Extract complete poses from a plain-background clip and compose a timed photographic movement study. Color-distance mattes and connected components extract selected complete figures. The renderer repositions each pose in chronological order, building a photographic sequence rather than measuring a real path. PopNow can supply missing artwork, footage or sound after a quote; owned material and the local example work without a connection.

Uses PopNow for
Images · Video · Music & voice
Needs
Python 3 · FFmpeg

The skill is free. Optional AI images, video and sound are quoted for your approval before generation. API-key calls use your separate API balance in USD; generation through ChatGPT or Claude connected via OAuth/MCP uses your website credits.

v1.0.0 · Updated Oct 25, 2026 · 2.1 MB · Use it for personal and client work; please don't resell or share the package.

What you get

  1. An 8-second 1280 × 720 H.264 MP4 made by the local algorithm

  2. Color-distance mattes and connected components extract selected complete figures. The renderer repositions each pose in chronological order, building a photographic sequence rather than measuring a real path.

  3. Editable JSON, a six-frame contact sheet and a receipt with actual checks

Good for

  • Dance studies, gesture experiments and editorial multiple exposure
  • Original creative work using owned or licensed material

Not for

  • Motion capture, biomechanical measurements or guaranteed identity continuity
  • Publishing without watching the rendered result

How to use it

You say

  • Use the PopNow skill "Chronophoto Motion Study" (chronophoto-motion-study) for this: Extract complete poses from a plain-background clip and compose a timed photographic movement study. Use the bundled project, render the example and inspect the full result before delivery.

Then try

  • Use sampleTimes [0.08, 1.25, 2.5, 3.25] to produce four selected poses.

  • Use my licensed music; keep source audio discarded.

What to have ready

  • A 4.8-second clip on a uniform background; choose three to seven moments.
  • Python 3.10+, FFmpeg/ffprobe, Pillow and NumPy

Similar skills

View all →

Ratings

No ratings yet. Installed it? Be the first to rate it.

Rate this skill

Questions

Is this automatic AI segmentation?

No. The local matte uses background color distance and connected components. Plain backgrounds work best; overlapping people or matching colors can fail.

Are the shown positions real measurements?

No. Positions are editorial. The bundled generated clip contains repeated figures; the example selects complete components and does not claim a single measured trajectory.

Does the local render spend generation funds?

No. It reads local media and renders locally. Missing media can be made through PopNow after an exact quote and approval; no paid call occurs in the renderer.