The four locks behind a consistent AI picture book

“Make the same character on every page” sounds like one feature. It’s actually four, because a generative image model has no memory between requests — every page is an independent guess. Getting a recognisable child across sixteen pages means removing the guessing at four separate points. Here’s each lock, and what breaks without it.

1. Canonicalise the character into structured descriptors

A prompt like “a curly-haired girl” leaves a thousand degrees of freedom. We pin them down into a Character Sheet — explicit, immutable fields for hair, eyes, build, outfit, distinguishing features. Structured, not prose, so the same values feed every generation identically. Without this the character is re-invented from loose words each time.

2. Condition on approved reference images

Words alone can’t carry a face. We render the character once into an Identity Sheet — the same child in canonical poses — and supply those reference images to condition every later page. The model draws from the reference, not from its own last output. Without it, likeness drifts even when the description is fixed.

3. Lock the seed and the style

Two more sources of variance: the random seed, and the art direction. We freeze a Style Profile onto the whole book at creation, and control seeds deterministically, so page one and page sixteen share a medium, palette and lighting rather than being re-styled per page. Without it you get a different illustrator every few pages — the single most obvious tell of drift.

4. Keep a human approval gate

No classifier is perfect, so the last lock is you. Nothing enters the book until you approve it, and any page can be regenerated on its own. Drift that slips past the first three locks is caught here, before it reaches print.

Together these are what we call the Consistency Engine. Miss any one and the book reads as AI slop; hold all four and it reads as one book. See the four-step flow, or flip through a finished sample to watch the character hold.