OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
微缩前后转变立体模型
Miniature Before-and-After Diorama
以单体抬高底座呈现主题转变前后的等距微缩3D分景，并用顶部标题、前后对比副标题和极简转变图标清晰说明变化。
提示词 / Prompt
中文提示词
创作一个清晰的微缩3D分景立体模型，展示a small urban rooftop garden / 一座小型城市屋顶花园在conversion from a bare concrete roof into a lush productive garden / 从裸露混凝土屋顶改造为繁茂且可种植的花园前后的状态。使用一个整体抬高的底座，底座为长方形，以45°俯视等距角度呈现。底座分为无缝衔接的两个环境：左侧为转变前，展示a sparse bare concrete roof with a few utility vents / 稀疏、裸露的混凝土屋顶，仅有少量通风设施；右侧为转变后，展示raised garden beds, leafy vegetables, and a compact rainwater barrel / 高架种植床、茂盛蔬菜与紧凑型雨水桶。两侧都要清楚易读，采用柔和精致的纹理、真实PBR材质和soft neutral studio illumination, balanced evenly across both halves / 柔和中性影棚光，两侧均匀平衡。确保两侧均衡柔和照明。加入微小风格化成年人物，人物可略多以强化尺度感；其身份遵循配置参考ref-10a-v1，不绘制面部细节，仅用于表现尺度和变化。底座置于干净的纯色warm light ivory / 暖浅象牙白背景上，确保干净纯色背景。顶部中央大号粗体标题为ROOFTOP GARDEN / 屋顶花园，副标题准确为：Before & After，使用中号文字置于标题下方，下方极简转变图标置于副标题下方。所有文字必须清晰可读，并根据背景文字自动采用黑白高对比，以在各自局部底色上保证易读。立体模型居中并留出整洁边距，不添加额外面板、标签、标志、杂乱装饰或水印，不加水印。
English prompt
Create a clear miniature 3D split diorama showing a small urban rooftop garden / 一座小型城市屋顶花园 before and after conversion from a bare concrete roof into a lush productive garden / 从裸露混凝土屋顶改造为繁茂且可种植的花园. Use one unified raised base, a rectangular slab, viewed from a 45-degree top-down isometric angle. Divide the slab into two seamlessly joined environments. Place before state on the left: a sparse bare concrete roof with a few utility vents / 稀疏、裸露的混凝土屋顶，仅有少量通风设施. Place after state on the right: raised garden beds, leafy vegetables, and a compact rainwater barrel / 高架种植床、茂盛蔬菜与紧凑型雨水桶. Keep both halves equally legible, with soft refined textures and realistic PBR materials. Use balanced soft lighting: soft neutral studio illumination, balanced evenly across both halves / 柔和中性影棚光，两侧均匀平衡. Add tiny stylized adult figures whose identity follows configured reference ref-10a-v1; show no facial details, and use them only to communicate scale and change. Against a clean solid background of warm light ivory / 暖浅象牙白, place a large bold title at top center: ROOFTOP GARDEN / 屋顶花园. Directly beneath it, place the exact subtitle: Before & After, in medium text; place a minimal transformation icon below. Make every text element sharply legible, with automatic white-or-black text contrast chosen for each local background. Keep the diorama centered with clean margins and no extra panels, labels, logos, decorative clutter or watermark; no 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
- 90年代冷色调仙侠风翡翠绿汉服人像
Ethereal 9:16 full-body portrait of a clearly adult Chinese woman in jade-green xianxia-inspired hanfu amid layered gauze curtains, silver ornaments, and cold teal moonlight with nostalgic 1990s fantasy-drama diffusion.
- 超精细3D漫画球星收藏级海报
Reusable 4:5 sports-memorabilia poster template for a named football player, combining a stylized likeness, current kit, chronological miniature career display, trophies, milestone props, and engraved nickname plaque.
- 复古赛车海报设计提示词
Reusable 4:5 vertical retro racing poster template with a centered front-facing car hero view, integrated geometric landscape graphics, fictional brand mark, slogan, and distressed vintage print finish.
- Q版角色聊天表情包生成指令
Reusable template for a consistent chibi chat-sticker character showing one clear emotion and action at a time, with a reserved Chinese-copy area and white or transparent background.
- 认识蜜蜂儿童科普百科海报
Colorful classroom infographic poster centered on a friendly fuzzy honey bee, with modular anatomy, life-cycle, superpower, and conservation sections in a soft cream honeycomb design.
- 时尚色块拼贴人像摄影
Premium fashion-campaign collage of five adult European models in separate rounded geometric panels, using royal blue, crimson, emerald, mustard, and white luxury color fields with clean studio flash.