Wan-AI/Wan2.6-I2V
Turn any image into a video. Intelligent shot scheduling supports multi-shot storytelling, generating multi-shot narrative videos with consistent subjects, scenes, and atmosphere
Try the model with a sample request using the same API shape shown in the reference page.
Duration of the generated video in seconds (2-15) (Default: empty, 2 ≤ duration ≤ 15)
First-frame image: either a URL or base64-encoded image data
Whether to add AI Generated watermark
URL of audio file for synchronized audio and video. (Default: empty)
Whether to enable prompt rewriting for better quality
Shot type: single continuous shot or multi switching shots
Resolution tier of the generated video (720P or 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.
