OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
熔金密室中的超现实高级时装肖像
Surreal High-Fashion Portrait in a Molten Gold Chamber
固定身份参考中的成年女性置身于以树脂和涂层搭建的琥珀金色实景布景，穿着不透明、具有液态金属垂坠感的前卫礼服；以可调顺时针倾斜构图和强烈明暗对比表现超现实奢华。
提示词 / Prompt
中文提示词
创作一张超现实高级时装社论肖像，竖版4:5构图。使用已配置身份参考图ref-10a-v1作为唯一一位成年女性的身份依据，保留她可辨识的身份，不要暗示附加了其他参考图。场景是一间触感鲜明、搭建出来的“黄金密室”：墙壁和表面涂覆浓稠琥珀金色树脂与金属漆，视觉上如蜂蜜般粘稠、缓慢滴落。这是安全的实景布景效果，不是真实高温或危险液体。女性略偏离画面中心，处于脆弱、内省的一刻，低垂目光并略微转开，肩部轻轻下沉。她穿着前卫高级定制礼服，呈半透明金属金色观感，但以不透明布料表现出湿润金属般的垂坠光泽，视觉上仿佛融入布景，同时不暴露身体。搭配克制的熔金树脂感超现实珠宝，不出现可辨识的设计师标志。采用明显的顺时针倾斜角25 degrees clockwise和倾斜地平线构图，人物偏置，周围留出充满质感的负空间。使用刺眼的定向硬光和极少补光，形成深邃锐利的阴影及树脂表面明亮但受控的镜面高光；同时保留清楚的面部细节和自然肤质。氛围沉重、仿佛潮湿、金属感强而奢华，加入克制的高光晕和边缘轻微色差。追求有触感的中画幅时尚摄影写实感，而非CGI。不要其他人物、文字、标志或水印。
English prompt
Create a surreal high-fashion editorial portrait in a vertical 4:5 frame. Use configured identity reference ref-10a-v1 for the single adult woman, preserving her recognizable identity; do not imply another reference is attached. Set the scene in a tactile, constructed Gold Room: walls and surfaces are coated with thick amber-gold resin and metallic paint that look viscous and slowly dripping, like heavy honey. This is a safe practical set effect, not real hot or hazardous liquid. Place the woman slightly off-center in a fragile, introspective moment, gaze lowered and turned away, shoulders gently sloped. She wears an avant-garde couture gown in translucent-looking metallic gold, rendered as opaque fabric with a glossy wet-metal drape that seems to visually merge with the set without exposing the body. Add restrained surreal molten-gold resin jewelry, with no identifiable designer logo. Compose with a pronounced clockwise Dutch angle of 25 degrees clockwise and a tilted horizon, leaving textured negative space around her. Use a hard directional spotlight, minimal fill, deep sharp shadows and bright controlled specular highlights across the resin; preserve readable facial detail and natural skin texture. The atmosphere is heavy, humid-looking, metallic and opulent, with subtle halation and slight edge chromatic aberration. Aim for tactile medium-format editorial realism, not CGI. No extra people, text, logos or 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
- 暗黑大肥鱼
整体基调：东方史诗神话灾难大片质感，暗黑恶魔动漫爆发感融合好莱坞写实CG，UE5电影渲染，HDR光追，真实物理，强烈黑金色侧逆光，深红体积沙尘与恶魔烟尘，电影景深，动态运动模糊，节奏干脆迅猛，黑红金主色，地狱化战场氛围。 图1锁定角色：蓝渐变长卷发，头顶呆毛，鲸鲨鱼耳，鲸鲨长尾，女仆裙装，白色围裙，围裙印有小鲸鱼图案，Q版比例。角色造型保持不变，但整体气质改为暗黑恶魔审判者感，表情冷冽、嘲弄、残忍，动作像恶魔刽子手执行处刑。 图2锁定巨型黑黄条纹甲壳虫王，巨口獠牙、尖刺前爪、虫群头领气质。 图3只用于冲击帧视觉语言【严格遵循Impact Frame规则】：冲击帧不是连续动画，不是撕裂米粒
- 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