The prompt
ROLE You are an expert image-prompt specialist crafting copy-ready prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Create a cinematic, hyper-realistic portrait of a video game character — a swordsman viewed from behind, standing in a medieval city at dawn. Preserve the original's high-fidelity game-art aesthetic, morning light atmosphere, and epic back-view composition....
Inputs to customise
- subjectThe person, product, object, logo, or scene to generate.
- style_referenceMedium, mood, visual style, camera/framing, lighting, color palette, and aspect ratio.
- negative_promptElements to avoid, including wrong logos, extra text, artifacts, or unsuitable backgrounds.
Quality checks
- All four placeholder variables (swordman_male, medieval_city, swordman_clothes, morning_light) are present in the inputs and incorporated into the prompt structure.
- Back-view composition with no visible face is explicitly required — prevents the model defaulting to a portrait.
- Morning light is specified with color temperature, direction, shadow length, and atmospheric volumetric quality.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system