OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
90年代复古报刊亭八人街头时尚大片
1990s Newspaper Eight-Person Street Fashion Editorial
八位成年时尚人物围绕复古报刊亭组成电影感群像，报纸飞扬，两辆复古踏板车与工业街景营造90年代街头编辑摄影氛围。
提示词 / Prompt
中文提示词
创作一幅电影感高时尚编辑群像，恰有八位明确成年的虚构人物聚集在一座复古都市报刊亭周围。将一位成年主模特始终绑定到已配置身份参考图ref-10a-v1；其余七位成年配角应有不同肤色和各自普通、不可识别的面孔，不要复制主模特身份。场景设在氛围化的室内都市街景布景中，包含磨损混凝土地面、深色工业墙面和克制的城市细节。报刊亭上清晰呈现唯一指定标牌文字“NEWSSTAND”。报纸以受控弧线在空中飞扬并带自然动态虚化，但不得遮挡人物面部和主标牌；其他报纸印刷内容应过小或转向背面而不可读。人物穿协调的90年代复古街头服饰——宽松夹克、层叠穿搭、帽子和墨镜——采用橄榄绿、棕色、奶油色和海军蓝。安排清楚的角色位置：一人在报刊亭旁倚靠并手持折叠报纸；一人静坐在前景奶油色复古踏板车上；另一人站在青绿色复古踏板车旁；其余五人以放松自信的姿势站立或坐在简洁椅子上。踏板车均为通用无品牌款式，所有人物保持静止安全。背景加入散落纸张和一只红色消防栓。使用柔和电影主光、温暖高光与弥散阴影，营造高级杂志编辑摄影氛围；主体清晰对焦，布料和混凝土纹理真实，胶片颗粒克制、调色自然。不要其他可读文字、标志、车辆徽章、行驶车辆、额外人物、水印或无依据的镜头/分辨率宣称。
English prompt
Create a cinematic high-fashion editorial scene with exactly eight clearly adult fictional people gathered around a vintage urban newsstand kiosk. Bind one lead adult model consistently to configured identity reference ref-10a-v1; the seven supporting adults should have varied skin tones and distinct, generic, non-identifiable faces rather than repeating the lead identity. Set the scene on an atmospheric indoor urban-street set with worn concrete flooring, dark industrial walls and restrained city details. Put the exact readable sign “NEWSSTAND” on the kiosk. Newspapers sweep through the air in controlled arcs with natural motion blur, while keeping faces and the main sign unobscured; all other newspaper print remains too small or turned away to read. Style the group in coordinated 1990s retro streetwear—oversized jackets, layered clothing, caps and sunglasses—in olive, brown, cream and navy. Compose clear role placements: one person leans at the kiosk holding a folded newspaper, one sits stationary on a cream vintage scooter in the foreground, another stands beside a teal vintage scooter, and the remaining five stand or sit on simple chairs in relaxed confident poses. Scooters are generic and unbranded; keep everyone safely stationary. Include scattered papers and one red fire hydrant against the industrial background. Use soft cinematic key light, warm highlights and diffused shadows for a premium magazine-editorial mood, with crisp subject focus, realistic fabric and concrete textures, restrained film grain and natural color grading. No other readable text, logos, vehicle badges, moving traffic, extra people, watermark, or unsupported lens/resolution claims.
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
- 1girl
gpt image2.5生成
- 【超必杀】圣光白米大肥鱼
整体基调：东方史诗神话灾难大片质感，热血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，强烈金色侧逆光，体积沙尘，电影景深，动态运动模糊，节奏干脆迅猛。 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。 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，不是撕裂米粒浪潮喷涌过程，也不是爆炸过程，而是**米粒旋风接触虫王躯干的命中顶点瞬间，强行打断正常运动、插入极短静态定格画面的视觉卡点**。冲击帧仅0.2秒，帧内无
- 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
- 威震天高定西装时尚大片
A text-driven fashion-cover portrayal of Megatron, retaining the source's silver-gray mecha, haute-couture suit and cyberpunk neon setting; it does not claim an exact adaptation-specific design. / 依据文字创作的威震天时尚封面，保留银灰机甲、高定西装与赛博朋克霓虹场景；不声称复现某一改编版本的精确造型。