tier of the generated video (720P or 1080P). Default 1080P
Negative prompt describing content to exclude. (Default: empty)
Text prompt describing the image
Random seed for reproducibility (Default: empty, 0 ≤ seed ≤ 2147483647)
Adjust settings and run the demo to see the model output generated here in real-time.
