Wan 2.2 Animate | AI Motion Control Video API

Wan2.2-Animate

What is Wan2.2-Animate?

Wan2.2-Animate is an Wan 2.2–based motion-transfer model that turns a single character image into a full performance. It copies body movement and facial expressions from a driving video while keeping the output stable, realistic, and identity-consistent.

Modes: animate vs replace

Wan2.2-Animate supports two behaviors:

animate The person or object in the input image is animated to follow the motion in the driving video. Use this when you want to bring a still portrait, illustration, or character design to life.
replace The model replaces the main performer in the video with the person or object from the image, keeping the original motion, scene, and camera. Use this when you want to swap a new character into an existing shot (presenter, actor, mascot, etc.).

Pricing

Pricing depends on output length and resolution.

Resolution	Price per 5 s	Max billed length
480p	0.20 USD	120 s
720p	0.40 USD	120 s

Billing rules

Underlying logic (no math required on your side):

Billed duration is clamped to the range 5–120 seconds
If the video is shorter than 5 s → billed as 5 s
If the video is longer than 120 s → billed as 120 s
480p
0.20 USD per 5 s → 0.04 USD per second
720p
Double 480p → 0.40 USD per 5 s → 0.08 USD per second

So, for example:

30 s at 480p → 30 × 0.04 = 1.20 USD
30 s at 720p → 30 × 0.08 = 2.40 USD
150 s at 720p (over the cap) → billed as 120 s → 120 × 0.08 = 9.60 USD

How to use Wan2.2-Animate

image (required) Upload a clear character image.

Prefer PNG or JPG
Avoid WEBP and heavily compressed images

video (required) Upload the driving video whose pose, movement, and expressions you want to copy.
mode (required)

animate: make the image character move like the subject in the video
replace: swap the image character into the video

prompt (optional) Short guidance such as:

“Preserve outfit, natural expression, no background change.”
“Smoother head motion, cinematic lighting.”

resolution Choose 480p for faster, cheaper previews or 720p for higher-quality output.
seed (optional)

Leave default for a fresh variation each run.
Set a fixed integer if you want to reproduce the same layout and motion.

Run generation, review the result, and adjust image, video, mode, prompt, and resolution as needed.

Practical tips

Match composition and pose Try to keep the image and video similar in camera angle, crop, and body pose. This reduces artifacts and identity drift, especially in replace mode.
Keep aspect ratio consistent Use the same or very similar aspect ratio for both the image and the video for more stable framing.
Use clean, well-lit faces Avoid heavy occlusion by hands, microphones, or props, and avoid strong motion blur in the driving video.
Prototype at 480p Start with 480p and short clips to find good settings, then switch to 720p and longer durations once you like the behavior.

This gives you a predictable-cost, two-mode pipeline for driving AI characters and doing high-quality character replacement in existing footage.

Wan 2.2 Animate API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/animate with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Wan 2.2 Animate below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/animate" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "image": "https://example.com/your-input.jpg",
    "video": "https://example.com/your-input.mp4",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "mode": "animate",
    "resolution": "480p",
    "seed": -1
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("wavespeed-ai/wan-2.2/animate", {
        "image": "https://example.com/your-input.jpg",
        "video": "https://example.com/your-input.mp4",
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "mode": "animate",
        "resolution": "480p",
        "seed": -1
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "wavespeed-ai/wan-2.2/animate",
    {
    "image": "https://example.com/your-input.jpg",
    "video": "https://example.com/your-input.mp4",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "mode": "animate",
    "resolution": "480p",
    "seed": -1
}
)

print(output["outputs"][0])  # → URL of the generated output

Wan 2.2 Animate API — Frequently asked questions

What is the Wan 2.2 Animate API?

Wan 2.2 Animate is a WaveSpeedAI model for pose / motion driven video, exposed as a REST API on WaveSpeedAI. Wan2.2-Animate unified character animation & replacement model replicating movement and expression; generates 720p videos up to 120s. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Wan 2.2 Animate API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.2-animate.

How much does Wan 2.2 Animate cost per run?

Wan 2.2 Animate starts at $0.20 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Wan 2.2 Animate accept?

Key inputs: `prompt`, `image`, `video`, `resolution`, `seed`, `mode`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.2-animate.

How long does Wan 2.2 Animate take to generate?

Average end-to-end generation time on WaveSpeedAI is around 223 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Wan 2.2 Animate outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ExamplesView all

Related Models

README