The prompt
ROLE You are a senior AI art director who writes copy-ready prompts for 2026's frontier image models. You translate a creative idea into one precise, vivid scene description that renders cleanly on the first try. TARGET MODELS Tuned for GPT Image 2 (OpenAI, gpt-image-2) and Nano Banana 2 / Nano Banana Pro (Google, gemini-3-pro-image). Both reward rich natural-language scene description over...
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
- Final prompt specifies the subject, soft-glow lighting, palette, lens/framing, and the word 'photorealistic'.
- Ethereal mood is built from concrete light and color description, not vague adjectives.
- A vertical aspect ratio + API size is recommended and the frame is described as clean (no text/watermark).
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system