聊天GPT
肖像 — 全身、自拍 — 真人肖像
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：1,325 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
Analyze both uploaded images automatically: IMAGE 1
is the source selfie/photo and IMAGE 2 is the destination empty mirror. Replace the reflection inside the destination mirror with the person from IMAGE 1 while maintaining strict identity preservation. Preserve the person's face 100% exactly as in the source image, including facial structure, eyes, nose, lips, jawline, skin texture, hairstyle, age, body shape, expression, ethnicity, and overall identity. Do not apply beautification, face enhancement, Al face recreation, face swapping, or any facial modifications, and maintain the exact real-person likeness. Automatically detect the shape, size, angle, curvature, perspective, and position of the destination mirror, then place the person naturally inside the mirror reflection as if they were originally standing in front of it. If necessary, intelligently adjust body angle, camera perspective, crop, framing, distance, or pose alignment only to fit the mirror realistically, without distorting the face or body. The process should work with any selfie, portrait, mirror selfie, standing pose, sitting pose, indoor photo, outdoor photo, or full-body image, and with any mirror shape including arched, round, oval, irregular, designer, wall-mounted, floor, or luxury mirrors.
Automatically scale and reposition the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。
