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

千禧年前后一次性相机夕阳身份保留编辑

Disposable Camera Sunset Identity Preservation Edit, Circa the Millennium

An identity-preserving 4:5 edit styled as an aged late-1990s/early-2000s disposable-camera memory, with warm sunset flare, accidental framing, subtle emulsion wear, and no printed border.

千禧年前后一次性相机夕阳身份保留编辑 — AI image creation
千禧年前后一次性相机夕阳身份保留编辑

提示词 / Prompt

中文提示词

使用附带的图像作为主要面部参考，保留准确的面部结构、自然的非对称性、肤色、发型纹理和可辨识的成年身份。制作一张来自旧家庭收藏的1990年代末至2000年代初的一次性相机照片：主体占据约70–80%画面，位置略微偏离中心，在温暖的夕阳散步中转身，仿佛相机旁有人叫她的名字。保留平静梦幻的表情、自然拂过脸侧和肩膀的深色长发、长坠饰耳环，以及覆盖得体的2000年代初闪烁挂脖式上衣。一个肩膀向前倾，头部略向后仰，形成放松的非对称感而非摆拍式时装姿态。加入温暖光晕、柔和漏光、轻微荷兰式倾斜、并不完美的偶然构图，以及廉价一次性相机贴近镜头的亲密感。呈现温暖褪色肤色、提亮炭灰黑色、冲淡阴影、压缩对比度、柔化亮部、减弱饱和度、微妙青洋红老化污染、发黄灰尘、浅划痕、乳剂磨损，并仅在外缘加入微妙的灼烧损伤。让图像填满整个画面，从边缘到边缘，无冲印边框、无水印、无标志、无可读文字和无现代数字锐度；保持自然解剖且编辑内容非情色。

English prompt

Use the attached image as the main facial reference and preserve exact facial structure, natural asymmetry, skin tone, hair texture, and recognizable adult identity. Create a late-1990s to early-2000s disposable-camera photograph from an old family collection: the subject fills about 70–80% of the frame and is slightly off-center, caught mid-turn during a warm sunset walk as if someone called her name beside the camera. Preserve a calm dreamy expression, long dark hair moving across one side of the face and shoulder, long dangling earrings, and a modest early-2000s shimmering halter-style top with secure coverage. Use one shoulder angled forward and the head slightly tipped back, with a relaxed asymmetry rather than a posed fashion stance. Add warm flare, soft light leaks, a slight dutch tilt, imperfect accidental framing, and the close-to-lens intimacy of a cheap disposable camera. Render warm faded skin tones, lifted charcoal blacks, washed shadows, compressed contrast, softened highlights, weakened saturation, subtle cyan-magenta aging contamination, yellowed dust, faint scratches, emulsion wear, and minimal subtle burn damage only near outer edges. Let the image fill the entire frame edge-to-edge with no printed border, no watermark, no logo, no readable text, and no modern digital sharpness; keep anatomy natural and the edit non-explicit.

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