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

Tỷ lệ khuôn mặt cùng một nhân vật và ảnh ghép ba phong cách nghề nghiệp

Facial proportion chart of the same character with three occupational styling collages

Tỷ lệ khuôn mặt cùng một nhân vật và ảnh ghép ba phong cách nghề nghiệp — 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.

Tỷ lệ khuôn mặt cùng một nhân vật và ảnh ghép ba phong cách nghề nghiệp — AI image creation
Tỷ lệ khuôn mặt cùng một nhân vật và ảnh ghép ba phong cách nghề nghiệp

Prompt

Prompt tiếng Trung

使用随任务提供的identity_reference ref-10a-v1，使所有画格中的人物始终是同一位明确成年女性。创作一张干净的竖幅编辑风格拼贴图，共四格，格间以细白线分隔：左侧约占三分之二宽度并贯穿全高的大幅肖像，右侧纵向堆叠三幅小图。左侧为居中对称的头部及颈部上方影棚肖像，采用清晰、高端的编辑摄影质感；叠加轻柔半透明的审美构图辅助线，包括对称轴、眼线、鼻底参考线、柔和的下颌弧线和比例引导线。它们仅是装饰性的视觉构图参考，不是医疗或生物识别分析；不显示分数、测量值、排名、身份声明或推断特质。只使用少量精致微小的英文标签：“symmetry axis”“eye line”“jaw curve”“proportion guide”。右侧三格分别表现同一女性的三种差异鲜明、虚构的职业造型：corporate strategy consultant in a contemporary office、creative art director in a bright studio和field research engineer at a clean outdoor survey site。默认造型依次为现代办公室中的企业战略顾问、明亮工作室中的创意艺术指导，以及整洁户外勘测现场的野外研究工程师。每格提供符合角色的服装、清楚的环境和一个轻松但真实的小道具或瞬间；面部应清晰可见，并保持与ref-10a-v1一致。将这些职业作为想象性的编辑造型方案呈现，不作为对人物性格、能力或真实职业的结论。采用电影感光线、浅景深、丰富但不杂乱的背景、真实高端摄影质感，并让所有画格色调统一。文字保持极少，仅在左侧大格保留上述英文辅助标签。不要真实姓名、ID、生物识别分数、额外标签、标志或水印。

Prompt tiếng Anh

Use the supplied identity_reference ref-10a-v1 as the same clearly adult woman in every panel. Create one clean vertical editorial collage with four panels and thin white dividers: a large portrait panel occupying roughly the left two-thirds, full height, and three smaller panels stacked vertically on the right. In the large panel, show a centered, symmetrical head-and-upper-neck studio portrait in crisp high-end editorial photography. Add a subtle translucent aesthetic-layout overlay with a symmetry axis, eye line, nose-base guide, gentle jaw-curve arcs and proportional guide marks. Treat these solely as illustrative design guides, not medical or biometric analysis; show no scores, measurements, rankings, identity claims or inferred traits. Use only a few tiny tasteful English labels: “symmetry axis”, “eye line”, “jaw curve”, “proportion guide”. In the three right panels, depict the same woman in three distinct, fictional career styling concepts: corporate strategy consultant in a contemporary office, creative art director in a bright studio and field research engineer at a clean outdoor survey site. Use the defaults as a corporate strategy consultant in a contemporary office, a creative art director in a bright studio, and a field research engineer at a clean outdoor survey site. Give each panel role-appropriate clothing, a clear environment and one light, realistic playful prop or moment; keep her face visibly consistent and recognizable as ref-10a-v1. Select and present these as imaginative editorial wardrobe scenarios, not as conclusions about her personality, competence or actual occupation. Use cinematic light, shallow depth of field, rich but uncluttered backgrounds, realistic premium photography and a cohesive color grade across all panels. Keep text minimal and confined to the small English guide labels in the large panel. No real names, IDs, biometric scores, additional labels, logos or watermark.

Xem mô hình API

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