OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
雨中京都喫茶店怀旧人像与手帐插画
Nostalgic Portrait and Journal Illustration at a Kyoto Café in the Rain
雨中京都复古喫茶店的怀旧女性肖像，可切换为同主题的水彩铅笔手帐插画。
提示词 / Prompt
中文提示词
以用户上传的参考图作为主要可见人物的面部身份依据。在不与身份参考冲突的情况下，保留来源的场景、造型、服装、姿势、构图、光线和视觉风格。 创作一幅雨日京都复古喫茶店中的温暖怀旧场景。一位明确成年的女性，面部身份依据 ref-10a-v1，坐在轻轻起雾的窗边，手捧一杯陶瓷杯装抹茶拿铁。她留短款波浪波波头，穿米色宽松针织开衫和长款格纹裙。呈现真实木质室内、复古灯具、摆有精致甜点与杯具的木桌，以及窗外朦胧可见的雨中京都街道。采用温暖琥珀色灯光、柔和棕褐与暖米色调、亲密取景、自然皮肤纹理和柔和浅景深。 渲染方式设为photoreal café portrait，只使用所选方式，不要混合。选择“写实咖啡馆肖像”时，呈现电影感写实生活方式时尚摄影；选择“水彩手帐插画”时，将同一成年女性、服装、咖啡馆场景与雨窗绘制成水彩加铅笔手绘手帐页面，可加入雅致的咖啡涂鸦、箭头、邮票形贴纸和日式手写风格小字作为装饰符号，但不编造特定文案或添加标志。面部可采用柔和动漫式简化，但不得仿制具名工作室风格。保持温馨细腻；不得出现其他可辨认人物、凭空编造的可读文字、标志或水印。
English prompt
Use the uploaded reference image as the facial identity reference for the main visible person. Keep the source scene, styling, clothing, pose, composition, lighting and visual style unless they conflict with the identity reference. Create a cozy nostalgic scene inside a traditional vintage Kyoto kissaten on a rainy day. One clearly adult woman matching ref-10a-v1 sits beside a softly fogged window, holding a ceramic cup of matcha latte. She has a short wavy bob and wears a cream oversized knit cardigan with a long plaid skirt. Show authentic wooden interiors, retro lamps, a wooden table with carefully rendered café desserts and cups, and a rainy Kyoto street softly visible outside. Use warm amber light, muted sepia and warm-cream tones, intimate framing, natural skin texture and gentle shallow depth of field. Set the rendering treatment to photoreal café portrait and use only that treatment, not a mixture. For “photoreal café portrait,” create realistic cinematic lifestyle fashion photography. For “watercolor journal illustration,” create a hand-drawn watercolor-and-pencil journal page with the same adult woman, outfit, café scene and rainy window; include tasteful café doodles, arrows, postage-stamp-like stickers and small handwritten Japanese-style notes as decorative marks only, without asserting exact wording or adding logos. Use soft anime-inspired facial simplification without copying a named studio. Keep the scene cozy and detailed, with no other identifiable people, no legible invented text, no logos, and no 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