聊天GPT
糖果店的視窗瞬間"
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:1,702 個字元。 2 提供範例影像。
閱讀全文決定您的任務是否需要參考照片。 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
Do not change the subject's facial bone structure, eye shape and
color, nose shape, lip shape, jawline, or skin tone in any way — keep
it 100% identical to the original photo. Do not change identity.
SCENE (describe it like a real moment, not a photoshoot): She was
sitting by a cafe window, waiting for her order, absentmindedly
looking outside at the street when something outside made her smile —
maybe a dog running past, or a familiar song playing. Caught in that
unguarded half-second before she even realized someone was looking
at her.
NEW POSE (explicit, not the original photo's pose): Seated sideways
in the chair, one arm resting on the table near a coffee cup, other
hand lightly touching a strand of hair near her ear, body turned
slightly toward the window, head tilted just a little.
MICRO-EXPRESSION (not an emotion word — the physical detail): corners
of the mouth lifting unevenly on one side first, eyes slightly
crinkled at the outer corners, eyebrows relaxed and natural, a soft
exhale visible in her shoulders.
CAMERA STYLE: Shot like a candid photo taken by a friend sitting
across the table on a phone camera — not a professional shoot. Off-
center framing with the window and street softly visible in the
background, natural imperfect crop, subject not centered in the frame.
Background: an ordinary cafe interior, window with soft daylight
coming in, a blurred coffee cup and someone's hand in the near
foreground, everyday cafe lighting — no dramatic glow, just realistic
warm indoor light.
AVOID: symmetrical stance, direct posed eye-contact with camera,
airbrushed/glossy skin, perfectly centered composition, studio-quality
polish, forced smile.複製完整的提示並根據要求使用您自己的參考照片。

此提示提供的範例影像。此提示尚未經過我們網站的測試。


