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.
Idle
$0.75per run·~13 / $10
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.
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).
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Portrait image (URL or file upload). |
| video | No | Reference parkour video for video-to-video animation. Duration follows the reference video (up to 120s). |
| style | No | Parkour style preset. Default: rooftop. See options below. |
| duration | No | Output length in seconds when no reference video is provided. Options: 5, 10, or 15. Default: 5. |
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 | Description |
|---|---|
| rooftop | Rooftop running, gap jumps, wall vaults, rolls. (default) |
| urban | Street railings, ledges, kong vaults, barrier slides. |
| wall_run | Vertical wall runs, wall climbs, fence vaults. |
| flip | Front flips, cartwheels, acrobatic celebration moves. |
| forest | Trail running, log jumps, branch swings, stream crossings. |
| stairs | Staircase sprints, handrail vaults, bench jumps. |
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.
| Duration | Cost |
|---|---|
| 5s | $0.75 |
| 10s | $1.50 |
| 15s | $2.25 |
$0.45 per 5 seconds of reference video, with a minimum of 3 seconds and a maximum billable duration of 120 seconds.
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/ai-parkour-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Ai Parkour Video below.
set -euo pipefail
: "${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
doneconst 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));
}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 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.
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.
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.
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.
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.
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.