OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
生活速写手绘涂鸦分格拼贴狗狗
Life Sketch Hand-Drawn Doodle Grid Collage Dog
A bright segmented collage of the dog in reference image 1, using candid variations, soft photographic texture, clean white gutters, and playful near-white hand-drawn annotations.
提示词 / Prompt
中文提示词
围绕参考图1中的同一只狗狗，制作明亮的连续分格生活速写簿拼贴。将许多近距离小画面排成有节奏的网格，画面之间用均匀、干净的白色边界分隔。每一格都保留狗狗可辨认的一致外观、柔和真实影像质感和轻微胶片颗粒，并通过不同角度、表情、局部裁切、俏皮遮挡、动作和与狗狗相关的行为制造自然变化。直接在真实照片上叠加厚度不均的近白手绘线条，像随手涂鸦：勾勒狗狗轮廓、耳朵、爪子、项圈或道具，围绕头部并延伸到空白区域，生成源自狗狗的小图标、情绪符号、松散短手写标记和夸张轮廓。第一眼应读到清爽分格与手绘注释之间的俏皮互动。背景保持浅亮、通风、简洁，为线条留下足够干净空白。文字只作为松散的手写情绪节奏，绝不承担说明信息。色彩从狗狗自身的材质、情绪和故事中提取：大面积明亮干净底色、柔和低饱和主体色、清晰明暗结构、仅在小物件或符号上少量强调色，以及近白信息线。整体保持明亮、清透、洁净，避免厚重阴影、浑浊滤镜、杂乱背景和过度装饰。
English prompt
Create a bright continuous segmented collage centered on the dog in reference image 1. Arrange a rhythmic life-sketchbook grid of small close-up frames separated by uniform clean white gutters. In every frame keep the same recognizable dog with soft real-image texture and slight film grain, shown in relaxed candid variations: different angles, expressions, partial crops, playful obstructions, gestures, and dog-specific actions. Overlay near-white hand-drawn lines of uneven thickness directly on the photographs, like spontaneous graffiti: trace the dog's silhouette, ears, paws, collar or props, extend lines around the head and through blank areas, and form small dog-derived icons, emotional symbols, short loose handwritten marks, and exaggerated contours. The first-read effect should be the playful interaction between fresh photographic segments and doodle annotations. Keep the background light, airy, and simple with enough clean white space for the lines. Any lettering is only a loose emotional handwritten rhythm, never instructional. Extract colors from the dog's material, emotion, and story: large clean high-brightness base colors, soft low-saturation dog colors, clear light-dark structure, sparse accent colors on small objects or symbols, and near-white information lines. Keep the overall image bright, clear, and clean; avoid heavy shadows, muddy filters, cluttered backgrounds, or dense decoration.
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
- 最喜欢的角色进食动作
Add a food-specific eating action to the character in the configured reference image. Food is editable; defaults to a strawberry. The source mentions Nano Banana as its tool context. / 为配置参考图中的角色添加指定食物的进食动作；食物可编辑，默认一颗草莓。来源将 Nano Banana 作为工具语境提及。
- 橘红光影下的电影感极简人像
A photorealistic 4:5, 2K studio portrait with a fitted matte-black pique polo, serious upward off-camera gaze, low-angle face-and-shoulders framing, orange-red gradient, dramatic shadows and rim light. / 4:5、2K 逼真影棚人像：哑光黑色珠地棉 Polo 衫、严肃且略向上的镜头外视线、低角度面部与肩部构图、橙红渐变背景、戏剧性阴影与轮廓光。
- 红夹克女子四场景系列
以同一位黑色短发、带雀斑、穿红夹克的年轻女子为主角，分别呈现城市、海滩、山脉和夜街四个环境；每张单独成图，并使用同一固定身份参考保持人物一致。
- 吃西瓜的古怪年轻女性手绘编辑插画
一位古怪的年轻成年女性在厨房桌旁吃西瓜，呈现半写实、松散有质感的传统手绘编辑插画；保留指定的发型、服装、姿势、神情、色彩和素描本质感。
- 黑曜石玻璃悬浮全息幻彩产品摄影
以可替换产品为主体，置于纯黑空间中居中悬浮；用黑曜石玻璃质感、内部体积辉光、焦散折射与强烈虹彩表现全息幻彩效果。示例默认值为掌上游戏机。
- Fenty Beauty 五封邮件营销序列视觉模板
将来源中的邮件序列请求整理为一张五栏视觉营销邮件模板板，保留欢迎、品牌理念、畅销产品、社交证明与首单优惠五个阶段及参考图中的美妆风格和主要文案。中英文提示词等义，优惠变量带有可复用默认值，并绑定工作流指定的人像参考。