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

棒球直播看台自然抓拍

Natural Candid Shot of Baseball Live Stands

使用固定身份参考的成年女性坐在棒球观众席中,由远处长焦直播机位自然捕捉,呈现混合观众、通用记分牌与轻微电视转播质感。

棒球直播看台自然抓拍 — AI image creation
棒球直播看台自然抓拍

提示词 / Prompt

中文提示词

使用已配置的身份参考图ref-10a-v1绑定画面中明确成年的女性,并保留其可辨识身份。创作一张虚构棒球比赛的真实感电视直播看台抓拍:远处看台机位以长焦拍摄,她坐在观众席中,身体略微后靠,目光转向一侧,呈现刚注意到镜头时自然、轻微惊讶的神情;嘴唇可以自然微启,不要夸张。她穿完整、不透明、宽松合身的棒球风上衣和牛仔裤;上衣保持正常衣长,不塞成短款、不卷起或打结。姿势放松,一只手臂搭在座椅或腿上。周围是构成自然、穿着多样的成年观众,包括不同球衣、素色衬衫和夹克,背景轻微虚化。构图为不完美的远距离电视长焦截帧,不是自拍、特写或纯侧面人像。画面上角加入小型虚构赛事转播记分牌,准确显示可读标签“HOME”和“AWAY”,并以简洁字段呈现局数、得分、安打和失误;不要出现真实联盟、球队名称、标志、队服或品牌化图形。使用明亮球场照明、轻微转播压缩感和克制数字噪点,同时保留自然皮肤纹理与真实直播构图。不要磨皮,不要刻意强调女性身体,不要水印或无关可读文字。

English prompt

Use configured identity reference ref-10a-v1 for the clearly adult woman featured in this scene and preserve her recognizable identity. Create a realistic, fictional live baseball broadcast crowd shot from a distant telephoto camera in the stands, with the woman seated among stadium spectators, leaning slightly back and glancing off to one side with a naturally surprised, just-noticed-the-camera expression; her lips may be gently parted, not exaggerated. She wears a complete opaque, relaxed-fit baseball-style jersey and jeans, with the jersey full length, untucked and not rolled or tied. Keep her pose casual, one arm resting on the seat or her lap. Surround her with a mixed, natural crowd of adult fans in varied jerseys, neutral shirts and jackets, softly out of focus. Frame as an imperfect long-lens television capture rather than a selfie, close-up or profile shot. Include a small generic fictional broadcast scoreboard in the upper corner with the exact readable labels “HOME” and “AWAY” and simple inning, runs, hits and errors fields; use no real league, team names, logos, uniforms or branded graphics. Add bright stadium lighting, subtle broadcast compression and restrained digital noise while preserving natural skin texture and realistic live-TV framing. No beauty smoothing, extra emphasis on the woman's body, watermark or unrelated readable text.

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

  • 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

  • 威震天高定西装时尚大片

    A text-driven fashion-cover portrayal of Megatron, retaining the source's silver-gray mecha, haute-couture suit and cyberpunk neon setting; it does not claim an exact adaptation-specific design. / 依据文字创作的威震天时尚封面,保留银灰机甲、高定西装与赛博朋克霓虹场景;不声称复现某一改编版本的精确造型。

  • 黑木崖红衣飞针傲立悬崖

    An original cinematic wuxia interpretation of the named fictional character, preserving the source's flying embroidery needles, red clothing, long hair, Heimuya cliff and blood-red sunset. The configured generic portrait is used only as the required face identity anchor, not as a canonical character

  • 李佳琦口红矩阵直播间背景

    A fictional, unoccupied livestream-commerce background with a lipstick matrix display wall, warm ambient lighting and the source's exact English visible copy. It does not claim to reproduce Li Jiaqi's actual studio. / 虚构的无人直播带货背景,包含口红矩阵展示墙、暖光氛围灯与来源要求的准确中文可见文案;不声称复刻李佳琦的真实直播间。