popnow
PricingSign inStart creating
Red and cyan camera views combined into an anaglyph of floating faceted geometric forms

A seeded scene places faceted solids at explicit three-dimensional coordinates. Converged left and right perspective cameras render the same surfaces; the final image takes red from the left view and green/blue from the right, with both original views retained. Scene construction and both camera renders are local, with no generation calls. More objects and larger canvases increase local drawing work; suitable viewing glasses are separate from the digital output.

Needs
Python 3

v1.0.0 · Updated Oct 25, 2026 · 401 KB · Use it for personal and client work; please don't resell or share the package.

What you get

  1. Red-cyan anaglyph PNG and raster-wrapped SVG

  2. Separate left/right PNG and editable vector views

  3. Scene ledger, local view switcher and portable brief

Good for

  • Geometric stereoscopic art and depth studies
  • Comparing a stereo pair with its combined view

Not for

  • Estimating real depth from a photograph
  • Glasses-free depth or guaranteed perception on every display

How it works

Includes a local renderer

  1. Choose the input

    Set a geometric scene seed, depth spread and eye separation.

  2. Render and inspect

    Render both perspective views and combine their color channels.

  3. Adjust and export

    Switch between the component views and inspect the anaglyph with suitable glasses.

How the workflow runs

How Stereo anaglyph shadowbox works

A seeded scene places faceted solids at explicit three-dimensional coordinates. Converged left and right perspective cameras render the same surfaces; the final image takes red from the left view and green/blue from the right, with both original views retained.

What's inside the skill

What you can change

  • eye_separation: 0.02–0.22 scene units
  • layer_depth: 0.3–1.8
  • object_count: 8–30 and focal_length: 2.5–6
  • Scene seed and output dimensions

What to review before delivery

  • Left and right rendered views differ in actual pixels.
  • The scene ledger contains the requested object count.
  • The saved brief reproduces the PNG and SVG; unsafe replacement is rejected.

See the package files

These are selected working files from this edition, with their actual role. The complete download also contains instructions and applicable license notices.

  • The domain algorithm and invariant checks.

    scripts/recipe.py

  • Runnable, editable example parameters.

    examples/brief.json

  • Control meanings, proof interpretation and limits.

    references/design-notes.md

Why use this skill

Start with this package

The workflow supplies an explicit scene, camera pair and inspectable component exports. It avoids faking binocular depth with a single flat-image offset or an unexplained color filter.

Compare the options

A prompt, your own skill, or this workflow?

Start with a prompt

Your agent can create from a plain request. The brief, visual rules, asset choices, output format and review process still need to be established for that project.

Write your own skill

You choose and maintain the reusable instructions, defaults, file structure and checks. This is useful when your process needs different rules or integrations.

A workflow created for PopNow

This workflow was built for PopNow. Its source files, included dependencies and applicable notices are part of the package; the scope described below belongs to this edition.

Guide reviewed Oct 25, 2026

What will this cost?

Scene construction and both camera renders are local, with no generation calls. More objects and larger canvases increase local drawing work; suitable viewing glasses are separate from the digital output.

The supplied route runs locally. A new-media request is a separate choice. Free skill. New media is quoted before it runs.

The skill package

Free to install under your account's download allowance. The package license covers your own and client work; redistribution is excluded.

Existing assets and local work

Reusing suitable assets, editing files and running local assembly do not call a PopNow generation model. Your computer and any required runtime still do the work.

Your agent and hosting

Any subscription, hosted computer, deployment or other provider fee belongs to that service. Installing this skill does not include those services.

How PopNow billing works

Connections using a PopNow API key, including API-key MCP connections, spend from the separate API balance in USD. A ChatGPT or Claude connection authorized through OAuth spends website credits. These balances are separate; the quote shown by your connection is the approval basis.

Download allowances and current account conditions apply. A free package does not mean unlimited free generation.

See model ratesAPI USD balanceWebsite credit packs

How to use it

You say

  • Use the PopNow skill "Stereo anaglyph shadowbox" (stereo-anaglyph-shadowbox) for this: Set a geometric scene seed, depth spread and eye separation. Use the packaged example as a starting point and return the actual artwork with its editable inputs.

Then try

  • Rebuild a visibly different version using eye_separation: 0.10 → 0.18; layer_depth: 1.2 → 1.6.

  • Explain the result using its actual proof files and algorithm ledger.

What to have ready

  • Desired object count and depth spread
  • Red-left/cyan-right glasses to inspect stereo depth
  • Python 3.10+, Pillow and NumPy

Similar skills

View all →

Ratings

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

Rate this skill

Questions

Do I need glasses to see depth?

Use red-left/cyan-right glasses for the intended binocular effect. Without them, the normal display shows the two color channels overlaid; perception also depends on the screen and viewer.

Where does the depth come from?

It comes from declared object coordinates and two camera positions. The package does not infer depth from a flat source image or claim the scene was photographed.

What costs depend on this workflow?

Scene construction and both camera renders are local, with no generation calls. More objects and larger canvases increase local drawing work; suitable viewing glasses are separate from the digital output.

What is already packaged in Stereo anaglyph shadowbox?

The domain algorithm and invariant checks. Runnable, editable example parameters. Control meanings, proof interpretation and limits.

Which parts of Stereo anaglyph shadowbox can add a charge?

Scene construction and both camera renders are local, with no generation calls. More objects and larger canvases increase local drawing work; suitable viewing glasses are separate from the digital output. Connections using a PopNow API key, including API-key MCP connections, spend from the separate API balance in USD. A ChatGPT or Claude connection authorized through OAuth spends website credits. These balances are separate; the quote shown by your connection is the approval basis.

How does Stereo anaglyph shadowbox differ from writing a prompt or my own skill?

The workflow supplies an explicit scene, camera pair and inspectable component exports. It avoids faking binocular depth with a single flat-image offset or an unexplained color filter.