ChatGPT

"Aesthetic Mirror Selfie 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 an authentic, 
effortless mirror selfie — the kind she'd actually take before going 
out, casual but put-together, real and relatable rather than an over-
produced studio shot.

COMPOSITION: A full-length or three-quarter-length mirror selfie 
composition — a large wall or floor mirror reflecting her standing 
figure, phone held up in one hand as if actively taking the photo, 
her reflection as the main subject.

LIGHTING SETUP (as a real photographer would dial it in): Key light — 
soft warm ambient room light or a nearby ring light glow, acting as a 
gentle key from camera-left, natural indoor brightness. Fill — soft 
bounced light from light-colored walls or flooring, gently lifting 
shadows at roughly a 2:1 ratio. Rim light — a window or lamp behind 
her creates a subtle soft edge-glow along her hair and outfit. 
Catchlights warm and soft, visible in the mirror reflection.

LENS & OPTICS: Simulate a realistic phone-camera focal length (around 
26mm equivalent) as would naturally be used for a mirror selfie — 
natural perspective without extreme distortion, background (bedroom, 
hallway, or aesthetic wall) rendered with mild natural softness, 
phone and hand holding it clearly and correctly visible in the 
reflection.

FILM/COLOR SCIENCE: Clean, natural phone-photo film response — soft 
highlight rolloff, gently lifted shadows, warm-neutral natural tones, 
true-to-reference skin tone — realistic phone-camera color rendering, 
not an artificially cinematic grade.

Style: A trendy, wearable outfit (co-ord set, casual dress, or jeans 
with a stylish top), minimal fresh makeup, hair naturally styled — 
relatable everyday-aesthetic, not a fantasy transformation.

NEW POSE & ANGLE (must differ from reference, face identity unchanged): 
Standing at a slight angle to the mirror, one hip popped slightly, 
phone held up at chest-to-eye level in one hand with the arm naturally 
bent, the other hand resting on her waist or lightly touching her 
hair, weight shifted onto one leg — freshly generated for this scene, 
not matching the reference photo's original pose.

NEW EXPRESSION (must differ from reference, face identity unchanged): 
A relaxed, natural half-smile or soft neutral expression looking at 
the phone/mirror rather than directly posed for a camera lens — the 
casual, unguarded look of an everyday selfie, not a stiff copied 
expression.

ANATOMY ACCURACY: Correct hand anatomy holding the phone (five fingers, 
natural grip, phone proportionally correct size), correct mirror 
reflection logic (reflection matches her pose accurately, no mismatched 
or duplicated body parts).

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 — should 
still look like a real, unfiltered phone photo, not overly polished.

FINISHING: Very subtle natural phone-camera grain, no digital 
sharpening halos, slightly imperfect natural framing as a real self-
taken mirror selfie would have — not a perfectly centered studio 
composition.

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. Also 
confirm the phone/hand anatomy and mirror reflection are logically 
consistent.

Copy the complete prompt and use your own reference photos where requested.

Open ChatGPT ↗

Example image provided with this prompt. This prompt has not been tested by our site.

Photo studio
AI-generated example

A little inspiration for your own photo.

1Add your photos
Person A

Keep the face clearly visible

Person B

Keep the face clearly visible

JPG, PNG or WebP · Max. 10 MB each

Your photos are sent only when you choose Generate. Use photos you have permission to use.

2Make it yours
Change the details
Edit your prompt
Open Gemini

Getting ready…

Sign in to your account

Continue with your Google account.

You can browse and copy prompts without signing in.

How we use your information: Privacy policy