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

成年日本体操选手紫色连体服竖叉人像

Adult Japanese Gymnast in Purple Leotard Doing Split

一位20岁的成年日本女性体操选手身穿浅紫色不透连体服，侧身站立完成竖叉；黑色长直发、自然红晕与明亮写实的竖幅运动人像相结合。

成年日本体操选手紫色连体服竖叉人像 — AI image creation
成年日本体操选手紫色连体服竖叉人像

提示词 / Prompt

中文提示词

创作一张写实的竖幅9:16运动时尚人像：一位明确成年的20岁日本女性体操选手。面部身份以已配置的固定参考 ref-10a-v1 为准。她有小巧的鹅蛋脸、大而灵动的眼睛、微红的脸颊和柔顺的黑色长直发，神情明快、自然俏皮，略带羞涩。身材表现均衡自然，不突出胸部、腰部、锁骨或纤瘦程度。她穿一件稳妥、不透的浅薰衣草紫色体操连体服，采用标准运动覆盖度。她侧身站立完成竖叉，动作平衡而受控，抬起的腿线条舒展，支撑腿稳定；整体是运动展示，不采用挑逗姿势。场景简洁，不让背景干扰人物动作和服装辨识；照明清晰均匀。保持成年运动员、黑色发型、浅紫色连体服、侧身方向与竖叉动作一致。呈现日本写实运动人像、自然肌肤纹理、真实人体结构与克制修饰。画面不出现文字、标志或水印。确切镜头和像素尺寸由图像工具能力决定。

English prompt

Create a realistic vertical 9:16 sports-fashion portrait of one clearly adult 20-year-old Japanese woman gymnast. Bind her face to the configured fixed identity reference ref-10a-v1. Give her a small oval face, large expressive eyes, softly flushed cheeks and long, straight black hair. Her expression is bright, naturally playful and a little bashful. Keep her athletic appearance balanced and natural, without emphasizing bust, waist, collarbones or body thinness. She wears a secure, opaque light-lavender gymnastics leotard with standard athletic coverage. Show her in a side-facing standing vertical split, balanced and controlled, with a clean line through the raised leg and stable supporting leg; keep the pose athletic rather than suggestive. Use a simple uncluttered setting and clear, even light so her pose and clothing are easy to read. Preserve the adult athlete, black hairstyle, lavender leotard, side-facing orientation and vertical-split pose. Photorealistic Japanese sports portrait, natural skin texture, realistic anatomy and restrained retouching. No text, logos or watermark. Exact lens and pixel dimensions are image-tool dependent.

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