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

写实夏日汉服奇幻女主角肖像

Realistic Summer Hanfu Fantasy Heroine Portrait

A vertical photorealistic fantasy portrait of an adult woman in tasteful summer hanfu-inspired clothing, reaching toward the camera in a sunlit outdoor setting with wind-blown silk and gauze details.

写实夏日汉服奇幻女主角肖像 — AI image creation
写实夏日汉服奇幻女主角肖像

提示词 / Prompt

中文提示词

创作一幅 vertical 9:16 的超写实中国奇幻肖像,表现一位优雅的成年女性夏日汉服灵感女主角。她拥有乌黑长发、自然皮肤、富有表现力的眼睛和真实优雅的气质。将她置于a sunlit summer garden beneath flowering trees,环境有明亮夏日阳光、开阔天空、树木、微风和电影感户外氛围。采用低角度第一人称视角与 28–35mm wide-angle portrait look。她正面面对镜头,从上方略微向前倾斜并直接进行眼神交流;one hand reaches directly toward the camera,仿佛温柔邀请观者牵手。保持正面姿势,不要回身或侧身。让她穿得体的夏日汉服灵感奇幻服装,带结构化腰带、不透视的层叠裙摆、优雅领口与肩颈线、飘逸披帛、半透明但不暴露的薄纱袖子,以及真实丝绸、刺绣、缎带和自然褶皱。轻盈透气但保持精致覆盖。风吹动她的头发、披帛、袖子和裙边;阳光捕捉发丝与面料边缘,形成空灵轮廓光。皮肤、手部、手指和人体结构真实自然,服装符合物理规律,背景柔和而有细节。避免 CGI、插画、未成年外观、幼稚化造型、塑料皮肤、假发质感、僵硬姿势、厚重冬装、廉价服装感、庸俗暴露、坏手、多余或缺失手指、融合手指、折断手腕、过大手部、模糊面部和扭曲背景。

English prompt

Create a vertical 9:16 photorealistic Chinese-fantasy portrait of one adult woman as an elegant summer hanfu-inspired heroine. She has long black hair, natural skin, expressive eyes and a graceful realistic presence. Place her in a sunlit summer garden beneath flowering trees with bright summer sunlight, open sky, trees, gentle wind and a cinematic outdoor atmosphere. Use a low-angle first-person POV with a 28–35mm wide-angle portrait look. She faces the camera directly, leans slightly forward from above and makes direct eye contact; one hand reaches directly toward the camera as if gently inviting the viewer to take her hand. Keep the pose front-facing, never turned away or side-facing. Dress her in a tasteful summer hanfu-inspired fantasy outfit with a structured waist sash, opaque layered skirt, elegant collar and shoulder line, flowing pibo scarves, translucent but non-revealing gauze sleeves, silk, embroidery, ribbons and natural folds. Balance light breathable summer layers with refined coverage. Wind lifts her hair, scarves, sleeves and skirt edges; sunlight catches the hair and fabric edges to create airy rim light. Photorealistic skin, natural hands and fingers, credible anatomy, realistic fabric physics and a softly detailed background. Avoid CGI, illustration, underage appearance, childish styling, plastic skin, synthetic wig hair, stiff pose, heavy winter costume, cheap costume look, vulgar exposure, bad hands, extra or missing fingers, fused fingers, broken wrists, oversized hands, blurry face and distorted background.

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

  • 暗黑大肥鱼

    整体基调:东方史诗神话灾难大片质感,暗黑恶魔动漫爆发感融合好莱坞写实CG,UE5电影渲染,HDR光追,真实物理,强烈黑金色侧逆光,深红体积沙尘与恶魔烟尘,电影景深,动态运动模糊,节奏干脆迅猛,黑红金主色,地狱化战场氛围。 图1锁定角色:蓝渐变长卷发,头顶呆毛,鲸鲨鱼耳,鲸鲨长尾,女仆裙装,白色围裙,围裙印有小鲸鱼图案,Q版比例。角色造型保持不变,但整体气质改为暗黑恶魔审判者感,表情冷冽、嘲弄、残忍,动作像恶魔刽子手执行处刑。 图2锁定巨型黑黄条纹甲壳虫王,巨口獠牙、尖刺前爪、虫群头领气质。 图3只用于冲击帧视觉语言【严格遵循Impact Frame规则】:冲击帧不是连续动画,不是撕裂米粒

  • 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