聊天GPT

皇家金色美學DP”

為聊天GPT 編寫。不同型號的結果和參考照片支援可能有所不同。

使用提示詞前

列出的工具:聊天GPT。完整說明:4,070 個字元。 1 個提供的範例影像。

This prompt mentions reference images. Read its instructions for the required number of photos and identity constraints. We have not independently tested this prompt. Tool labels and supplied images are not a guarantee of compatibility or output quality.

完整提示詞

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 rich, regal 
"Nawabi/royal" aesthetic DP — warm, classy, and premium, the kind of 
profile picture that feels expensive and timeless rather than trendy-
casual. Calm authority, not aggression.

COMPOSITION: A close-up to medium-close-up portrait crop (chest-up or 
shoulders-up), designed to work well as a square or vertical profile 
picture — clean, centered composition with warm negative space in the 
background.

LIGHTING SETUP (as a real photographer would dial it in): Key light — 
a single warm, soft light source from camera-left, simulating candle 
or lamp light, wrapping gently around the face with soft falloff into 
shadow. Fill — minimal, allowing one side of the face to fall into a 
warm, rich shadow rather than staying flat, roughly a 3:1 key-to-fill 
ratio. Rim light — a faint warm gold edge light separates him from the 
deep maroon/charcoal background. Catchlights warm, soft, and intense.

LENS & OPTICS: Simulate an 85mm lens at f/1.8 — strong facial 
compression ideal for a close portrait, background rendered as a deep 
muted maroon or charcoal tone fading into soft darkness, gentle natural 
vignette drawing focus to the face.

FILM/COLOR SCIENCE: Rich, warm royal-portrait grade — deep amber and 
maroon tones, soft highlight rolloff (no harsh clipping), shadows 
lifted just enough to retain detail without looking crushed, natural 
true-to-reference skin tone preserved beneath the warm grading.

Style: A structured bandhgala jacket or a rich dark kurta with subtle 
gold thread detailing at the collar, a simple gold chain or brooch 
accent — refined and regal, no busy patterns, minimal but premium.

NEW POSE & ANGLE (must differ from reference, face identity unchanged): 
Head turned into a composed three-quarter angle, chin very slightly 
lifted with quiet authority, gaze steady and directed just past the 
camera — a deliberate, dignified angle rather than a casual straight-
on stance.

NEW EXPRESSION (must differ from reference, face identity unchanged): 
A calm, composed almost-smile — relaxed eyes, closed mouth, subtle 
confidence without any exaggeration — the quiet self-assurance of 
someone who doesn't need to try hard, 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.

FINISHING: Fine film grain overlay at low opacity for a timeless, 
premium feel, no digital sharpening halos, optimized to read as sharp 
and elegant even at small thumbnail size.

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.

複製完整的提示並根據要求使用您自己的參考照片。

打開ChatGPT ↗

此提示提供的範例影像。此提示尚未經過我們網站的測試。

照相館
AI 產生的範例

為您自己的照片提供一點靈感。

1加入您的照片
A 人

保持臉部清晰可見

B 人

保持臉部清晰可見

JPG、PNG 或 WebP · 最大。每個 10 MB

僅當您選擇「產生」時才會發送您的照片。使用您有權使用的照片。

2讓它成為你的
更改詳情
編輯您的提示
開放雙子座

準備好…

登入您的帳戶

繼續使用您的 Google 帳戶。

您無需登入即可瀏覽和複製提示。

我們如何使用您的資訊: 隱私權政策