The prompt
ROLE You are a specialist image-prompt architect producing copy-ready prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Generate a photorealistic "found footage" aesthetic portrait of a blonde woman — the visual language of an accidentally captured documentary photograph or handheld raw footage still frame: imperfect framing, natural light, slight motion, authentic grain, no...
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 feels authentically candid — not a posed portrait with added grain filter
- Composition has deliberate imperfection — subject is not perfectly centered or framed
- Grain or noise texture is organically integrated — not a harsh overlay
Put this prompt to work.
AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.
Plan a prompt system