OpenZhenZhen AI 프롬프트 갤러리 · gpt-image-2.5 · image
몰락한 귀족 아가씨가 옛 거리의 만두 노점 앞에 멈춰 서다
A Fallen Noblewoman Pauses at a Steamed Bun Stall on an Old Street
‘몰락한 귀족 아가씨가 옛 거리의 만두 노점 앞에 멈춰 서다’은(는) gpt-image-2.5로 만든 작품입니다. OpenZhenZhen에서 원본 프롬프트와 생성 예시를 살펴보고 새로운 창작에 활용해 보세요.
프롬프트
중국어 프롬프트
使用固定身份参考ref-10a-v1作为这位明确成年东亚女性的身份依据；不假定另有来源照片已附加。创作一张16:9的写实抓拍场景，地点在古风中国街巷。一位落难贵女身穿紫色汉服，停在蒸包子摊旁，望着蒸笼里的包子，神情饥饿又惆怅，并明显咽了咽口水。取景从脚踝以上，画面中包子摊和冒着热气的蒸笼清楚可辨。她的乌黑长发松散垂在身后，几缕发丝贴近脸颊；头部微侧，下巴略收。妆容精致而有戏剧感，呈现古典东方美：紧致椭圆脸、柔和立体的眉骨与颧骨、修长有神的深棕黑眼睛、纤细鼻梁、轮廓清晰的嘴唇，以及酒红和莓红色系妆容；同时保留真实皮肤纹理，神情沉静、微带魅力但不作挑逗。她穿多层紫色古风汉服，衣料明显破损凌乱以表现落难处境；服装不透明、穿着稳固且完整遮盖，不做透视裸露。采用自然街巷环境光、兼具电影感与纪实感的写实风格，并保留手机随手抓拍的自发感。以昔日贵气妆容、破旧衣着与渴望包子的眼神形成故事反差。不出现现代店铺元素、可读文字、标志或水印。
영어 프롬프트
Use the fixed ref-10a-v1 identity reference for the clearly adult East Asian woman; no separate source photo is presumed attached. Create a photorealistic 16:9 candid scene on an old-fashioned Chinese street. A fallen noblewoman in purple Hanfu has paused beside a steamed-bun stall, looking at the buns with a hungry, wistful expression and visibly swallowing in anticipation. Show her from above the ankles upward, with the stall and steaming baskets readable in the scene. Her long jet-black hair falls loosely behind her with a few strands near her cheeks; her head tilts slightly and her chin lowers. Give her refined, dramatic Chinese beauty styling: a compact oval face, softly sculpted brows and cheekbones, long expressive brown-black eyes, slender nose, defined lips and elegant wine-red/berry makeup, while retaining realistic skin texture and a calm, gently alluring but non-provocative expression. She wears layered purple historical Hanfu with a distressed, ragged appearance suggesting hardship; keep the garments opaque, secure and fully covering, with no sheer exposure. Use natural street ambience, cinematic yet documentary-like realism and a spontaneous mobile-phone snapshot feel. Let the contrast between her once-noble styling, worn clothing and longing look toward the buns carry the story. No modern storefront elements, readable text, logos or watermark.
더 많은 이미지·동영상 프롬프트 보기 · 이미지 생성 · 동영상 생성 · AI 캔버스에서 만들기