OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

俯拍台球室中的成年女性动态肖像

Dynamic portrait of an adult woman in a billiard room from above

9:16写实动态肖像，明确成年的原创女性在暗色木质台球室靠在球桌边缘，以俯拍视角呈现自然平衡姿态和桌面细节。

俯拍台球室中的成年女性动态肖像 — AI image creation
俯拍台球室中的成年女性动态肖像

提示词 / Prompt

中文提示词

9:16纵向照片级写实动态肖像，一位明确成年的原创女性使用人物参考 ref-10a-v1，站立时下背部轻靠经典台球桌侧边，身体向后形成戏剧性的但安全自然的扭转，上身和头部抬起，直视高处俯拍镜头；左臂向下伸展，左手掌平放在绿色台呢上保持平衡，手指自然分开，右臂沿躯干曲线放置。她有深色长波浪发和自然无妆皮肤纹理，穿不透明的无袖灰紫色高领上衣、利落的深色长裤和舒适的平底鞋，服装无logo、无文字、无品牌。场景为昏暗的经典深色木饰面台球室：球桌为绿色台呢与深色木质桌沿，桌面放着一根抛光木质球杆，附近有红白条纹球和黄色球；桌面、球杆、木质边框和球体的反光准确呈现高角度闪光与人物轮廓。使用高处斜向单点硬闪光，形成台呢上的清晰阴影、皮肤和眼睛上的受控高光与轻微边缘暗角；5500K日光平衡，约35mm广角观感、f/2.8、ISO 160、8K级细节。保持自然闭口中性表情，不露牙、不微笑、不化妆、不美颜磨皮；排除纹身、豹纹、额外肢体、扭曲手指、品牌logo、可读文字和伪影。

English prompt

Vertical 9:16 photorealistic dynamic portrait of one clearly adult original woman using character reference ref-10a-v1. She stands with her lower back lightly supported against the side edge of a classic billiard table, creating a dramatic but safe natural twist with her upper torso and head lifted toward a high-angle camera; her left arm extends downward with the palm flat on the green felt for balance and naturally splayed fingers, while her right arm follows the curve of her torso. She has long dark wavy hair and natural unmade skin texture, and wears an opaque sleeveless mauve high-neck top, tailored dark trousers, and comfortable flat shoes, all without logos, lettering, or brands. Set the scene in a dim classic billiard room with dark wood paneling: green felt, dark mahogany rails, a polished wooden cue lying horizontally on the table, and nearby red-and-white striped and yellow billiard balls. All reflective surfaces must accurately show the high-angle flash and the subject silhouette without distortion. Use a single hard oblique overhead flash creating defined shadows on the felt, controlled highlights on skin and eyes, and slight edge vignetting; daylight-balanced 5500K, approximately a 35mm wide-angle look, f/2.8, ISO 160, and 8K-level detail. Keep a closed-mouth neutral expression with no teeth, smile, makeup, or beauty smoothing. Exclude tattoos, leopard patterns, extra limbs, distorted fingers, brand logos, readable text, and generative artifacts.

查看 API 模型

探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作

  • 特斯拉电动车核心部件示意全景

    横向概念示意海报：以未指定车型的特斯拉电动车为中心，周围安排若干模块放大细节。电池包、电驱电机、逆变器/电力电子、车载充电器、热管理回路、悬架与制动、充电接口均为整理者选定的示意模块，不是来源列明的清单，也不代表特定车型布局或工程规格。 / A landscape conceptual overview centered on a Tesla EV of unspecified model, surrounded by selected module detail callouts. Battery pack, drive motor, inverter/power electronics,

  • 日系负片里的记忆碎片

    A 9:16 candid Japanese negative-film style portrait. The adult person, unposed walk and quiet neighborhood lane are replaceable curator-selected defaults, not subject or scene details supplied by the source. The currently configured ref-10a-v1 is used as the generic person identity reference and is

  • 1girl

    gpt image2.5生成

  • 法式风情地标美食海报

    A premium, clean and elegant poster concept built from the source’s broad request. Eiffel Tower, Arc de Triomphe, ratatouille and Provençal bouillabaisse are curator-selected illustrative examples, not details stated by the source; they can be replaced in a future variant. The source example image i

  • 梦回江户浮世绘古典人物像

    A reference-led Edo-period ukiyo-e portrait transformation that preserves the supplied person’s facial identity while restyling hair, clothing and accessories in traditional Japanese fashion. The current ref-10a-v1 is the generic person preview for this workflow, not a claim about any external named

  • 盛世长安万国来朝图

    A text-driven historical reconstruction of the source scene: an aerial view of Kaiyuan-era Chang’an, Emperor Xuanzong and Yang Guifei looking out from Hanyuan Hall, and a distant tribute procession. The configured generic portrait is used only as a face-identity anchor for Yang Guifei in this genera