聊天GPT

日落情侣肖像"

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:4,201 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): Both faces in 
the output MUST be the exact same two people as the uploaded reference 
photo. Do not generate new faces, do not beautify, do not idealize, do 
not blend either face with a generic face. If you are unsure whether a 
face matches, default to making it MORE identical to the reference, 
not less.

IDENTITY LOCK (exact match required for both subjects): Match the 
reference photo exactly for each person: 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 for either person.

DO NOT COPY FROM REFERENCE (only these things should change): both 
subjects' expressions, eye gaze directions, head angles/tilts, and 
body poses should NOT match the reference photo — generate these 
freshly based on the scene below. To be clear: FACE IDENTITY (both 
people) = locked exactly. EXPRESSION/POSE/ANGLE (both people) = freely 
generated and different from the reference.

EMOTIONAL INTENT (design goal): This should feel like a genuine 
"relationship goals" moment — the kind of photo any couple would want 
for an anniversary, engagement announcement, or just to show real, 
warm chemistry. Real touch, real closeness, not a stiff stock-photo 
distance. Both partners must look equally flattering — neither should 
outshine the other.

LIGHTING SETUP (as a real photographer would dial it in): Key light — 
low golden-hour sun behind them, acting as a strong warm backlight 
from directly behind at a low angle. Fill — soft ambient sky light 
from above and in front, gently lifting shadows on both faces at 
roughly a 2:1 ratio so they don't go silhouette-dark. Rim light — the 
low sun creates a bright golden rim along both subjects' hair and 
shoulders. Catchlights in both sets of eyes should be warm and soft.

LENS & OPTICS: Simulate an 85mm lens at f/1.8 — flattering facial 
compression, background rendered as a soft dreamy wash of golden 
bokeh from a scenic outdoor setting (field, beach, or hillside), 
gentle fall-off in sharpness away from the focal point, faint natural 
vignette at the corners.

FILM/COLOR SCIENCE: Warm golden-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 tones 
for both — color grading must not shift either person's actual skin 
tone from the reference.

Style: Coordinated, flattering, wearable outfits (soft pastel or warm-
toned casual-elegant wear that complements each other) — realistic 
and relatable, not an exaggerated glam transformation for either 
person.

COUPLE BIOMECHANICS & NEW POSE (must differ from reference, face 
identity unchanged for both): Standing close together facing each 
other, both hands loosely held between them at natural waist height, 
fingers gently interlaced. One partner's forehead close to the 
other's, weight shifted slightly toward each other, one partner's 
head tilted down slightly while the other looks up — a genuine natural 
height-difference lean, not two matched, independently posed figures.

NEW EXPRESSION (must differ from reference, face identity unchanged 
for both): A quiet, tender closeness — soft eye contact between them, 
gentle smiles with the corners of both mouths lifted slightly and 
asymmetrically, not stiff copied expressions from the reference.

RETOUCH PIPELINE: Smooth tonal transitions while fully preserving fine 
pore-level texture and each reference face's exact proportions. No 
flattening, no waxy skin, no facial reshaping of any kind for either 
person.

FINAL VERIFICATION (mandatory self-check before output): Compare each 
generated face side-by-side against its corresponding reference photo 
face shape, eyes, nose, lips, and jawline. If either person's facial 
features do not match their reference, discard and regenerate that 
face to match exactly — only expression, pose, and angle are allowed 
to differ for both.

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