Prompt Architecture

Status: Candidate production standard

Prompts must be readable, diffable, and reusable. Store the structured record; compile it into model-specific text only at generation time.

Inheritance

Universe → Show → Season → Cast → Location → Shot → Model adapter

Later layers may add detail but must not silently contradict an earlier lock.

Human-readable shot record

identity:
  show: Little Lanterns
  season: 01 Alphabet Adventures
  episode: S01E__
  panel: 06

style:
  medium: cinematic anime-inspired preschool animation
  rendering: clean shapes, soft dimensional light, controlled texture
  palette: warm lantern gold against teal-blue shadows

cast:
  visible: [Lumi]
  lumi:
    hair: deep navy twin buns
    eyes: large teal
    wardrobe: teal and cream with warm-gold details
    signature: small lantern pendant

location:
  name: Lantern Club room
  anchors: [arched window, low map table, hanging lanterns]
  time: blue hour

shot:
  framing: close-up
  lens_intent: intimate portrait compression
  camera_height: eye level
  subject_scale: face fills most of frame
  composition: Lumi alone; clean eyeline space camera-right
  action: she notices the letter glowing
  emotion: quiet wonder
  continuity: pendant visible; background softly recognizable

output:
  aspect_ratio: 3:4
  dimensions: 864x1152

Compilation rules

1. Include only visible character features in the final shot prompt.
2. Put shot framing and subject scale near the beginning and reinforce them in composition.
3. State exactly who is visible; “Lumi alone” is stronger than omitting Pip.
4. Use stable location anchors, but vary camera position and focal depth.
5. Preserve style language verbatim across a sequence.
6. Keep negative constraints in the model adapter, not scattered through story fields.
7. Record model, workflow version, seed, dimensions, and output link.

Why distinctive features matter

Perfect pixel identity is unrealistic across independent generations. Strong, orthogonal visual anchors—silhouette, hair shape, palette, signature object, and movement—make small variance tolerable while preserving recognition.