ChatGPT
"City Skyline Success Portrait"
Written for ChatGPT. Results and reference-photo support may differ across models.
The complete prompt
CRITICAL RULE #1 (read first, applies above all else): The face in the
output MUST be the exact same person as the uploaded reference photo.
Do not generate a new face, do not beautify, do not idealize, do not
blend with a generic face. If you are unsure whether the face matches,
default to making it MORE identical to the reference, not less.
IDENTITY LOCK (exact match required): Match the reference photo exactly
for: face shape and bone structure, eye shape/size/color/spacing,
eyebrow shape, nose shape and width, lip shape and fullness, chin and
jawline shape, cheekbone structure, skin tone and undertone, any
visible marks, moles, or asymmetries. These are not suggestions — they
are hard constraints. Zero deviation allowed.
DO NOT COPY FROM REFERENCE (only these things should change): expression,
eye gaze direction, head angle/tilt, and body pose should NOT match the
reference photo — generate these freshly based on the scene below. To
be clear: FACE IDENTITY = locked exactly. EXPRESSION/POSE/ANGLE = freely
generated and different from the reference.
EMOTIONAL INTENT (design goal): This should feel like a "lead character"
moment — the kind of photo a guy would genuinely want to post because
he looks powerful, successful, and effortlessly confident, like the
protagonist of his own story. Not overly posed or try-hard — relaxed
swagger, sharp presence.
LIGHTING SETUP (as a real photographer would dial it in): Key light —
warm late-evening sun over a city skyline, acting as a strong warm
backlight from behind at a low angle. Fill — soft ambient light
bouncing off nearby glass buildings, gently lifting shadows on his
face at roughly a 2:1 ratio so he doesn't go silhouette-dark. Rim
light — the low sun creates a sharp golden rim along his hair and
jacket edge. Catchlights in his eyes should be sharp and intense.
LENS & OPTICS: Simulate an 85mm lens at f/1.8 — flattering facial
compression, background rendered as a soft dreamy wash of golden
bokeh from city skyscrapers and lights beginning to switch on, gentle
fall-off in sharpness away from the focal point, faint natural
vignette at the corners.
FILM/COLOR SCIENCE: Warm success-hour film response — highlights
bloom softly rather than clipping, shadows lifted gently rather than
crushed black, warm amber-gold midtones, natural true-to-reference
skin tone — color grading must not shift his actual skin tone from
the reference.
Style: A sharply fitted blazer or structured jacket over a plain
shirt, sleeves slightly rolled or collar open, minimal accessories
(watch, simple chain) — the kind of look that signals success without
trying too hard, realistic and relatable, not an exaggerated glam
transformation.
NEW POSE & ANGLE (must differ from reference, face identity unchanged):
Standing on a rooftop or high balcony ledge, one hand in his pocket,
jacket caught slightly by the wind, body angled at three-quarters to
the camera, head turned back over one shoulder toward the lens,
weight settled confidently on the back foot.
NEW EXPRESSION (must differ from reference, face identity unchanged):
A calm, confident half-smile with a relaxed jaw and sharp, steady
eyes — the natural composed look of someone who has just accomplished
something and is taking in the view, not a stiff copied expression.
RETOUCH PIPELINE: Smooth tonal transitions while fully preserving fine
pore-level texture and the reference face's exact proportions. No
flattening, no waxy skin, no facial reshaping of any kind.
FINAL VERIFICATION (mandatory self-check before output): Compare the
generated face side-by-side against the reference photo's face shape,
eyes, nose, lips, and jawline. If any facial feature does not match
the reference person, discard and regenerate the face to match exactly
— only the expression, pose, and angle are allowed to differ.Copy the complete prompt and use your own reference photos where requested.
Example image provided with this prompt. This prompt has not been tested by our site.


