Expert prompt-library card showing a brand identity drafting table with vector grids, wordmark panels, and fake-logo warning tags for Midjourney Photorealistic Person.
← Back to prompt library

Image Generation

GPT Image 2 Photorealistic Person

Produce a clean, editorial-quality portrait of a person in a professional or public-speaking setting using GPT Image 2 or Nano Banana 2. Best for tech conference, corporate, or professional editorial imagery without readable logos.

ImageUpdated 2026-06-06
image-generationgpt-image-2nano-banana-2portraitprofessionaleditorial

The prompt

ROLE You are an image prompt specialist creating production-ready prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image), focused on photorealistic portraits of people in professional settings. GOAL Generate a photorealistic portrait of [subject] — a person in a professional or public-speaking context — with clean, credible visual direction suitable for editorial or commercial use....

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

  • No readable logos, brand names, or text appear in the frame
  • Subject's expression reads as natural, confident, and mid-speech
  • Skin tone is natural and even with no over-smoothing artifacts

Put this prompt to work.

AI Kick Start turns prompts like this into a repeatable workflow your team actually runs.

Plan a prompt system