Alibaba Wan - video extend (3.0)
Alibaba's Wan 3.0 continues a video forward or backward, up to 30 seconds in all, with the same characters, motion and sound.
Alibaba Wan 3.0 continues the video you give it: it takes the last moments of the clip and makes what happens next (forward), or takes the first moments and makes what led up to it (backward), keeping the characters, motion, camera and sound. The result is the clip you gave followed or preceded by the new seconds.
Inputs: prompt (required: what happens in the new part), video (required; MP4 or MOV, 1-15 s, up to 100 MB), direction (forward by default, or backward), duration (the length of the whole result, the clip plus the new seconds, up to 30; -1 lets the model choose: a 5-second clip extended by 3 seconds is 8), resolution (480P, 720P by default, 1080P), reference_images (up to 10), reference_audios (up to 5), ratio (adaptive: the result keeps the video's shape), audio, prompt_extend, watermark and seed. Write your own "Extend Video 1 ..." sentence in the prompt for both directions at once.
It does not edit what is already in the clip (use flymyai/wan-3_0-video-edit) and does not start from a prompt alone (use flymyai/wan-3_0-t2v). Alibaba refuses videos and instructions its content inspection flags.
Billed per second of video at the resolution's rate, for the clip you give plus the clip you get: $0.05 at 480P, $0.10 at 720P, $0.20 at 1080P. A 5-second clip extended to 8 seconds at 720P is 13 billed seconds, about $1.30; at 480P about $0.65. A refused or failed run costs nothing.
- Text to Video
Price: From $0.05 per second of video, depending on resolution; the clip you give counts as well as the clip you get (30 s in all).
Run Alibaba Wan - video extend (3.0) via API
curl -X POST https://api.flymy.ai/api/v1/flymyai/wan-3_0-video-extend/predict \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"The camera slowly pulls back to reveal the whole miniature city while the tiny figures keep walking","video":"https://storage.googleapis.com/open-inference-results/agent-files/1585/40ecb0fd73ed4b5eb3b34b53b3b7e290/bytedance-seedance-2_0-fast-text-to-video_a64b.mp4","direction":"forward","resolution":"480P"}'API documentation · Create a free account · Pricing