聊天GPT
兩條路，一個影子
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：1,241 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
Create a vertical 4:5 photograph featuring two appearances of the same man from the reference image.
On the left, show a larger figure walking toward the camera, with both hands in his pockets and his head gently lowered. On the right, show a smaller figure walking away with his back facing the camera.
Both figures wear a burnt-orange zip-up hoodie with the hood raised and very wide light-wash jeans. Under the hood, preserve the natural proportions and recognizable facial features of the reference: the face width, nose, mouth, and jawline. A soft cream-colored light reflection subtly reveals part of the facial features within the shadows.
Construct a unified environment in petroleum blue and cream, creating depth between the two figures. Blend both moments together using optical blur, diffused light around the edges, soft mist near the legs, and fine film grain.
The texture should resemble a printed photograph, with no rigid separation between the two exposures.
Preserve the person's recognizable identity, natural facial features, body proportions, and clothing details from the reference image.
Vertical 4:5, experimental photography, analog photographic texture, cinematic atmosphere, soft diffusion, double exposure.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。
