用于将经典影视或小说作品的核心名场面生成3D轴侧微缩模型艺术图，配合叙事驱动的情绪化背景与底部作品名和经典台词排版，尺寸16:9，适合影视IP视觉化与展览级艺术创作。

中文版提示词

作品信息检索：目标作品名称为《{作品名称}》，检索该影视剧/小说的剧情、设定与叙事结构，自动筛选最具代表性的名场面或核心地点，并提取其情绪核心（如悲伤、希望、决断、重逢、毁灭、静谧等）。

主场景构建（3D轴侧微缩模型）：在画面中央呈现写实的3D微缩模型，采用轴侧视角（axonometric/isometric）；建筑细节按原作写实还原；人物动作表情符合物理与叙事逻辑；环境氛围写实呈现（暴风雨、晨雾、夕阳、火光等）；渲染风格为写实材质与光线的物理级渲染，效果如"现实场景的缩微复制品，被展览级灯光照亮"。

背景设计（叙事驱动的写实抽象空间）：禁用纯白或单色背景；基于"场景情绪核心"构建写实抽象化的情绪空间，包括情绪色调（悲伤→冷蓝灰、希望→温金光、紧张→深色对比）、空气动态与体积光（光雾、尘粒、逆光等）、轻量符号元素（花瓣、纸屑、灰烬、星尘、水纹等）、空间深度（空气透视、柔焦、渐层光线营造深邃虚空）。

底部排版（作品名+经典句子）：底部居中排版，包含中文作品名称（字体符合作品气质）与一句与该场景相关的原著描写或台词（优雅衬线体）；整体排版参考艺术博物馆铭牌，简洁、平衡、有质感。

整体视觉要求：微缩模型写实、精准、有真实材质；背景以情绪色彩、体积光与符号粒子强化叙事；全画面呈现高级展览级叙事艺术品的真实感与诗意氛围。

直接出图，尺寸16:9。

英文版提示词

Work information retrieval: the target work is titled "{work title}". Research the plot, setting, and narrative structure of this film/TV series or novel, automatically select the most representative iconic scene or key location, and extract its emotional core (e.g., sadness, hope, resolve, reunion, destruction, tranquility).

Main scene construction (3D axonometric miniature model): present a realistic 3D miniature model at the center, from an axonometric/isometric viewpoint; reproduce architectural details faithfully to the original; keep character actions and expressions physically and narratively logical; render the environment realistically (storm, morning mist, sunset, firelight, etc.); use physically-based rendering for realistic materials and light — the effect of "a miniature replica of a real scene lit by exhibition-grade lighting."

Background design (narrative-driven realistic abstract space): no pure white or monochrome background; build a realistically abstract emotional space based on the scene's emotional core, including emotional color tones (sadness → cool blue-gray; hope → warm golden light; tension → deep contrast), air dynamics and volumetric light (light fog, dust particles, backlight), lightweight symbolic elements (petals, confetti, ashes, stardust, water ripples), and spatial depth (aerial perspective, soft focus, gradient light creating a deep void).

Bottom typography (work title + classic line): centered at the bottom, with the Chinese work title (font matching the work's temperament) and one line of original description or dialogue related to the scene (in an elegant serif font); the overall typography references an art-museum plaque — simple, balanced, and textured.

Overall visual requirements: the miniature model must be realistic, precise, and have true materials; the background should enhance the narrative with emotional colors, volumetric light, and symbolic particles; the whole image should convey the realism and poetic atmosphere of a high-end exhibition-grade narrative artwork.

Output the image directly, at 16:9.

🛠️ **适用 AI 工具**：Midjourney、Stable Diffusion、DALL·E、即梦、豆包、Nano Banana