Nano Banana 2 & Pro Sale — 15% OFF | Apr 1–15 Only
/탐색/Best Video Models/wavespeed-ai/ai-parkour-video
image-to-video

image-to-video

AI Parkour Video

wavespeed-ai/ai-parkour-video

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.

Input

Drag & drop or click to upload

preview

Drag & drop or click to upload

Idle

이 요청에는 $0.5 실행당가 필요합니다.

$10으로 이 모델을 약 20회 실행할 수 있습니다.

추가 안내:

예시전체 보기

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, generate clips from 5 to 15 seconds. 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. Range: 5–15. 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 5–15 seconds.
  5. Submit — generate, preview, and download your parkour video.

Pricing

Image-to-Video (no reference video)

DurationCost
5s$1.05
10s$2.10
15s$3.15

Video-to-Video (with reference video)

$0.45 per 5 seconds of reference video, with a minimum of 5 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 (5–15 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.