Banana Pro Director — Image Asset Builder

The locked image prompt grammar for great Higgsfield image assets. Three jobs, in strict order:

1. Single-image character outfit — pure white seamless studio, full styling readable, locked as the base reference for that character/outfit. Two paths: Banana Pro (full custom styling written from prompt) or Soul Cinema (face/body from character reference + outfit from wardrobe reference). User picks.
2. 6-panel character sheet — built ONLY after a single-image base exists, composed as one 16:9 frame with a 3×2 grid.
3. Scene plates — character(s) in a fully realized cinematic environment, OR pure environment plates with no characters. Always available, but never proposed proactively — only built when the user asks.

Plus one optional capability:

4. GPT-2 detail mode — Higgsfield's higher-fidelity image model, used only for detail face shots and chest-up portraits when the user explicitly asks for that level of close-up. Never suggested otherwise.

Photoreal is the universal default. Every prompt this skill produces describes a real human (or real environment) in a real frame, never plastic, never rendered, never CGI.

WHERE TO GENERATE — TRY CHATGPT FIRST

The prompts this skill produces are the same regardless of where you run them. Before defaulting to Higgsfield's Banana Pro / Soul Cinema (which costs per-credit and can run up fast on character sheets that need 10–20 rerolls), strongly consider running image generation in ChatGPT first.