WAN 3.0 is LIVE — 30s in one shot | Try in Video Generator →

wavespeed-ai/

AI Parkour Video generates dynamic parkour action videos from a portrait image. Choose from 6 parkour styles or provide a reference video. Ready-to-use REST inference API, no coldstarts, affordable pricing.

image-to-video
Input

Idle

$0.75per run·~13 / $10

Next:

ExamplesView all

Related Models

README

AI Parkour Video

AI Parkour Video turns any portrait into an action-packed parkour video. Upload your photo, pick a style, and watch yourself vault, flip, and sprint across rooftops, cities, and forests — no stunt training required.

Why Choose This?

  • Two generation modes Generate from a single image, or use a reference parkour video for video-to-video animation at 720p.

  • 6 parkour style presets From rooftop gap jumps to forest trail runs — choose the environment and movement style that fits your vision.

  • Flexible duration In image-to-video mode, choose from 5, 10, or 15 second clips. In video-to-video mode, duration follows the reference video (up to 120 seconds).

Parameters

ParameterRequiredDescription
imageYesPortrait image (URL or file upload).
videoNoReference parkour video for video-to-video animation. Duration follows the reference video (up to 120s).
styleNoParkour style preset. Default: rooftop. See options below.
durationNoOutput length in seconds when no reference video is provided. Options: 5, 10, or 15. Default: 5.

Two Modes

Image-to-video (no video provided): image + style + duration → generates a new parkour clip at 720p.

Video-to-video (video provided): image + video + style → animates the portrait onto the reference parkour footage at 720p. Duration follows the reference video.

Style Options

StyleDescription
rooftopRooftop running, gap jumps, wall vaults, rolls. (default)
urbanStreet railings, ledges, kong vaults, barrier slides.
wall_runVertical wall runs, wall climbs, fence vaults.
flipFront flips, cartwheels, acrobatic celebration moves.
forestTrail running, log jumps, branch swings, stream crossings.
stairsStaircase sprints, handrail vaults, bench jumps.

How to Use

  1. Upload your portrait — a clear, front-facing photo works best.
  2. Upload a reference video (optional) — provide a parkour video to use video-to-video mode.
  3. Pick a style — choose from 6 presets, or leave as default (rooftop).
  4. Set duration (optional) — only applies when no reference video is provided. Choose 5, 10, or 15 seconds.
  5. Submit — generate, preview, and download your parkour video.

Pricing

Billing duration: Input media duration is rounded up to whole seconds. The minimum billed duration is 3 seconds; shorter inputs are billed as 3 seconds. Existing per-5-second rate tables remain unchanged.

Image-to-Video (no reference video)

DurationCost
5s$0.75
10s$1.50
15s$2.25

Video-to-Video (with reference video)

$0.45 per 5 seconds of reference video, with a minimum of 3 seconds and a maximum billable duration of 120 seconds.

Best Use Cases

  • Social media content — Create eye-catching parkour videos of yourself for Instagram Reels and TikTok.
  • Entertainment & fun — Put yourself or friends into wild action sequences without leaving home.
  • Creative projects — Use custom reference videos to place any portrait into specific parkour footage.
  • Gaming & avatar content — Generate action clips for gaming personas or digital characters.

Pro Tips

  • A clear, front-facing portrait with a visible full body produces the most convincing parkour animation.
  • In video-to-video mode, use high-quality parkour reference footage with clear, dynamic movement for best results.
  • Try different style presets on the same portrait photo to find the most visually striking result.

Notes

  • image is always required; all other parameters are optional.
  • When a reference video is provided, duration is determined by the reference video length (up to 120 seconds).
  • When no reference video is provided, duration controls the output length (5, 10, or 15 seconds).
  • Ensure image and video URLs are publicly accessible if using links rather than direct uploads.
  • Please ensure your content complies with WaveSpeed AI's usage policies.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Ai Parkour Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ai-parkour-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Ai Parkour Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "style": "rooftop",
    "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ai-parkour-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/ai-parkour-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "style": "rooftop",
        "duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "style": "rooftop",
    "duration": 5
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/ai-parkour-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Ai Parkour Video API — Frequently asked questions

What is the Ai Parkour Video API?

Ai Parkour Video is a WaveSpeedAI model for video generation from images, exposed as a REST API on WaveSpeedAI. AI Parkour Video generates dynamic parkour action videos from a portrait image. Choose from 6 parkour styles or provide a reference video. Ready-to-use REST inference API, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Ai Parkour Video 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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/ai-parkour-video.

How much does Ai Parkour Video cost per run?

Ai Parkour Video starts at $0.75 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 Ai Parkour Video accept?

Key inputs: `image`, `video`, `duration`, `style`. 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/ai-parkour-video.

How long does Ai Parkour Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 252 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Ai Parkour Video 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.