# Character Consistency Across 24 Pages of a Generated Picture Book

> Source: <https://dev.to/clarajbennett/character-consistency-across-24-pages-of-a-generated-picture-book-4i80>
> Published: 2026-07-24 19:36:08+00:00

Generating one illustration of a child from a reference photo is easy now. Generating twenty-four of them — same child, same style, different scenes, no drift — is where it gets hard.

Generate each page independently and every one is individually plausible. Put them in sequence and the child ages three years between page 4 and page 11, the hair changes length, the nose shape wanders.

Nobody notices a single page. Everyone notices the book. Picture books are consumed as a sequence, so consistency errors compound in a way single-image metrics never capture.

Worth separating early, because the fixes are different:

**Identity consistency** — is this recognisably the same child? Driven by the reference embedding and how strongly it is weighted per generation.

**Style consistency** — do all pages look like one illustrator drew them? Watercolour texture, line weight, palette, paper grain.

Style is the easier of the two: fix the seed contribution for style, use identical style prompt fragments, and keep sampler settings constant. Identity is harder because it must survive pose, expression, and lighting changes across scenes.

**Fix everything you can.** Same base model version, same sampler, same step count, same style tokens across the whole book. Every free variable is a chance to drift. This sounds obvious and is routinely violated by pipelines that let per-page prompts specify their own parameters.

**Regenerate the whole book, never one page.** If page 9 is wrong and you regenerate only page 9, it will not match its neighbours. Consistency is a property of the set, so the set is the unit of work. This has an ugly implication: a single bad page costs a full regeneration.

**Weight identity conditioning higher than feels necessary.** The failure mode where the child is unrecognisable is much worse than the one where poses are a bit stiff. Users forgive stiffness; they do not forgive "that is not my kid."

**Constrain the scene vocabulary.** Wildly varying environments — underwater, then a spaceship, then a forest at night — drag lighting and palette around, which reads as style drift even when identity holds. A constrained palette across scenes hides a lot.

Per-image quality metrics miss the entire problem. What actually correlates with "this looks like one book":

Reading aloud in a parent's voice from a short sample means the cloned voice must stay consistent across chapters recorded as separate synthesis calls. Same failure shape as illustration drift: each clip fine alone, the set inconsistent. Fixing speaker embedding and synthesis parameters across the whole book is the same discipline.

This is what I work on at [StoryMine](https://storymine.app) — one photo in, a watercolour keepsake book out, same face on every page.

Everything here is empirical and model-specific. The failure modes have been stable; the mitigations change with every model generation, so treat the specifics as dated and the categories as durable.