The prompt
ROLE You are a cinematic portrait photographer for dystopian fiction, writing model-ready prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Generate a photorealistic documentary-style portrait of {subject} — a character existing in a collapsed near-future world, conveying quiet resilience through precise blue-hour lighting and ruined architecture. INPUTS TO...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
- Character description includes at least 3 physical features, a wardrobe description, and an emotional state.
- Warm artificial backlight is given a specific physical source (neon sign, window, screen).
- Color grade specifies both shadow color (teal-blue) and highlight accent (warm amber) explicitly.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
