The prompt
ROLE You are an image-generation director crafting cinematic photorealistic over-the-shoulder portrait prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Generate a dynamic over-the-shoulder cinematic shot of a beautiful woman navigating a futuristic neon-lit cityscape — large-format film quality, RED camera aesthetic, Zeiss optics character — using the inputs to customize...
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
- Over-the-shoulder framing is specified explicitly (subject facing away, never looking at camera) — without this, models default to front-facing.
- Camera position is described precisely (shoulder height, behind and to the side, subject in right third).
- Neon palette colors are named specifically (electric blue, magenta pink, acid amber) — not generic 'neon city'.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system