Thư viện prompt AI OpenZhenZhen · gpt-image-2.5 · image

Chân dung tĩnh trong đám đông ồn ào

Still Portrait in a Noisy Crowd

Chân dung tĩnh trong đám đông ồn ào — khám phá tác phẩm được tạo bằng gpt-image-2.5 trên OpenZhenZhen, kèm prompt gốc và ví dụ tạo nội dung để tham khảo.

Chân dung tĩnh trong đám đông ồn ào — AI image creation
Chân dung tĩnh trong đám đông ồn ào

Prompt

Prompt tiếng Trung

以用户上传的参考图作为主要可见人物的面部身份依据。在不与身份参考冲突的情况下,保留来源场景、姿势、构图、光线和视觉风格。 创作一张电影感人像:主角为同一位明确25岁或以上的成年人,静立于繁忙的步行广场中央,周围及身后有不同人群走动。仅使用ref-10a-v1保持其可见面部身份,不推断个人经历或其他属性。人物保持比例自然、清晰对焦,神情沉静内省并直视镜头。周围行人以长曝光运动模糊及流动轨迹呈现,形成静止主体与流动人群的鲜明对比。采用柔和漫射的自然日光、浅景深和中性柔和的粉彩色调,并辅以细腻电影感调色。呈现压缩感85毫米人像视角,同时保持主体清晰、移动人群柔和拖影。整体是梦幻而写实的电影摄影与情绪叙事构图,保留自然细腻的皮肤质感。不要未成年人、抢占肖像焦点的前景人物、文字、Logo、水印或扭曲解剖结构。

Prompt tiếng Anh

Use the uploaded reference image as the facial identity reference for the main visible person. Preserve the source scene, pose, composition, lighting and visual style unless they conflict with the identity reference. Create a cinematic portrait of the same clearly adult person, age 25 or older, standing still at the center of a busy pedestrian plaza with a diverse crowd moving behind and around them. Use ref-10a-v1 only to preserve visible facial identity; do not infer biography or other personal attributes. Keep the subject sharply focused with natural proportions, looking directly at the camera with a calm, introspective expression. Surround them with passersby rendered as long-exposure motion blur and flowing movement streaks, creating a clear contrast between stillness and movement. Use soft, diffused natural daylight, shallow depth of field, and neutral pastel tones with subtle cinematic color grading. Give the portrait a compressed 85mm perspective while keeping the subject crisp and the moving crowd softly streaked. Dreamy yet realistic cinematic photography, emotional storytelling composition and detailed natural skin texture. No minors, extra foreground subjects competing with the portrait, text, logos, watermark or distorted anatomy.

Xem mô hình API

Xem thêm prompt hình ảnh và video · Tạo hình ảnh · Tạo video · Tạo trên canvas AI