Same prompt, generated with each model separately — click one to see how it holds up.
Why this works
The phrase “young man in profile wearing rectangular glasses” gives the portrait a crisp, recognizable close-up outline, while “his silhouette filled with the Chicago skyline” makes the city read as internal imagery rather than a separate background. “Blue hour,” “cooler silver-blue reflections,” and “deeper indigo/teal background” establish the moody black-gray palette, with “subtle electric cyan accents” adding restrained points of contrast along the buildings. “A central tall tower still silhouetted among the cluster of skyscrapers” supplies a visual anchor inside the profile, and “cinematic contrast” keeps the facial edge and skyline legible despite the dark tones.
FAQ
→How do I make the skyline more prominent than the man’s face?
Replace “portrait-closeup” and “young man in profile wearing rectangular glasses” with “medium close-up profile with a simplified facial silhouette and skyline-dominant double exposure.” Change “his silhouette filled with the Chicago skyline” to “the Chicago skyline occupying most of the silhouette, with skyscrapers extending beyond the head and neck.”
→How do I shift this from moody futuristic blue hour to a warmer, nostalgic city portrait?
Replace “blue hour,” “cooler silver-blue reflections,” and “deeper indigo/teal background” with “late golden hour, warm amber reflections, and a dusky rose-orange background.” Change “subtle electric cyan accents” to “soft tungsten-gold lights along building edges” and replace “futuristic urban atmosphere” with “nostalgic cinematic urban atmosphere.”
→How do I create a series of variations using different cities while keeping this visual structure?
Keep “photorealistic double-exposure portrait,” “young man in profile wearing rectangular glasses,” “cinematic contrast,” and “sharp clean composition” unchanged. Replace “the Chicago skyline” and “Chicago River” with a city-specific pair such as “Tokyo skyline and Sumida River,” “London skyline and the Thames,” or “New York skyline and the East River,” then change “a central tall tower” to a landmark appropriate to that city.
Learn the technique behind this
- Why can't AI spell, and how do I get readable text in an image? — Older diffusion models had no character-level representation of text, so they produced letterform-shaped texture instead of words.
- How should a prompt be structured, and does word order matter? — A prompt that behaves predictably names one subject first, then what it is doing, then where, then the light, then the lens or medium, then the style.
- Which aspect ratio should I use, and how does it change the image? — Aspect ratio determines what the model composes, not how it's cropped afterwards.
Related prompts
Woman in Teal Light, Shadowed Fashion Portrait
Eerie Elegance Among Marble Busts
Charcoal turtleneck with red eye-beam
Dreamy Macro Portrait in Cool Water
