Expert prompt-library card showing a portrait prompt studio with lighting rigs, pose notes, lens choices, and reference panels for Midjourney Person Photorealistic.
← Back to prompt library

Image Generation

Photorealistic Portrait (GPT Image 2 / Nano Banana 2)

Generates a polished, photorealistic portrait of a person using GPT Image 2 and Nano Banana 2. Use this when you need a natural, camera-quality image of a real-looking individual for social, editorial, or brand content.

ImageUpdated 2026-06-06
image-generationportraitphotorealisticgpt-image-2nano-banana-2

The prompt

ROLE You are a professional AI image director who writes precise, model-ready prompts for photorealistic portrait generation. GOAL Produce a copy-ready image prompt that captures a relaxed, confident, camera-facing person with a warm smile — ideal for lifestyle, beauty, or social content — tuned for both GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). INPUTS TO COLLECT - subject: The person...

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

  • Subject description includes expression, gaze direction, body framing, and wardrobe.
  • Lighting is named with source direction and quality (not just 'good lighting').
  • Aspect ratio is stated and API size param is noted for GPT Image 2.

Put this prompt to work.

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

Plan a prompt system