wan-2.7-i2v
Wan 2.7 Image-to-Video animates a still image (or continues an existing clip) into a 3-15 second video, with optional first-and-last-frame control and audio synchronisation. Output runs at 720p or 1080p.
Input
Describe the action and direction of the generated video. Optional but recommended — without it the model has to guess motion from the first frame alone.
Optional first frame to animate (jpg / png / bmp / webp, ≤ 20 MB). Mutually exclusive with `video` (clip continuation).
Optional last frame for first-and-last-frame video generation. The model interpolates between `image` and `last_frame` over the duration.
Optional source video to continue from (mp4 / mov, 2-10 s, ≤ 100 MB). Mutually exclusive with `image`.
Optional audio track (wav / mp3, 3-30 s, ≤ 15 MB). When provided, the video's voice / music is synchronised to the audio.
Describe content that should NOT appear in the video.
Output video resolution.
Output length in seconds. Pricing scales linearly with duration.
Automatically expand and optimise the prompt for better motion direction. Recommended on.
Optional random seed for reproducible generations.
Output
Run the model to see output here.
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/alibaba/wan-2.7-i2v \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'