聊天GPT
季風雨公園肖像拼貼
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:1,505 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 image as the PRIMARY VISUAL REFERENCE. Preserve the exact recognizable facial identity, facial structure, hairstyle, skin tone and natural body proportions of the subject. Recreate the same three-panel vertical rainy-day portrait collage in a lush city park. Panel 1: the subject stands casually in heavy rain with both hands in his pockets, wearing a black button-up shirt, grey jeans and a simple necklace. Panel 2: the subject stands under a transparent umbrella, holding the curved handle naturally while surrounded by rain and dense green trees. Panel 3: the subject walks alone along a wet park pathway lined with vintage-style lamps and benches, with reflections visible on the rain-soaked ground. Maintain the dark cinematic monsoon atmosphere, wet clothing, realistic raindrops, soft lamp glow, deep green foliage and natural overcast lighting. Keep the same clothing and hairstyle consistently across all three panels. The subject MUST look directly into the camera in every panel. Photorealistic cinematic rain photography, realistic water reflections and natural skin texture, 1122 × 1402 px, vertical.
Negative Prompt
Face distortion, wrong identity, inconsistent identity between panels, pasted face, altered hairstyle, bad anatomy, distorted hands, extra fingers, unnatural legs, warped clothing, inconsistent outfit, distorted umbrella, unrealistic rain, artificial reflections, excessive darkness, CGI look, blur, unnatural shadows, duplicated body parts, AI artifacts.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。


