聊天GPT

電影黑暗電影 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:4,419 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 dark, intense, 
Bollywood/film-poster-style DP — the kind of dramatic, powerful profile 
picture that makes people stop scrolling. Mysterious, brooding, hero-
like presence, not a soft casual selfie.

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 — bold, high-impact composition with strong negative space in 
the dark background.

LIGHTING SETUP (as a real photographer/cinematographer would dial it 
in): Key light — a single hard, narrow light source from camera-left 
(like a shaft of light through a window or a spotlight), creating 
dramatic chiaroscuro contrast — one side of the face clearly lit, the 
other falling into deep shadow. Fill — minimal to none, allowing 
shadows to stay rich and deep rather than soft, roughly a 4:1 or 
higher key-to-fill ratio for strong cinematic drama. Rim light — a 
faint cool-toned edge light separates his silhouette from the pure-
black background. Catchlights sharp, small, and intense.

LENS & OPTICS: Simulate an 85mm lens at f/1.8 — strong facial 
compression ideal for a close dramatic portrait, background rendered 
as near-total darkness with faint drifting smoke or dust particles 
catching the light, heavy natural vignette pulling all focus to the 
lit side of the face.

FILM/COLOR SCIENCE: High-contrast cinematic film-poster grade — deep 
crushed blacks, desaturated cool-toned shadows, a single warm or 
amber-toned highlight on the lit side of the face for dramatic 
contrast, natural true-to-reference skin tone preserved on the lit 
side beneath the dramatic grading.

Style: A dark-toned outfit — black leather jacket, dark henley, or an 
open dark shirt collar — minimal and moody, no busy patterns, built to 
disappear into the shadow.

NEW POSE & ANGLE (must differ from reference, face identity unchanged): 
Head turned into a strong three-quarter angle with chin slightly 
lowered, one eye catching the light directly while the other rests in 
shadow, gaze intense and fixed slightly off-camera — a powerful, 
deliberate angle rather than a straight-on stance.

NEW EXPRESSION (must differ from reference, face identity unchanged): 
An intense, composed expression — jaw set firm, eyes sharp and focused, 
mouth closed and neutral to serious — the quiet intensity of a film 
hero in a poster shot, not a smile, not exaggerated anger, just 
controlled power.

RETOUCH PIPELINE: Smooth tonal transitions while fully preserving fine 
pore-level texture on the lit side of the face 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-medium opacity for a true 
cinematic feel, faint atmospheric haze/smoke drifting through the dark 
background catching the rim light, no digital sharpening halos, 
optimized to read as bold and striking 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