聊天GPT
電影換臉肖像
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：1,206 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 the uploaded person's face as the primary identity reference. Create a photorealistic cinematic portrait of the same person, naturally integrated into the body and pose. Keep the person's facial identity, facial proportions, eyes, nose, lips, jawline and skin texture consistent with the uploaded photo.
Place him in the same type of pose: slightly leaning backward with a natural head position and a normal, anatomically proportionate neck. Do NOT elongate, stretch, or distort the neck. The head-to-neck-to-shoulder connection must look completely natural.
Give him messy dark textured hair, subtle facial hair, small earrings, an open black blazer, a simple chain necklace, and a dark cinematic industrial background. Moody low-key lighting, realistic skin texture, subtle sweat highlights, natural shadows, premium fashion-editorial photography, realistic anatomy, highly detailed, photorealistic.
IMPORTANT: Preserve the uploaded person's face accurately. Do not change the identity. Keep the neck normal length and natural thickness. No stretched neck, no warped face, no oversized head, no unnatural body proportions. Vertical portrait composition, realistic camera perspective.
Negative prompt: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。
