# Low-poly parable

Recipes / Preset / Edit styles. Checked 2026-11-13.

A hard subject becomes watchable as one person's story, while every turn rests on a source the viewer can see.

- Use when: Brand films, opinion pieces, future scenarios, awareness.
- Phrase: a first-person narrated story in dated chapters, staged in a low-poly 3D world with anonymous figures, a figure holding the printed source to camera at every fact, sentence captions revealed word by word
- Page: https://directorchair.ai/preset/edit-low-poly-parable
- JSON: https://directorchair.ai/api/preset/edit-low-poly-parable.json

## Watch out

- No photoreal face anywhere: the anonymity is the point. (practitioner; Director Chair measurement of a published short, Oct 2026)
- People watch a story and keep a list: 1.6 percent of plays saved here, against 5 to 6.5 percent for the same account's step lists. Do not use it for a how-to or a lead magnet. (measured; Director Chair measurement of a published short, 23 Oct 2026)
- The reference opens on a black frame 0, which is its thumbnail. Open on the first lit frame. (measured; Director Chair measurement of a published short, 23 Oct 2026)

## Measured on the reference

| What | Value |
|---|---|
| Length | 344.4 s |
| Aspect | 9:16 |
| Visual changes per 10 s | 2.03 |
| Median segment | 4.1 s |
| First visual change | 0.43 s |
| First spoken word | 0.0 s |
| Spoken words per second | 2.57 |
| Loudness, integrated | -15.2 LUFS |
| True peak | -2.2 dBTP |
| Sound floor | -42.6 dBFS (a quiet bed is likely) |
| Face in sampled frames | none: no presenter |
| Plays, saves | 12,700 plays, 1.6 percent saved (read 23 Oct 2026) |
| Against the account's median | 2.1 times |

## The recipe

1. Write the script as one person's story in dated chapters, each turn anchored on a real source. Narrate in the first person at about 2.5 words per second.
2. Build each chapter as a low-poly 3D set with soft light and shallow depth of field. Cast anonymous figures and one narrator figure.
3. Hold each set with a slow push or drift and cut at the end of a sentence: 1.5 to 2.5 changes per 10 seconds, holds of 3 to 5 seconds.
4. Whenever a fact is stated, cut to a figure holding the printed source page to camera, readable.
5. Captions: one sentence at a time, small white sans with no box, revealed word by word, low centre.
6. A quiet ambient bed under the voice; sound effects only where the story has an object. Voice at -14 LUFS.

## Not for

Step lists, tool tutorials, lead magnets, product demos, anything under 60 seconds.

## Prompts

### Any chat model

```
Give me a production plan: the shots or scenes in order, what each one needs, and the edit settings, for a short video about [your product], for [your audience]. The technique is low-poly parable: a hard subject becomes watchable as one person's story, while every turn rests on a source the viewer can see. How it works: a first-person narrated story in dated chapters, staged in a low-poly 3D world with anonymous figures, a figure holding the printed source to camera at every fact, sentence captions revealed word by word. It is right for: brand films, opinion pieces, future scenarios, awareness. No photoreal face anywhere: the anonymity is the point. People watch a story and keep a list: 1.6 percent of plays saved here, against 5 to 6.5 percent for the same account's step lists. Be concrete: numbers, seconds and settings, no theory. Ask me one question first if something you need is missing.
```

## Goes well with

- Source held to camera: https://directorchair.ai/effect/source-to-camera
- Sentence captions, revealed word by word: https://directorchair.ai/effect/caption-sentence-reveal
- Cut on the end of a sentence: https://directorchair.ai/transition/cut-on-sentence-end
- Fade from black (know the cost): https://directorchair.ai/transition/fade-from-black
- 3D render: https://directorchair.ai/style/3d-render-style
- Generated scenes cut to sound: https://directorchair.ai/format/format-generated-scenes

## Source

Our own reading and measurement of a TikTok by @pro.glitch, posted 19 Oct 2026. The clip is a third-party reference and is not shown; the words here are ours https://www.tiktok.com/@pro.glitch/video/7698204515014577421

Text CC BY 4.0, Director Chair (directorchair.ai). Reference clips and their card texts belong to their makers.