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

夏日网球成年男性运动时尚肖像

Summer Tennis Adult Male Sport Fashion Portrait

单独成片的3:4竖幅动态网球运动时尚肖像，保留人物身份、夏日蓝场、真实动作与无品牌约束。

夏日网球成年男性运动时尚肖像 — AI image creation
夏日网球成年男性运动时尚肖像

提示词 / Prompt

中文提示词

基于上传的清晰单人人像参考，使用人物参考绑定 ref-10a-v1，创作一张单独成片的3:4 竖构图，呈现一位明确成年的男性网球运动员在蓝色网球场上进行真实的正手挥拍动作。严格保持参考人物的真实五官、脸型、肤色、年龄感、发际线和整体辨识度，不换脸、不变成陌生人；保留真实皮肤纹理、自然比例、健康匀称体态和清晰运动表情。人物穿清爽的奶油白网球polo、浅灰运动短裤、白袜和复古网球鞋，佩戴简洁护腕或吸汗发带，不出现品牌 logo。采用接近全身的动态构图，球拍、握拍手势、肩颈线、双腿和脚步关系完整可见，身体重心自然，动作有力量但不过度夸张。场景包含蓝色网球场、网球网、白色边线、少量散落网球、球筐、蓝天和围网；使用明亮夏日硬光、自然阴影和少量正面补光，画面真实、清爽、带细微胶片感，兼具高预算运动时尚大片和男性杂志编辑质感。只生成这一张独立照片，不做拼贴或多图排版。避免站桩摆拍、健身房风、油腻耍帅、空洞眼神、奇怪肢体、畸形手脚、错误透视、变形球拍、文字水印和品牌 logo。

English prompt

Based on the uploaded clear single-person portrait reference, use the person-reference binding ref-10a-v1 to create one independent image in 3:4 vertical composition: a clearly adult male tennis athlete performing a real forehand swing on a blue tennis court. Strictly preserve the reference subject's real facial features, face shape, skin tone, age appearance, hairline and overall recognizability; no face swap or stranger identity. Keep realistic skin texture, natural proportions, a healthy balanced build and a focused but natural expression. Dress him in a fresh cream-white tennis polo, light-grey sports shorts, white socks and vintage tennis shoes, with a simple wristband or sweatband; no brand logos. Use a near-full-body dynamic composition with racket, grip gesture, shoulders and neck, legs and grounded footwork fully visible; weight distribution should feel athletic and natural, powerful but not exaggerated. Set the scene on a blue tennis court with a net, white sidelines, a few scattered tennis balls, a ball basket, blue sky and fence. Use bright summer hard light, natural shadows and a small amount of front fill, with a bright realistic image and subtle film feel combining high-budget sports-fashion advertising and men's magazine editorial quality. Render this as one independent photograph only, not a collage or multi-image layout. Avoid static posing, gym-style posing, greasy forced coolness, hollow eyes, strange limbs, deformed hands or feet, incorrect perspective, distorted racket, text watermarks or brand logos.

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