popnow
PricingSign inStart creating
Portrait of a woman in coral clothing reconstructed from overlapping geometric triangles on blue

A seeded search places triangles where the source still differs from the current reconstruction. Each candidate solves its own color and is accepted only when it reduces pixel error; the final SVG contains the accepted translucent polygons. Suitable owned portraits render locally without generation calls. PopNow can create a missing portrait after an exact quote and approval; output size, search count and candidate count affect local computation.

Uses PopNow for
Images
Needs
Python 3

Generation is optional when you have suitable input material.

v1.0.0 · Updated Oct 25, 2026 · 5.9 MB · Use it for personal and client work; please don't resell or share the package.

What you get

  1. Portrait PNG and editable triangle-layer SVG

  2. Ordered shape ledger with per-layer error reduction

  3. Copied source, portable brief and local preview

Good for

  • Art portraits built from visible geometric planes
  • Editable cover artwork and color studies

Not for

  • Photorealistic detail preservation
  • Semantic retouching or identity verification

How it works

Includes a local renderer

  1. Choose the input

    Choose a clearly lit portrait and an output crop.

  2. Render and inspect

    Fit the triangle layers, then compare the face with the copied source.

  3. Adjust and export

    Adjust shape count or opacity and export the PNG, SVG and ledger.

How the workflow runs

How Geometric shape portrait works

A seeded search places triangles where the source still differs from the current reconstruction. Each candidate solves its own color and is accepted only when it reduces pixel error; the final SVG contains the accepted translucent polygons.

What's inside the skill

What you can change

  • shape_count: 60–1600 accepted-search steps
  • opacity: 0.25–1 for every fitted layer
  • candidates: 12–140 alternatives per step
  • seed and output width/height

What to review before delivery

  • Every accepted triangle has a positive error reduction.
  • The example and changed count both reduce source error by at least 25%.
  • 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 supplies the residual search, fitted color solver and ordered editable layers. A text prompt alone does not provide this reproducible decomposition or its error ledger.

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?

Suitable owned portraits render locally without generation calls. PopNow can create a missing portrait after an exact quote and approval; output size, search count and candidate count affect local computation.

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 "Geometric shape portrait" 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 "Geometric shape portrait" (geometric-shape-portrait) for this: Choose a clearly lit portrait and an output crop. 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 shape_count: 620 → 120.

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

What to have ready

  • A portrait you own or may use
  • Desired shape count and output size
  • 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

Are the shapes actually editable?

Yes. The SVG stores each accepted triangle as a separate polygon with a fill and opacity. It does not embed the source photograph as the finished portrait.

Will more shapes always look better?

More accepted shapes reduce the fitting error, but a lower count may produce a stronger geometric reading. Review the actual face at the intended size; the fitting metric does not judge likeness or artistic quality.

What costs depend on this workflow?

Suitable owned portraits render locally without generation calls. PopNow can create a missing portrait after an exact quote and approval; output size, search count and candidate count affect local computation.

What is already packaged in Geometric shape portrait?

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

Which parts of Geometric shape portrait can add a charge?

Suitable owned portraits render locally without generation calls. PopNow can create a missing portrait after an exact quote and approval; output size, search count and candidate count affect local computation. 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 Geometric shape portrait differ from writing a prompt or my own skill?

The package supplies the residual search, fitted color solver and ordered editable layers. A text prompt alone does not provide this reproducible decomposition or its error ledger.