聊天GPT

電影倫敦街頭漫步 – 逼真的臉孔

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:2,445 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 Image 1 as the MAIN SCENE reference for the complete composition, pose, body position, clothing, accessories, walking posture, hand positions, rose, background, architecture, supporting people, lighting, camera angle, perspective, depth of field, and overall photographic style.

Use Image 2 ONLY as the IDENTITY / FACE reference.

Replace the male character’s face in Image 1 with the exact facial identity from Image 2. Preserve the identity-defining characteristics from Image 2 with maximum accuracy: face shape, forehead, eyes, eyebrows, nose, lips, cheeks, jawline, skin tone, hairstyle, moustache, beard/facial hair, and natural facial proportions.

At the same time, recreate the exact facial expression and emotion visible in Image 1. Transfer the expression naturally, including head angle, eye direction, eyelid position, eyebrow position, mouth shape, cheek tension, jaw position, and subtle facial muscle movement. The result should look like the person from Image 2 is naturally standing in the exact same scene and expressing the exact same emotion as the original person in Image 1 — not like an obvious face swap.

Keep the original character’s patterned black-and-cream shirt, red inner shirt, layered gold chains, green patterned wrap/shorts, pink shorts underneath, yellow sneakers, rose in the left hand, walking pose, and interaction with the woman exactly as shown in Image 1. Preserve the woman completely unchanged.

Maintain the grand historic stone building in the background, bright overcast daylight, city walkway, background dancers, natural atmospheric haze, realistic shadows, depth, and cinematic photography.

Ensure perfect anatomical integration around the face, ears, hairline, neck, jaw, and skin, with realistic skin pores and texture. Match the lighting direction, color temperature, exposure, sharpness, perspective, and shadows of the original image.

Ultra-realistic professional photography, photorealistic skin texture, natural facial anatomy, realistic hair strands, seamless face integration, accurate proportions, high detail, realistic depth of field, 4K HDR quality.

Do not copy the identity of Image 1. Do not alter the identity from Image 2. Do not beautify, reshape, slim, age, or redesign the face. Do not change the woman, clothing, pose, background, or composition. Final result must look like a genuine photograph of the person from Image 2 naturally photographed in Image 1’s scene.

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