Skip to main content
Declarative motion graphics that AI can write, humans can tweak — and the human’s edits survive an AI regeneration. At “prompt → mp4”, reframe is on par with Hyperframes or a Remotion skill — our own benchmark says exactly that, parity not superiority. The difference starts on the second turn: what you get back is not freeform code but an addressable document, so you can keep tweaking, regenerating, and scaling it without your changes being silently lost. A human-edited scene (top) and the same edits surviving a full AI redesign of the base scene (bottom) Top: a scene with human overlay edits applied (brand color, retimed reveal, watermark). Bottom: an AI fully regenerated the base scene — different layout, different timing — and the same overlay reapplied by stable id. 4 edits survived; the one renamed node was reported as an orphan, never silently dropped. The reframe demo — made with reframe itself The demo above is a reframe scene (examples/scenes/reframe-demo.ts) — render it yourself: npx reframe-video render examples/scenes/reframe-demo.ts.

​
What it is

Everything is a pure function of time: evaluate(scene, t) — no wall clocks, no randomness without a seed, so scrubbing and distributed rendering come for free, and the same input renders byte-identical frames.

Quickstart

Install, render your first scene, open the editor.

The loop

Why AI-write + human-edit + deterministic render is one document.

Authoring guide

The complete eDSL syntax — what an LLM reads to write valid scenes.

Gallery

A reel of scenes, each a few-line declaration.

​
Why not just Hyperframes / Remotion?

Their output is arbitrary HTML/React — great to generate once, impossible to safely operate on afterwards. reframe’s output is data with stable addresses, and everything below falls out of that one difference:
the second turnHTML / React outputreframe
”tweak just the color and timing”edit code by hand, or re-prompt and hope nothing else changesturn knobs in the preview — no code
”now redesign it” after my tweaksregeneration overwrites your hand edits — silent loss is the defaultedits live in an overlay; they reapply onto the regenerated scene (measured 100% across 23 regenerations/turns), breaks are reported loudly
”make 50 personalized versions”only what the author pre-parameterized (props)any address, post-hoc: nodes.name.content
”is it wrong before I render?“semantic failures are invisible until pixelsstructure validates pre-render with actionable errors
If your video is fire-and-forget, use the simpler tool. If it’s an asset that will be tweaked, regenerated, and multiplied — that loop is what reframe is for.