A paper portrait opens into a surreal composition of three visual thoughts. The local edit follows the real opening with separate close-ups of the rocket, flower and moon, then returns to the full collage. PopNow can create a new reference and motion clip after a quote; thought labels remain editable.

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 24, 2026 · 546 KB · Use it for personal and client work; please don't resell or share the package.

What you get

  1. A 5-second example MP4 from five seconds of source, plus editable project settings

  2. A hinge opening, three timed detail shots and a full-collage return with exact thought labels

  3. A contact sheet and render receipt with actual duration and source hash

Good for

  • Travel daydreams and personal introductions
  • Personal creative posts using original or owned material

Not for

  • A playable game or a physically accurate animation simulator
  • Automatically generating motion without footage or a generation connection

How to use it

You say

  • Use the PopNow skill "Surreal Mind Collage" (surreal-mind-collage) for this: A hinged paper portrait opens onto three surreal thoughts, followed by playful detail shots. Use the provided example settings and quote any missing media before generating.

Then try

  • Move the main action cue to match the actual footage, then render again.

  • Use my own music and keep the graphic labels editable.

What to have ready

  • A user-owned portrait plus three chosen objects.
  • Three thought labels and matching objects
  • A local motion clip, or a connected PopNow account for quoted generation
  • Python 3, FFmpeg and Pillow

Similar skills

View all →

Ratings

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

Rate this skill

Questions

Can I choose what comes out of the portrait?

Yes. Supply exactly three thought labels and describe one visual object for each. Regenerate only the source clip if the objects need to change; timing and labels stay editable locally.

Can I use my own footage?

Yes. Point the project input at a local clip or pass --input. The renderer checks the chosen range and never uploads local material.

What has the renderer actually checked?

It verifies input values, source duration, frame rendering and output duration. You still need to watch for believable action, stable subjects and good sound timing.