Can I change the words and colors?

Yes. All five listed content fields are JSON inputs, with palettes and semantic overrides. The observation-sheet header is fixed in the scene code; the image is replaced through its named raster slot.

Do I need to supply footage?

No presenter footage is needed. The observation sheet does require evidence-image, but a bundled default is supplied. Replace that illustration when your explanation calls for actual evidence material.

Can I revise the motion?

Yes. Keep the initial source convergence, coordinated compaction and larger evidence layout. Removing the second layout would discard the shot’s central explanation rather than merely shorten it.

Will it find the shared pattern in my inputs?

No. processor, evidenceTitle and evidenceRows are all supplied by you. The scene illustrates your reasoning without performing research or validating the conclusion.

Is the bundled picture genuine research evidence?

No. It is illustrative material. Use an appropriate replacement and maintain the provenance of your actual sources if the presentation makes an evidential claim.

CreatorMotion · Convergence to Evidence

Previews from the publisher

Move from a collection of sources to a finding, then make room for the evidence behind it. Source labels connect to a central finding; the complete network shrinks upward as a large observation sheet and audience label appear. This 7.1-second scene presents a research explanation you have prepared, without conducting interviews, analyzing sources or generating the finding itself.

What you get

A local generator, editable HyperFrames two-layout shot and motion/review instructions for a 1920×1080, 30 fps segment. Generate a project and render the visual explanation from your supplied material.
Up to six inputs, a processor label, evidenceTitle, up to four evidenceRows and audienceLabel. A required evidence-image raster slot has a bundled default that can be replaced with relevant local material.
Source-to-finding connectors, a network compaction beginning at 2.25 seconds, an observation sheet entrance at 2.80 seconds and an audience glyph from 3.65 seconds. The second layout retains the smaller network as context instead of stopping at a convergence diagram.
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

Prepare the evidence panel before writing the finding. If the rows cannot support the conclusion independently of the animation, revise the claim rather than using converging lines and a polished sheet to lend it authority.

Good fit

A creator explaining how several already-reviewed sources inform a particular observation.
A short research or teaching passage where the audience needs both the relationship diagram and a readable supporting panel.
A series of findings using consistent source rows, evidence-sheet typography and an audience context.

Not for

Automatically analyzing interviews, extracting findings, validating research or proving that a pattern represents an entire population.
Generating genuine evidence from the bundled illustrative image, or treating a connection line as a citation or verification.
Automatic long-form editing, generated presenter performances or soundtrack, or copying another creator’s identity and source materials.

How to use

You say

/creatormotion-diagram-convergence-evidence Turn my supplied explanation into a white-yellow B-roll scene using the Convergence to Evidence effect. Use the text, data and media I provide, and ask for any required input that is missing.

Prepare concise inputs, processor, evidenceTitle, evidenceRows and audienceLabel. Use no more than six visible source labels and four evidence rows; the implementation ignores later entries. The source labels and finding are supplied text, not a computation.
Cross-check each evidence row against your actual research. Distinguish participant observations from your interpretation, and describe the audience no more broadly than the material supports. The animation itself does not test representativeness or generate supporting citations.
Reuse the bundled evidence-image only for an illustrative scene, or replace it through --images MAP.json with material appropriate to your explanation. Relative image paths resolve beside the map, and unnamed defaults stay in use. This image is required by the scene helper; there is no blank placeholder fallback. No presenter clip or alpha matte is used.
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. Inspect both layouts and the camera handoff in actual rendered frames. Keep the enlarged sheet, image crop, title and notes readable after the network shrinks; check that connectors still preserve their source relationship. Follow the image policy and keep supporting labels at least 24 px on the documented canvas.

Requirements and costs

You bring: inputs: provide your own content or retain the illustrative default. · processor: provide your own content or retain the illustrative default. · evidenceTitle: provide your own content or retain the illustrative default. · evidenceRows: provide your own content or retain the illustrative default. · audienceLabel: 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