AI Skill Report Card

Directing Banana Pro Image Prompts

B+79·Aug 30, 2026·Source: Extension-selection
13 / 15

Before writing any prompt, determine mode and confirm inputs:

  1. Character exists? No → text spec → confirm → Mode 0 face lock. Yes → get reference, mirror back spec, confirm.
  2. Pick the mode: 0 face lock / 1 outfit base / 2A 3-panel sheet (default) / 2B 6-panel (explicit only) / 3 scene plate / 4 GPT-2 detail / 5 outfit swap.
  3. Run the pre-prompt check (bulleted, references first) and wait for the green light.
  4. Deliver one fenced code block. No aspect ratios, no character names, no @image tags in the prompt body (Mode 5 is the exception — it uses @image1/@image2).

Example pre-prompt check:

Pre-prompt check:
- References attached: locked character reference, outfit wardrobe plate
- Character: platinum-blonde ponytail, warm fair skin, sharp almond eyes, neutral expression
- Outfit: ivory zip-V corset, ivory parachute pants, cream platforms
- Backdrop: mid-gray seamless studio (locked default)
- Framing: full body
Sound good?
Recommendation
Add a concrete input/output example showing an actual full prompt text (fenced code block) rather than describing what the output would contain — currently examples describe the process, not the literal deliverable.
14 / 15

Progress:

  • Step 0: Determine if character is new or existing
  • Step 1 (new only): Lock text spec in plain language, confirm with user
  • Step 2 (new only): Mode 0 face lock — pick tool (Banana Pro default / GPT-2 highest fidelity / Soul Cinema two-pass iteration)
  • Step 3: Mode 1 single-image outfit base (Banana Pro full-styling OR Soul Cinema two-step composite)
  • Step 4 (optional): Mode 2A 3-panel character sheet (default) — never propose 2B 6-panel
  • Step 5 (optional, on request only): Mode 3 scene plate, Mode 4 GPT-2 detail, or Mode 5 outfit swap
  • Always: pre-prompt confirmation before every full prompt delivery

Never skip ahead. No outfit work before face lock exists. No character sheet before a single-image base exists. No scene plate or GPT-2 detail proposed unprompted.

Recommendation
Description is dense and jargon-heavy (Banana Pro, Soul Cinema, GPT-2, cinema-stack) — a glossary or one-line definitions of these terms early on would help Claude apply the skill correctly without prior context.
  • Photoreal is universal default. Never stylized/illustration/anime unless explicitly requested.
  • Flattering-realism ceiling: full skin texture (pores, peach fuzz, subsurface scattering) always on, but never harsh — no acne, no rough pores, no clinical macro-detail. Fine, even, flattering.
  • 18% gray seamless + flat shadowless grade is the locked default backdrop/lighting for ALL character work (Modes 0, 1, 2, 4, 5): one uniform gray value, no gradient, no falloff, matched equal fill on all sides, zero shadow side, zero cast shadow. White seamless only on explicit request — flatness never comes off even then.
  • Mode 3 is the only mode with directional cinematic lighting (the cinema-prose register, five-paragraph structure, positional prose not coordinates).
  • No character names — describe by visual markers only (hair, wardrobe, identity markers). Real brand names allowed, paired with visual description. Camera/lens/film-stock brand names never used.
  • No aspect ratios in prompt text — set in the Higgsfield UI.
  • Cinema stack closes Modes 0/1/2/4/5; Mode 3 closes with the five-paragraph cinema-prose register instead.
ModePurposeGate
0Face lock for new charactersText spec confirmed first; tool fork (Banana Pro / GPT-2 / Soul Cinema two-pass)
1ASingle-image outfit, Banana ProFace lock or existing reference must exist
1BSingle-image outfit, Soul Cinema two-stepSame; Step 1 builds outfit on neutral model, Step 2 composites onto locked character
2A3-panel character sheet (DEFAULT)Base outfit reference must exist and be approved
2B6-panel character sheet (legacy)Explicit request only; flag resolution tradeoff once
3Cinematic scene plate (with/without character)Never proposed proactively
4GPT-2 detail face/chest-upExplicit request; mention credit cost once
5Outfit replacement (two-reference swap)@image1=outfit/pose, @image2=character — order is fixed
14 / 20

Example 1 — New character request: Input: "I want to build a new character, a fierce street-racer type." Output: Skill asks for character description in the user's own words → mirrors back locked text spec (build, face, hair, skin, identity markers, default expression) → waits for confirmation → asks tool choice for Mode 0 (Banana Pro default) → delivers pre-prompt check → delivers Step 0.A prompt in one code block with mid-gray flat grade and locked black camisole/tank.

Example 2 — Character sheet request, no format specified: Input: "Can you make a character sheet for her in the red dress?" Output: Confirms a Mode 1 base outfit reference exists already. Defaults to Mode 2A (3-panel: headless front, full-body rear, tight chest-up face lock). Picks Variant B (clean neck cut) since a red dress with a plunging/strapless neckline has no collar to hollow. Delivers pre-prompt check, then single prompt in one code block. Does not ask about or mention the 6-panel.

Example 3 — Minor iteration: Input: "Same shot, just have her looking off to the side instead." Output: Since this is a minor tweak to an already-approved prompt in-thread, skip the pre-prompt check and deliver the revised full prompt directly.

Recommendation
The mode table and rules are excellent, but consider trimming redundancy between 'Core Rules', 'Best Practices', and 'Common Pitfalls' sections, which overlap on lighting/flat-grade repeated three times.
  • Always list uploaded references first in any pre-prompt check — confirms nothing was missed.
  • Lean on references for identity/geometry; only describe what's unique to this specific shot (composition, pose, light, framing).
  • Apply the resolution-aware detail rule in Mode 3: only describe what the camera at that distance/lens/motion/light could actually resolve.
  • Use positional prose ("anchored on the left third," "in the deeper background camera-left"), never X/Y coordinates, in Mode 3 output.
  • State the skin-tone consistency clause explicitly on every multi-panel sheet — rear panels drift darker without it.
  • Do NOT propose the 6-panel sheet unprompted — always default to 3-panel.
  • Do NOT add directional lighting (key/fill/rim/shadow side) to any character plate — flat grade only.
  • Do NOT build a character sheet before a single-image outfit base exists.
  • Do NOT re-describe identity/wardrobe already carried by an attached reference image — trust the reference.
  • Do NOT skip the pre-prompt check except for genuine minor iterations on an already-approved, already-delivered prompt.
  • Do NOT use character names, aspect ratios, @image tags (outside Mode 5), or teeth-showing smiles unless explicitly requested.
0
Grade B+AI Skill Framework
Scorecard
Criteria Breakdown
Quick Start
13/15
Workflow
14/15
Examples
14/20
Completeness
17/20
Format
13/15
Conciseness
13/15