Fusion character portrait — agent playbook

One face. N worlds. Build a webtoon / game-design character bible where the SAME character is rendered through N curated east-meets-west cultural fusion lenses — identity held constant, cultural lens variable. The artifact that demonstrates what AI does that humans cannot: fuse traditions that would each take a lifetime to master, in one repeatable run.

Output

Character constant block

12-cell webtoon grid (9:16)

Curated east-west pairings

Identity-stability bias

60s subtle-push-in reel (opt)

Solo-cello unified score

No-kitsch fusion grammar

Showcase HTML page

Customize this playbook

Fill in the fields below. Your answers are inserted into the complete recipe when you copy it.

Character archetype

e.g. "young woman, mid-20s, dignified emissary" / "elder scholar, late 60s" / "warrior monk, 30s"

Character constant

The verbatim block repeated in every cell prompt to bias gpt-image toward identity-stability. Example:

Composition constant

The verbatim composition rule baked into every cell. Example:

Cell count

8 (tight) / 12 (default) / 16 (extensive). 1 cell per fusion pairing.

Cells

Ordered list of N east-meets-west fusion pairings. Each item:

Fusion quality guards

Default ON unless you opt out:

Include reel

true (default) — fire 12 × kling-v3-i2v subtle push-in + 1 minimax-music score, total ~$10

Music brief

Score mood arc. Example:

Character slug

kebab-case for output filenames + showcase page. e.g. the-emissary / the-scholar / the-monk.

RUNNER

Create and edit images and video with your agent.

$npm install -g @livepeer/runner