OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

早餐咖啡馆中的多媒介人物

Multimedia Figures in a Breakfast Café

繁忙的早餐咖啡馆以真实摄影为基底，前景出现蓝发动漫男性，另有铅笔素描人物与黏土动画人物；三种媒介在同一日常场景中清晰区分又自然共存。

早餐咖啡馆中的多媒介人物 — AI image creation
早餐咖啡馆中的多媒介人物

提示词 / Prompt

中文提示词

创作一张日常感的繁忙早餐咖啡馆照片。前景突出一位明确成年的蓝发动漫风格男性，其面部身份以固定参考ref-10a-v1为准。同一构图的其他位置再出现两位明确成年的角色形象，也以ref-10a-v1作为身份依据，但分别采用截然不同的媒介表现：一位呈现在纸面上的铅笔素描人物，另一位呈现为有真实黏土质感的定格动画人物。三位形象在空间上彼此区分，动漫、铅笔绘画和黏土动画的表现方式一目了然；咖啡馆、桌椅、早餐服务和周围顾客则保持自然的摄影写实感。使用可信的清晨窗光、层次丰富的咖啡馆纵深和轻微忙碌感，建立清晰的视觉层级，使蓝发动漫男性成为前景焦点。让不同媒介自然融入场景，同时保留各自的材质特征。不要增加其他重点角色、改变来源指定的三种人物表现、添加文字或标志，也不要把整间咖啡馆变成插画。

English prompt

Create a candid-looking photograph of an everyday breakfast scene in a busy cafe. In the foreground, feature one clearly adult blue-haired anime-style man, with his face identity guided by fixed reference ref-10a-v1. Elsewhere in the same composition, include two additional clearly adult character depictions, each also identity-bound to ref-10a-v1 but rendered in distinct media: one as a visible graphite-pencil sketch figure on paper and one as a tactile claymation figure. Keep the three figures spatially distinct and make the anime, pencil-drawing and claymation treatments unmistakable, while the cafe, tables, breakfast service and surrounding patrons remain grounded in natural photographic realism. Use believable morning window light, layered cafe depth, subtle activity and a readable focal hierarchy so the blue-haired anime man remains the foreground focus. Blend the different media cleanly into the scene without obscuring their material qualities. Do not add other featured characters, change the source's three specified depictions, introduce text or logos, or turn the whole cafe into an illustration.

查看 API 模型

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