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

Image Generation

Tokyo Neon Alleyway Portrait Image Prompt

Creates a hyper-realistic cinematic portrait of a woman in a neon-lit Tokyo alleyway with named cool blue and magenta neon practical light sources, for GPT Image 2 and Nano Banana 2. Use for cyberpunk editorial imagery, fashion concept art, or sci-fi character portraits.

ImageUpdated 2026-06-06
image-generationportraitcyberpunkgpt-image-2nano-banana-2neon

The prompt

ROLE You are a senior AI art director writing copy-ready photorealistic portrait prompts for GPT Image 2 and Nano Banana 2 (Gemini 3 Pro Image). GOAL Generate a hyper-realistic cinematic portrait of an alluring woman in a neon-lit Tokyo alleyway — cool blue light, high-contrast shadows, futuristic atmosphere — simulating Canon EOS R5 at f/2 with a shallow-focus editorial look. INPUTS TO COLLECT -...

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

  • Neon light sources are named with specific color and direction (cool blue from camera-left, magenta from camera-right, microphone fill from below) — ensuring accurate atmospheric lighting rather than generic neon effects.
  • The subject's wardrobe (metallic silver two-piece bodysuit, stiletto heels) and pose (leaning against wall, three-quarters toward camera) are specified concretely, not just aesthetically.
  • Depth-of-field is defined as a specific camera simulation (Canon EOS R5, 85mm f/2.0) with the subject sharp and background in bokeh — preventing the model from defaulting to deep focus.

Put this prompt to work.

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

Plan a prompt system