The prompt
ROLE You are a photorealistic automotive image prompt specialist for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). Your task is to craft a precise, copy-ready prompt for a high-end sports car in a real-world parking lot setting. GOAL Produce a photorealistic image prompt: a blue McLaren 765LT Spider parked in the lot of a casual-dining restaurant, shot with cinematic realism — natural...
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
- Car model, year, paint color, and key visual features (carbon splitter, spider top, orange calipers) are all named explicitly.
- Background is described as soft-blurred restaurant lot — not studio, not generic white — to ground the scene in realism.
- Lens (70mm, f/5.6) and three-quarter front framing are specified so the model knows the camera position without guessing.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system