popnow
PricingSign inStart creating

Gradient energy and a protected central region feed a dynamic-programming search for each vertical seam. The renderer saves the source-coordinate removal order and replays actual pixel deletion and restoration, with a narrower image centered in the final frame.

Uses PopNow for
Images
Needs
Python 3 · FFmpeg

Generation is optional when you have suitable input material.

v1.0.0 · Updated Oct 25, 2026 · 3.9 MB · Use it for personal and client work; please don't resell or share the package.

What you get

  1. A real 1280 × 720 MP4, poster, contact sheet and source-hash receipt

  2. Editable local JSON and the task-specific implementation

Good for

  • Content-aware image transformations and explainable visual editing studies.

Not for

  • Guaranteed undistorted faces, automatic object masks or a simple animated crop.

How it works

Includes a local renderer

  1. Prepare the actual input

    An owned image with room around the main subject; the included cottage landscape is ready.

  2. Apply the supported controls

    Replace the source landscape. Remove 30–180 vertical seams. Set protected-region width and protection weight.

  3. Build and review the result

    The video renderer streams frames locally, emits H.264/yuv420p with fast-start metadata, and is silent. Add separately authorized audio in an external edit only if requested.

How the workflow runs

How Seam Carving Timefold works

Gradient energy and a protected central region feed a dynamic-programming search for each vertical seam. The renderer saves the source-coordinate removal order and replays actual pixel deletion and restoration, with a narrower image centered in the final frame.

What's inside the skill

What you can change

  • Replace the source landscape.
  • Remove 30–180 vertical seams.
  • Set protected-region width and protection weight.

What to review before delivery

  • The selftest checks one removed pixel per row per seam and a changed seam-count result.
  • Inspect architecture and the protected subject for distortion; change the protection settings when needed.

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.

  • Finds low-energy paths by dynamic programming and saves the original pixel-removal order.

    scripts/scene.py

  • Local validation, protected output and artifact construction.

    scripts/render.py

  • Runnable example with actual supported controls.

    examples/project.json

  • Mechanism-specific limits and visual review criteria.

    references/production.md

Why use this skill

Start with this package

Gradient energy and a protected central region feed a dynamic-programming search for each vertical seam. The renderer saves the source-coordinate removal order and replays actual pixel deletion and restoration, with a narrower image centered in the final frame. The package supplies the working example, bounded inputs and export route so these do not need to be designed from a plain prompt.

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?

The included original assets can be reused by the local builder. Replacing artwork or adding optional sound through PopNow requires a quote for that exact request. Local processing does not spend generation funds; the agent and external editing/viewing work are outside those generation charges.

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 "Seam Carving Timefold" 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 "Seam Carving Timefold" (seam-carving-timefold) for this: Remove real low-energy pixel paths, protect the main subject and replay the image transformation forward and back. Start with the bundled project, make the requested edits and inspect the actual output.

Then try

  • Replace the source landscape.

  • Remove 30–180 vertical seams.

What to have ready

  • An owned image with room around the main subject; the included cottage landscape is ready.
  • Python, Pillow, NumPy and FFmpeg/ffprobe.

Similar skills

View all →

Ratings

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

Rate this skill

Questions

How can I tell it is not just cropping?

Each removed path is selected by dynamic programming through image energy. The audit records its removal count and a hash of the seam-rank map; retained rows contain the original pixels after those paths are deleted.

Does the bundled example require paid generation?

No. The included assets or procedural inputs run locally. If you ask for new images, clips or sound, use PopNow with an exact quote and approval before generation; API USD and OAuth website credits are separate.

What is already packaged in Seam Carving Timefold?

Finds low-energy paths by dynamic programming and saves the original pixel-removal order. Local validation, protected output and artifact construction. Runnable example with actual supported controls. Mechanism-specific limits and visual review criteria.

Which parts of Seam Carving Timefold can add a charge?

The included original assets can be reused by the local builder. Replacing artwork or adding optional sound through PopNow requires a quote for that exact request. Local processing does not spend generation funds; the agent and external editing/viewing work are outside those generation charges. 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 Seam Carving Timefold differ from writing a prompt or my own skill?

Gradient energy and a protected central region feed a dynamic-programming search for each vertical seam. The renderer saves the source-coordinate removal order and replays actual pixel deletion and restoration, with a narrower image centered in the final frame. The package supplies the working example, bounded inputs and export route so these do not need to be designed from a plain prompt.