Use an owned motion clip as a time field. Each vertical or horizontal strip samples a different decoded source frame, gradually stretching the movement and resolving it back to the clean source. You control the delay, direction and axis, and receive a time map. PopNow can make a missing source clip after a quote.

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 · 4.2 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 time-ribbon film and contact sheet

  2. Editable delay, sampling axis and direction

  3. A per-frame CSV of the sampled source-time range

Good for

  • Fabric, light trails and clean object motion
  • Experimental visual transitions with an inspectable source-time map

Not for

  • Optical-flow interpolation or recovery of hidden detail
  • A guaranteed seamless loop from a non-looping source

How to use it

You say

  • Use the PopNow skill "Slit-Scan Time Ribbon" (slit-scan-time-ribbon) for this: Stretch the moving silk ribbon into a time ribbon, keep the opening clean, and resolve back to the source at the end. Use a 1.6-second horizontal delay.

Then try

  • Switch the sampling axis and reverse the delay direction.

  • Set the delay to zero to export a clean source-time comparison.

What to have ready

  • An authorized two-to-twenty-second motion clip
  • A clear subject with visible movement against a quiet background
  • 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 it invent intermediate frames?

It does not generate AI motion. The default gently blends neighboring decoded frames at the requested source time; set blendFrames to false for hard slices. The time map reports the sampled range.

Why does my result barely move?

The effect needs visible source movement. A static photo or a nearly stationary clip cannot become a meaningful time ribbon through this algorithm.

Can I generate the source in PopNow?

Yes. Inspect a current image-to-video model, quote a short clip with one clear movement, approve it, then put the returned video in the input slot. The local transform adds no paid calls.