popnow
PricingSign inStart creating
Hybrid image combining snow-leopard detail with the low-frequency structure of an owl

An explicit affine alignment prepares the near image. The renderer combines its high-frequency residual with a Gaussian-blurred far image, then applies one global linear normalization instead of clipping; it exports the component bands and a true small-view proof. Owned image pairs and all filtering run locally. PopNow can create missing, consistently framed sources after a quote and approval; extra source attempts are optional and need their own approval.

Uses PopNow for
Images
Needs
Python 3

Generation is optional when you have suitable input material.

v1.0.0 · Updated Oct 25, 2026 · 14.2 MB · Use it for personal and client work; please don't resell or share the package.

What you get

  1. Hybrid PNG with raster-wrapped SVG

  2. Near/far alignment and frequency-band proofs

  3. Actual small-view proof, copied sources and portable brief

Good for

  • Near-versus-far optical image experiments
  • Comparing source alignment and frequency separation

Not for

  • Guaranteed recognition with arbitrary image pairs
  • Semantic alignment or a hidden-depth reconstruction

How it works

Includes a local renderer

  1. Choose the input

    Choose compatible sources and inspect their feature alignment.

  2. Render and inspect

    Separate frequency bands and combine them without destructive clipping.

  3. Adjust and export

    Compare the full-size and genuine small views before adjusting the filters.

How the workflow runs

How Hybrid distance illusion works

An explicit affine alignment prepares the near image. The renderer combines its high-frequency residual with a Gaussian-blurred far image, then applies one global linear normalization instead of clipping; it exports the component bands and a true small-view proof.

What's inside the skill

What you can change

  • lowpass_sigma: 4–60 and highpass_sigma: 1–15
  • highpass_gain: 0.2–3
  • near_scale: 0.7–1.4 and near_offset_y: −0.2–0.2
  • Two local source images and output dimensions

What to review before delivery

  • The high-frequency band and low-frequency image both contain measured variation.
  • Changing filter width and gain changes the actual image.
  • 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 package provides explicit band separation, alignment controls and honest viewing-scale proofs. It makes the effect inspectable instead of merely asking a model for an optical illusion.

What PopNow adds

Use PopNow for the missing Images in this workflow. Keep adequate material you already own, then bring new assets back into the editing and assembly steps described here.

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?

Owned image pairs and all filtering run locally. PopNow can create missing, consistently framed sources after a quote and approval; extra source attempts are optional and need their own approval.

Generation is optional when you have suitable input material. 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.

New AI images, clips or sound

Quoted for the actual model, inputs, count, duration and resolution. Extra alternatives, revisions or optional enhancement passes can add generation requests.

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.

Check the cost of your version first

Your assistant can inspect the available models and quote the exact request first. You choose which optional passes to include and approve spending before generation.

Ask your assistant

  • Use the PopNow skill "Hybrid distance illusion" for my project. List the inputs you can reuse, quote only the missing media, show the quoted total and flag any unpriced steps. Separate optional enhancements, and wait for my approval before starting anything paid.

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 "Hybrid distance illusion" (hybrid-distance-illusion) for this: Choose compatible sources and inspect their feature alignment. 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 lowpass_sigma: 12 → 25; highpass_gain: 2 → 1.1.

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

What to have ready

  • Two compatible images with similarly placed key features
  • A near and far subject intention
  • 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

Why can the subject change with distance?

Fine source detail is more visible close up, while reducing the image suppresses that detail and favors the low-frequency source. The effect depends on alignment, display size and the viewer, so inspect the actual small-view proof.

Does it automatically align the subjects?

No. You set a near-image scale and vertical offset. The package saves both aligned inputs for inspection; compatible subject framing is still a creative decision.

What costs depend on this workflow?

Owned image pairs and all filtering run locally. PopNow can create missing, consistently framed sources after a quote and approval; extra source attempts are optional and need their own approval.

What is already packaged in Hybrid distance illusion?

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

Which parts of Hybrid distance illusion can add a charge?

Owned image pairs and all filtering run locally. PopNow can create missing, consistently framed sources after a quote and approval; extra source attempts are optional and need their own approval. 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 Hybrid distance illusion differ from writing a prompt or my own skill?

The package provides explicit band separation, alignment controls and honest viewing-scale proofs. It makes the effect inspectable instead of merely asking a model for an optical illusion.