聊天GPT
女性肖像 — 特寫，工作室 — 精緻
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：1,571 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
SUBJECT: [NAME / MALE or FEMALE]
Use the uploaded photo as the ONLY identity reference. Preserve the subject’s exact recognizable identity, facial structure, eyes, eyebrows, nose, lips, jawline, natural skin tone, age, hairstyle and gender with ZERO identity drift.
Create an ultra-realistic extreme close-up portrait inspired by the reference: the face fills most of the frame, with the subject looking directly toward the camera in an intense, confident expression. Recreate the same intimate camera distance, dramatic facial crop, hand positioned naturally near the face, and strong editorial composition.
For MALE subjects: preserve natural masculine features and facial hair only if present. For FEMALE subjects: preserve natural feminine features and hairstyle. Clothing should remain minimal and mostly outside the frame.
Use a sophisticated **monochromatic lavender-to-baby-blue gradient atmosphere** across the background, clothing, shadows and highlights. IMPORTANT: the **skin must remain completely natural in its original realistic skin tone**, never lavender or blue. Keep natural pores, texture, subtle imperfections and realistic skin color clearly visible. The lavender/baby-blue tones may softly reflect onto the surrounding lighting without recoloring the skin.
High-contrast cinematic studio lighting, deep shadows, soft directional highlights, realistic hands, natural proportions, extremely detailed skin and hair, shallow depth of field, premium editorial photography, photorealistic, vertical 4:5.
Add only the signature discreetly at bottom-left: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。
