玩具盒中的国家立体模型

Read the complete source prompt and attribution. Titles and source text retain their original language.

GPT-4o / gpt-image-1（合集Category）Text onlyMiniature worlds

玩具盒中的国家立体Model · Source example — Upstream maintainer reproduction using Sora; not regenerated by this site.
Image credit: @jamez-bondos.Previews were resized and converted to WebP; they were not regenerated by this site.

Complete prompt

An ultra-realistic top-down photograph of a 3D-printed diorama inside a beige cardboard box, with the lid being held open by two human hands. The interior of the box reveals a miniature landscape of [COUNTRY NAME], featuring iconic landmarks, terrain, buildings, rivers, vegetation, and crowds of tiny, detailed human figures. The diorama is filled with vibrant, geographically appropriate elements, all crafted in a tactile, toy-like style using matte 3D-printed textures with visible layer lines. At the top, the inside of the box lid displays the phrase “[COUNTRY NAME]” in large, colorful, raised plastic letters—each letter in a different bright color. The lighting is warm and cinematic, highlighting the textures and shadows to evoke a sense of realism and charm, as if the viewer is opening a magical miniature version of the nation

Source Chinese translation

一张超写实的俯拍摄影作品，展示了一个米色纸板盒内的3D打印立体模型，盒盖由两只人手撑开。盒子内部展现了[国家名称]的微缩景观，包含标志性地标、地形、建筑、河流、植被以及大量微小精细的人物模型。该立体模型充满了鲜活且符合地理特征的元素，全部采用触感舒适、玩具般的风格，使用哑光3D打印纹理制作，并带有可见的打印层纹。在顶部，盒盖内侧用大号、色彩鲜艳的凸起塑料字母显示“[国家名称]”字样——每个字母颜色各异，均为亮色。光线温暖且具有电影感，突出了纹理和阴影，营造出一种真实感和魅力，仿佛观看者正在打开一个神奇的国家微缩版本。

Make it your own

Start from the source text. Add your own authorized reference for a specific person, logo or product when needed.

Change one element at a time. Keep useful composition and lighting, and use your own reference material when required.

Structure: [Subject] + [Composition] + [Light] + [Material or style] + [Text or details to preserve] + [Aspect ratio]

Open the gallery workbench ↗

Sources & attribution

Prompt author: @TheRelianceAI
Original source: Original post / source page ↗
Source collection: Awesome GPT-4o Images
Model: GPT-4o / gpt-image-1（合集Category） (source label; not a current-version claim)
Source date: 2025-05-25 · Reproduction date from the upstream attribution file.
Snapshot: 2026-10-20
Evidence: 来源Collection entry；8,149 Stars 是整个合集的历史记录，不属于单张作品.
Content rights: CC BY 4.0 as declared by the source; attribution, exceptions and third-party rights apply..Retain attribution and source links. Upstream exceptions and third-party rights apply.
Source notes: 保留合集公开 Prompt；部分提示词是合集翻译或适配版.实际效果还受Model版本、Reference与采样差异影响.