Can I change the words and colors?

Yes. Supply before and after through JSON and select a palette or semantic overrides. Card geometry, rejection and approval sequence remain editable in the project.

Do I need to supply footage?

No. This particular effect is graphic-only. Its cards, drawn line and badges do not require presenter footage, a matte or photos.

Can I revise the motion?

Yes. Preserve rejection before discard, a fresh replacement at the same reading position and one clear approval. Render again to check the handoff and settled card.

Does it generate a better replacement for me?

The composition renders the before/after phrases you provide. It does not evaluate the original or substantiate the improvement; explain your editorial reasoning separately.

Can I use a long sentence or paragraph?

The authored strip is designed for concise phrases. Longer material needs a considered type/layout change and another rendered check; it is not automatically repaginated.

CreatorMotion · Copy Card Correction

Previews from the publisher

Show a specific wording improvement in two readable stages. The first phrase appears on a paper-like strip, receives a drawn strike and rejection mark, then tilts away. Its replacement lands at the same reading position with a check. This 6.8-second graphic makes your chosen correction visible without requiring a presenter or narration.

What you get

A local generator, editable HyperFrames correction scene and motion/review instructions for a 1920×1080, 30 fps segment. Enter your two phrases, generate the project and render the resulting animation.
before and after as editable short text on outlined cards with a strong offset shadow. The rejected heading has intentional strike-through; the replacement is shown cleanly with an accent-colored approval badge.
First-card entrance from 0.16 seconds, strike from 0.90 seconds and rejection from 1.18 seconds. The old card discards from 2.05 to 2.39 seconds; its replacement enters from 2.40 to 2.74 seconds and receives approval from 2.92 seconds, followed by a quiet hold.
Four styles keep the same data and choreography: White & Yellow (white-yellow), Charcoal & Lime (charcoal-lime), Paper & Orange (paper-orange), and Black & White (midnight-ice). Semantic style overrides are supported; check contrast after changing them. Dark canvases use a fine grid. Local fonts include Inter, IBM Plex Mono for measurements and ordinals, Smiley Sans and Noto Sans SC. Chinese text selects Smiley Sans automatically, including accompanying Latin text; --zh-font noto-sans-sc selects Noto Sans SC, while --font takes precedence for a supplied font.

Before you choose

Make the improvement specific enough to explain in one sentence. The animation can show replacement clearly, but the meaningful teaching comes from why the new wording serves the reader better.

Good fit

A creator explaining a concrete copy edit or replacing a vague instruction with a clearer one.
A short lesson where viewers should see both the rejected wording and the proposed alternative, even without sound.
A series of writing or communication examples needing a consistent correction rhythm and typography.

Not for

Automatically finding writing mistakes, judging which sentence is stronger or proving that a rewrite improves conversion.
Comparing long documents, tracking every textual difference or retaining both versions as a permanent side-by-side view.
Automatically editing an entire film, generating a presenter or soundtrack, or copying another creator’s identity and source material.

How to use

You say

/creatormotion-type-copy-correction Turn my supplied explanation into a white-yellow B-roll scene using the Copy Card Correction effect. Use the text, data and media I provide, and ask for any required input that is missing.

Write short before and after phrases that address the same idea. Decide why the second is preferable before animating it; the cross and check communicate your judgment rather than evaluating the text themselves.
Keep both versions brief enough for the centered strip and its large type. The new card occupies the same reading position as the old one, so a much longer replacement needs a layout adjustment and fresh review.
This scene uses editable text and geometry. It needs no presenter video, matte or image replacements. Shared image-map instructions are relevant only if you deliberately extend the composition with raster content; follow the image policy for any such addition.
From the extracted package, prepare Node.js 22+, FFmpeg and HyperFrames CLI 0.8.30. Run node scripts/create.mjs --out PROJECT --data CONTENT.json --style white-yellow, substituting another documented palette if wanted. Read the motion specification and image policy before adapting the scene; use semantic --overrides for deliberate style changes.
Inspect the editable project at entry, each motion handoff and final hold, then render with the command printed by the generator. Check the resulting frames for text collisions, correct numbers and readable contrast. Keep at least 1.2 seconds for the final reading when editing, and compare all four palettes with identical content after structural changes. Narration, music and assembly into a longer film remain separate work. Check the drawn strike against the first phrase, complete removal of the rejected card and readability of the replacement beneath its badge. Only the old heading permits deliberate strike-through occlusion. Keep the approved phrase still long enough to read.

Requirements and costs

You bring: before: provide your own content or retain the illustrative default. · after: provide your own content or retain the illustrative default.
Dependencies: HyperFrames CLI 0.8.30 or compatible — required · Node.js 22 or newer — required · FFmpeg — required
Outside costs: Not collected yet
Tools used: HyperFrames
Publisher testing: v1.0.1 — Claude Code / Claude Desktop / Cowork / Codex / ChatGPT