聊天GPT

外觀 - 黑白 - 重塑 Slim Widen

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:3,121 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

Use my uploaded personal photo as the ONLY source of facial identity. Use the provided reference image as the ONLY source for the subject's clothing, body figure, pose, hairstyle styling, composition, environment and overall visual appearance.
Recreate the reference image as closely as possible, but replace ONLY the face/identity of the main subject with my face.
IDENTITY: Preserve my exact facial identity from my uploaded photo — exact face shape, facial structure, skin tone, eyes, eyebrows, nose, lips, jawline, beard/moustache if naturally present, hairline and all recognizable facial characteristics. My face must clearly look like me. Do not beautify, reshape, slim, widen or redesign my facial features.
BODY & FIGURE: Keep the exact same body figure, physique, proportions, silhouette, height appearance, waist/shoulder proportions and overall body shape as shown in the reference image. Do NOT use my body's proportions from the personal reference photo. My uploaded photo is for FACE IDENTITY ONLY.
DRESS: Keep the exact same dress as the reference image — same white elegant floor-length gown, same backless/open-back design, same neckline, same fabric, same fit, same length, same draping, same folds and same overall silhouette. Do not replace, redesign or modify the clothing.
POSE: Copy the reference pose precisely: subject walking away from the camera, back toward the camera, body naturally positioned forward, one arm relaxed, torso slightly turned, and head looking back over the shoulder directly toward the camera.
EXPRESSION: Keep the same subtle look-back expression from the reference — calm, confident, elegant, slightly mysterious and naturally composed. Apply this expression to my face while preserving my real facial identity.
HAIR: Keep the hairstyle and overall hair arrangement consistent with the reference image, while naturally adapting it around my facial structure. Do not let the hairstyle change my identity.
BACKGROUND & COMPOSITION: Keep the same city street, skyscrapers, trees, cars, traffic lights, sidewalk, camera angle, framing, perspective and background atmosphere as the reference. Reproduce the same overall composition and subject placement.
PHOTOGRAPHIC STYLE: Ultra-realistic professional fashion/editorial street photography, natural daylight, subtle monochrome/low-saturation cinematic treatment, realistic skin texture, authentic fabric texture, natural shadows, realistic depth of field, subtle film grain and high photographic detail.
CRITICAL RULE: Reference image = BODY + FIGURE + DRESS + POSE + HAIR STYLING + BACKGROUND + COMPOSITION. My uploaded photo = FACE IDENTITY ONLY. Do not transfer anything else from my personal photo.
Negative prompt: different face, wrong identity, generic face, altered facial structure, beautified face, changed body proportions, changed figure, different dress, different gown, redesigned clothing, different pose, different camera angle, different composition, exaggerated expression, distorted hands, extra fingers, malformed body, unrealistic anatomy, plastic skin, CGI, cartoon, illustration, text, watermark, logo.

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