Flying | Trending Video Effects API

Flying Effect

Requirements

Number of Images

Mandatory
Only supports uploading one image

Number of People

Supports realistic-style single-person photos

Image Requirements

When the photo is a full-body shot of a single person with a scenic background, the effect is better

Prompt

Mandatory
The format should remain largely unchanged, for details please refer to the "prompt" parameter in the request example
If there are personalized requirements, the prompt words can be modified without altering the structure and majority of the content

Effect Boundaries

Possible issues include:
The person not flying forward
The subject becoming distorted when the head rotates 180 degrees

Best Practices

Use clear, full-body photos
Include scenic backgrounds for better effect
Ensure the subject is well-lit
Keep the default prompt structure
Use photos with good contrast
Avoid complex poses that might affect flying animation

Flying API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/video-effects/flying 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 Flying below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/video-effects/flying" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "image": "https://example.com/your-input.jpg"
}'

# 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("video-effects/flying", {
        "image": "https://example.com/your-input.jpg"
});

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

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "video-effects/flying",
    {
    "image": "https://example.com/your-input.jpg"
}
)

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

Flying API — Frequently asked questions

What is the Flying API?

Flying is a Video Effects model for AI inference, exposed as a REST API on WaveSpeedAI. Transform photos into superhero-style flying videos with dynamic camera movement using an Image-to-Video video-effects model. 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 Flying 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/video-effects/video-effects-flying.

How much does Flying cost per run?

Flying 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 Flying accept?

Key inputs: `image`. 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/video-effects/video-effects-flying.

How long does Flying take to generate?

Average end-to-end generation time on WaveSpeedAI is around 266 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Flying outputs commercially?

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

ExamplesView all

Related Models

README