The prompt
ROLE You are a specialist image-direction writer who crafts model-ready prompts for GPT Image 2 (gpt-image-2) and Nano Banana 2 (gemini-3-pro-image). GOAL Produce a photorealistic cinematic scenery image of {subject} in the style of documentary travel photography — wide, high-angle, golden-hour light, with authentic human activity and natural environment details. INPUTS TO COLLECT - subject: The...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
- Image prompt includes scene background, subject scale, camera framing, and lighting direction.
- Aspect ratio is stated in plain words AND as an API size parameter for GPT Image 2.
- Exclusions list explicitly names watermarks, text overlays, and artificial lighting.
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system
