OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
超写实暗黑古风冷艳汉服美人四视图
Hyper-realistic Dark Ancient-Style Cold Beauty in Hanfu Four-View
A 16:9 four-view realistic portrait sheet of a clearly adult Asian woman in black-and-silver Hanfu with crystal and pearl ornament, presented as a close-up plus front, side, and back full-body views.
提示词 / Prompt
中文提示词
创作一张8K超写实的16:9四视图古风人像设定画面，表现同一位明确成年的亚洲女性，使用85mm f1.4大光圈镜头和浅景深。保留细腻自然皮肤纹理、瓜子形鹅蛋脸、冷白皮、冷调烟熏古风妆容、灰调大地色眼影、眼下细碎水钻亮片、清冷通透眼神、精致杏眼、高挺鼻梁、饱满暗调酒红唇和冷静疏离的表情。她留乌黑浓密顺直长发，梳精致古风半盘发，发丝分明，带自然碎发和细闪珠光。佩戴银质雕花发冠，镶嵌白水晶、珍珠和水钻，两侧垂挂珍珠水钻流苏步摇，并配套银质水滴珍珠流苏耳坠。她穿暗黑系露肩古风汉服，主色纯黑，带银色镶边、银色缠枝暗纹刺绣、水钻、珍珠、银饰雕花、哑光高级丝绸和薄透纱质，衣缘袖口有精致钉珠。使用纯灰暗调背景、电影级伦勃朗光、侧逆光轮廓光、柔和面部补光、强烈明暗对比和细碎星光氛围。画面左侧为上半身特写，右侧并列展示同一人物全身正面、侧面和背面三个视图。四个视图必须保持同一身份、服装、发型、饰品和光线。避免未成年、身份漂移、现代服装、过度性化、肢体扭曲、饰品不一致、面料浑浊、水印、文字和UI。
English prompt
Create an 8K hyper-realistic 16:9 four-view ancient-style portrait sheet of one clearly adult Asian woman, photographed with an 85mm f1.4 large-aperture lens and shallow depth of field. Preserve delicate natural skin texture, a melon-seed oval face, cool white skin, cold smoky ancient-style makeup, gray earth-tone eyeshadow, tiny rhinestone accents under the eyes, clear cool eyes, refined almond eyes, high nose bridge, full dark wine-red lips, and a calm distant expression. Give her thick straight jet-black hair in an elegant ancient half-updo with distinct strands, soft baby hairs, and pearlescent shine. Add a silver carved hair crown set with white crystals, pearls, and rhinestones, long pearl-rhinestone tassel hair ornaments, and matching silver teardrop pearl earrings. Dress her in dark off-shoulder ancient Hanfu, primarily pure black with silver edging, silver interlocking-branch embroidery, crystals, pearls, silver carvings, matte silk, and translucent gauze with refined beadwork at cuffs. Use a pure gray dark background, cinematic Rembrandt light, side-back rim light, soft face fill, strong light-dark contrast, and delicate star-like sparkle atmosphere. On the left show a close-up of the upper body; on the right show three side-by-side full-body views: front, side, and back. Keep the same identity, outfit, hair, jewelry, and lighting across all views. Avoid minors, identity drift, modern clothing, over-sexualization, distorted anatomy, inconsistent accessories, muddy fabric, watermarks, text, and UI.
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