WaveSpeedVideo to videoComing soon

wavespeed-ai/wan-2.2/animate-2

Name: wavespeed-ai/wan-2.2/animate-2
Brand: WaveSpeed

wavespeed-ai/wan-2.2/animate-2 is a video to video tool from WaveSpeed that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`image` required	URL or file	—	The reference image of the character to animate. The output character keeps this identity; the background is generated from the prompt.
`video` required	URL or file	—	The driving video whose body motion, hand gestures and facial expressions are transferred to the character. Up to 120 seconds.
`seed`	number (whole)	—	The random seed to use for the generation. -1 means a random seed will be used.
`prompt`	text	—	Describes the character's appearance and the output background, e.g. "Character appearance description: ...\nBackground description: ...". Looks only - put motion wording in motion_prompt.
`resolution`	one of 480p, 720p	480p	The resolution of the output video.
`motion_prompt`	text	—	Describes the motion in the driving video, e.g. "A person doing energetic street dance".

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "wavespeed",
    "model": "wavespeed-ai/wan-2.2/animate-2",
    "input": {
      "image": "<image>",
      "video": "<video>"
    }
  }'