OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
电影感4:3超近景东亚成年女性深情凝视
Cinematic 4:3 Extreme Close-Up of an East Asian Woman's Intense Gaze
A cinematic horizontal 4:3 ultra-close portrait of a clearly adult East Asian woman leaning toward the camera. Long, slightly tousled center-parted black hair frames steady bright eyes; soft indoor light and realistic skin texture support a quiet, affectionate expression.
提示词 / Prompt
中文提示词
创作一张电影感的4:3横幅超近景人像：一位明确27岁的东亚成年女性轻轻低头并向镜头靠近。仅使用已配置的固定参考ref-10a-v1绑定她的面部身份；不要照搬参考图的姿势、发型、服装或场景。她的脸几乎占满画面。构图从发际线上方延伸至上唇处的画面下缘：清楚呈现额头、双眼、鼻梁和微微前噘的嘴唇上部，画面下缘从上唇处裁切，下唇与下巴留在画外。她留微乱的黑色长发并自然中分，脸颊两侧垂下几缕纤细发丝。她明亮的双眼稳定望向镜头，眼睑与眉毛放松，没有敌意或戒备，传达安静、专注、柔和而深情的迷恋感。神情温柔、非情色化，嘴唇仅轻微前噘。采用室内柔和电影光、浅景深、真实皮肤纹理与可见毛孔，呈现自然抓拍般的电影静帧质感。保持面部比例自然、高光克制。避免身份改变、攻击性或痛苦表情、夸张妆容、过度磨皮、文字、标志或水印。
English prompt
Create a cinematic horizontal 4:3 ultra-close portrait of one clearly adult 27-year-old East Asian woman leaning gently down and forward toward the camera. Bind her facial identity only to the configured fixed reference ref-10a-v1; do not copy the reference's pose, hairstyle, clothing or setting. Her face fills nearly the entire frame. Compose from just above the hairline to a lower edge that cuts through the upper lip: show the forehead, both eyes, nose bridge and only the upper portion of her softly pouting lips; keep the lower lip and chin outside the frame. Her long black hair is slightly tousled with a center part, and a few fine strands fall along both sides of her face. Her bright eyes look steadily into the lens, with relaxed eyelids and brows, no hostility or defensiveness, conveying a quiet, focused and affectionate romantic infatuation. Keep the expression gentle and nonsexual, with lips only slightly pursed. Use soft indoor cinematic light, shallow depth of field, realistic skin texture and visible pores, and a candid cinematic still quality. Maintain natural facial proportions and restrained highlights. Avoid altered identity, aggressive or distressed expression, exaggerated makeup, excessive skin smoothing, text, logos or watermark.
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
相关作品
- 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