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

赛车场看台情侣随拍

Couple candid at racetrack grandstand

固定身份参考中的成年女性在赛车场看台栏杆旁自然倚靠，伴侣以不露脸的局部姿态从后方亲昵相伴，呈现无文字的日光纪实照片。

赛车场看台情侣随拍 — AI image creation
赛车场看台情侣随拍

提示词 / Prompt

中文提示词

使用配置的人物参考图 ref-10a-v1，呈现前景中明确成年的女性并保持可识别的面部身份。创作一张4:5写实抓拍肖像，场景是通用现代赛车赛道看台。她站在前方，放松地倚靠金属安全栏杆；一位成年伴侣在她身后自然地将手臂环在腰间，但只露出局部肩膀和手臂，伴侣的脸和识别特征完全在画外。女性穿不透的全长红色运动圆领T恤、舒适的中腰蓝色牛仔裤和小型黑色矩形太阳镜。远处虚化显示弯曲赛道、看台和一块空白大屏，所有赛道板、横幅和标牌保持空白且不可读。使用明亮柔和日光，呈现自然、非色情的亲密抓拍；不得有徽标、赞助商品牌、可读文字、水印、露腹或其他可见人脸。

English prompt

Use configured identity reference ref-10a-v1 for the clearly adult woman in the foreground and preserve her recognizable facial identity. Create a photorealistic candid 4:5 portrait at a generic modern racing-circuit grandstand. She stands in front, leaning comfortably on a metal safety barrier; an adult partner is immediately behind her as only a partial shoulder and arm around her waist, with the partner's face and identifying features completely outside frame. Dress the woman in an opaque full-length red sporty crew-neck T-shirt, comfortable mid-rise blue jeans and small black rectangular sunglasses. Keep the top full-length and covered. Show a curving track, grandstand seating and a large blank screen in soft focus; all boards, banners and signage blank and unreadable. Bright soft daylight, casual non-sexual affectionate snapshot, no logos, sponsor branding, readable text, watermark, exposed midriff or extra visible faces.

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