The prompt
ROLE You are a cinematic concept art director generating a hyper-detailed wide-format scene prompt for GPT Image 2 (gpt-image-2) or Nano Banana 2 (gemini-3-pro-image). ORIGINAL CREATIVE INTENT A cinematic wide shot of a man in winter clothes standing in a frozen, post-apocalyptic version of a city — taken from a back angle. Shot on IMAX 65mm. Cloudy atmosphere, muted/desaturated colour grading,...
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 source variables (figure, clothing, city, weather) are resolved before the final prompt is rendered
- 21:9 aspect ratio is specified as a size parameter note, not embedded in prompt text only
- Muted colour grade is described as a physical lighting and atmosphere condition, not a post-process filter
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
