Build a camera-dependent illusion from your image: colored spheres look scattered from the side, then align into a recognizable subject. The renderer calculates real perspective registration and exports the object coordinates. PopNow can supply the missing source artwork after a quote; the orbit itself is rendered locally.

Uses PopNow for
Images · 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 · 4.8 MB · Use it for personal and client work; please don't resell or share the package.

What you get

  1. An eight-second H.264 reveal and a six-frame contact sheet

  2. An editable point cloud with the source colors and world coordinates

  3. A registration-error measurement and source-artwork hash

Good for

  • Optical-illusion posts with a deliberate reveal
  • An original animal or bold product silhouette

Not for

  • A physically fabricated sculpture or a construction-ready plan
  • Images with tiny type or low-contrast detail

How to use it

You say

  • Use the PopNow skill "Anamorphic Object Reveal" (anamorphic-object-reveal) for this: Make an eight-second optical reveal from the fox artwork. Show that it is scattered objects from the side, then let the fox read clearly from the front.

Then try

  • Reduce the particles to 1600 and keep the registered viewpoint unchanged.

  • Use my supplied silhouette and a smaller orbit; keep the coordinates with the film.

What to have ready

  • One authorized image with a bright subject against a dark background
  • A particle count, depth range and camera swing
  • Python 3, Pillow, NumPy and FFmpeg

Similar skills

View all →

Ratings

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

Rate this skill

Questions

Does the camera really reveal a 3D arrangement?

Yes. Each color sample is placed at a different depth, with its position adjusted for a pinhole camera. The registered projection is checked numerically; side views use the rotated coordinates.

Can I build the sculpture from this file?

The coordinates describe a visual experiment, without structural supports, tolerances or manufacturing checks. Treat them as a digital scene, not fabrication instructions.

Do I need to generate a video?

No. The local renderer builds every animation frame. Use your own source image, or quote a PopNow image request for missing artwork.