ChatGPT

"Sunlit Library Study Portrait"

Written for ChatGPT. Results and reference-photo support may differ across models.

The complete prompt

CRITICAL RULE #1: The face in the output MUST be the exact same person 
as the uploaded reference photo. Match exactly: face shape, eye 
shape/color, eyebrow shape, nose shape, lip shape, jawline, cheekbone 
structure, skin tone, any marks/moles. Zero deviation allowed.

FORMAT: A single, calm, atmospheric shot — one frame, no panels.

DO NOT COPY FROM REFERENCE: Only facial identity carries over. 
Expression, gaze, head angle, and pose are freshly generated per the 
description below.

SCENE CONCEPT: A quiet, sunlit library corner — tall wooden bookshelves 
filled with old books, warm dust particles visible floating in a 
single shaft of afternoon light, a small wooden desk with an open 
notebook and a cup of tea.

POSE (freely generated, not copied from reference): Seated at the 
desk, one elbow resting on the table with her chin lightly propped on 
her hand, the other hand holding an open book, body angled at three-
quarters to the camera, caught mid-thought looking slightly upward and 
away from the page.

EXPRESSION (freely generated, not copied from reference): A soft, 
thoughtful, genuine half-smile, eyes slightly distant as if lost in a 
good sentence she just read — calm and unguarded.

Style: A cozy oversized sweater or cardigan in a muted neutral tone, 
minimal natural makeup, hair loosely tied with a pencil tucked behind 
one ear, simple round glasses optional.

LIGHTING SETUP: Key light — a single warm shaft of afternoon sunlight 
through a tall window, falling directly across the desk and her face 
from camera-left. Fill — soft ambient light bounced from the light 
wooden shelves, gently lifting shadows at roughly 2:1. Rim light — the 
sunbeam grazes her hair edge, with visible warm dust particles 
floating through the light. Catchlights warm and soft.

LENS & OPTICS: Simulate an 85mm lens at f/2.0 — flattering facial 
compression, background rendered as soft creamy bokeh with rows of 
blurred book spines, gentle fall-off in sharpness, faint natural 
vignette.

FILM/COLOR SCIENCE: Warm, quiet film response — soft highlight rolloff 
where the sunbeam hits, gently lifted shadows in the shelf shadows, 
rich warm amber-brown midtones, natural true-to-reference skin tone.

NATURAL AUTHENTICITY DETAILS: Genuine skin texture with visible pores, 
a few loose hair strands, a candid unposed micro-expression, slightly 
imperfect natural framing as if caught mid-moment by a friend.

ANATOMY ACCURACY: Correct hand anatomy — five fingers per hand, 
natural grip on the book, no fusion or extra digits. Re-verify before 
finalizing.

RETOUCH PIPELINE: Frequency-separation-style retouching — smooth tonal 
transitions while fully preserving pore-level texture. No flattening, 
no waxy skin.

FINISHING: Fine film grain at low opacity, visible warm dust particles 
in the light beam, no digital sharpening halos, natural imperfect crop.

FINAL VERIFICATION: Compare the generated face against the reference 
photo's face shape, eyes, nose, lips, and jawline. Confirm correct 
hand anatomy holding the book.

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