OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
瓷之息：薄纱尘埃间的忧郁成人微距肖像
Breath of Porcelain: Melancholic Adult Macro Portrait in Veil of Dust
一位明确成年女性在瓷器修复工作室中被白色薄纱轻柔围绕的超现实微距人像，聚焦单眼、织物纹理与睫毛上的陶土尘埃。
提示词 / Prompt
中文提示词
创作一张4:5超写实、超现实微距肖像，主角是一位明确成年女性，人物原型为虚构的“忧郁神童”。使用已配置身份参考图ref-10a-v1作为面部身份依据；不要声称另有上传人像。采用视线高度的极近特写，强烈聚焦单只眼睛与颧骨。流动的半透明超细白色雕塑网纱与丝绸薄纱环绕并轻柔触及面部轮廓，借鉴烟雾的雕塑般流动，同时保留清晰可触的织物纹理。薄纱可遮绕太阳穴和脸颊，但必须让鼻孔与嘴部畅通，呼吸不受阻。呈现自然细腻的毛孔，以及睫毛上微小的瓷土灰尘；她的眼神悲伤而专注，仿佛一次深呼吸凝固在时间中，头部微微后仰以迎接织物流动。场景设于拥挤的瓷器修复工作室：空气中漂浮陶瓷尘埃与棉絮，破碎白瓷、老式卡尺和修复图纸在极浅微距景深中化为柔和散景。使用穿透尘埃的温暖伦勃朗式方向光、白瓷柔和反射补光、薄纱边缘细微轮廓高光，以及面部褶皱中的深邃阴影。氛围温暖、尘土弥漫、亲密而富艺术性的幽闭感；景深极浅，眼睛与网纱织纹锐利清晰，其余部分强烈虚化。摄影器材观感参考Hasselblad H6D-100c与120mm微距镜头；竖幅4:5，眼睛偏离中心对焦，负空间由织物纹理填充。不得出现其他人物、文字、标志、水印、遮挡呼吸道的不透明织物、伤害或束缚情节。
English prompt
Create a hyperreal, surreal 4:5 macro portrait of one clearly adult woman, the fictional archetype “The Melancholic Prodigy.” Use configured identity reference ref-10a-v1 for her face; do not claim another portrait is attached. Frame an extreme close-up at eye level, focused on one eye and the cheekbone. Flowing semi-transparent ultra-fine white sculpting mesh and silk tulle sweep around and gently touch the facial contours, echoing smoke's sculptural motion while retaining a distinct tactile weave. The fabric may veil the temple and cheek but must leave the nostrils and mouth unobstructed for clear breathing. Reveal natural fine pores and tiny porcelain-clay dust on the eyelashes; her gaze is sorrowfully focused, as if a deep exhale were held in time, with her head subtly tilted back against the fabric's flow. Set the image in a dense porcelain-restoration workshop: floating ceramic dust and lint in the air, broken white ceramic fragments, antique calipers and restoration diagrams reduced to soft macro bokeh. Use a warm directional Rembrandt-style beam through dusty air, soft bounce from white ceramics, a delicate rim highlight on mesh, and deep shadows in facial folds. Warm, dusty, intimate and artistically claustrophobic mood; extremely shallow depth of field, razor-sharp eye and mesh weave, heavy blur elsewhere. Photograph-like capture reference: Hasselblad H6D-100c with a 120mm macro lens, 4:5 portrait, off-center eye focus and negative space filled by fabric texture. No other people, text, logos, watermark, opaque fabric over airway, injury or distressed restraint.
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