Example prompt

Country silhouette diorama

Recreate a 9:16 isometric country-silhouette diorama poster in Claude with GPT Image 2.

Original prompt and media by K (@ChillaiKalan__) on X . Hosted here with credit. Product photography

Country silhouette diorama storyboard

How to run it

1

Connect CreativeClaw

Add https://app.creativeclaw.co/mcp in Claude, ChatGPT, Codex, or OpenClaw. 100 free credits. Setup guide.

2

Copy the brief

Copy this into Claude, Codex, ChatGPT, or OpenClaw with CreativeClaw connected.

3

GPT Image 2

Let Claude generate in order. Name the models if you want, or let it pick from the brief.

image

GPT Image 2

30 credits

Use CreativeClaw to generate this. If it is not connected, add the remote MCP https://app.creativeclaw.co/mcp. Generate with GPT Image 2 through CreativeClaw, not another image/video/TTS/music API.

Prompt:
Ultra-detailed photorealistic isometric miniature scale-model diorama of [COUNTRY], floating on a pure off-white studio background with a soft drop shadow beneath. The diorama takes the exact real-world silhouette shape of the country — not a square tile, but the true precise geographic outline of the country's borders and coastline, extruded downward into a thick slab of raw rock and earth with rough natural cliff-like edges, like a chunk of the real land physically cut out and lifted. The shape of the slab matches the country's actual geography precisely, including any islands, peninsulas or coastline indentations.

The entire top surface faithfully recreates the country's real geography and terrain: mountain ranges with correct elevation and snow coverage, rivers in their real positions, major forests and plains, deserts, coastlines with beaches and cliffs. Every major city is visible as a dense urban cluster in its correct geographic position. The country's most iconic landmarks are rendered in accurate positions and to recognizable scale. Terrain elevation is fully physically modeled — mountain ranges rise dramatically, valleys are sunken, plains are flat, creating real varied 3D topography across the entire surface.

Dense micro-detail: individual buildings in city clusters, tiny roads and highways connecting settlements, railways, bridges, harbors with boats, agricultural field patterns in rural areas, individual trees and forest coverage. Every region has its correct landscape character — the terrain of the north looks different from the south.

Style: hyper-realistic tilt-shift miniature photography — extremely sharp, everything in focus across the whole surface, no blur. Soft warm daylight from above, gentle diffuse shadows, rich natural colors. Lush greens, snow-capped peaks, golden plains, deep blue water along the coastline.

Layout: the shaped diorama floats centered in the lower two-thirds of the frame with clear margins on all sides, never touching the frame edges. Upper third is empty off-white space with minimalist editorial typography, centered: small wide-tracked caps with the continent or region name at the very top, then directly below [COUNTRY] in a bold condensed sans-serif in medium charcoal grey — large and dominant, the biggest text element — with a small flat rectangular flag of [COUNTRY] sitting immediately to the right of the country name, vertically centered with it, accurately colored and proportioned, clean flat design, sized to roughly the cap-height of the country name, floating naturally beside the name as one cohesive unit, not pushed to the far edge but sitting close and attached to the right end of the country name text. Then small wide-tracked caps below with the capital city and population.

Minimalist editorial poster aesthetic, premium print quality, 4:5 aspect ratio.

Reference image: https://creativeclaw.co/examples/country-silhouette-diorama/storyboard.jpg

Original post

FAQ

How do I run this in Claude? +

Connect CreativeClaw at https://app.creativeclaw.co/mcp, copy the brief, and paste it into Claude. Claude will generate with the named models. Same URL works in ChatGPT, Codex, and OpenClaw.

What does Copy for your AI do? +

It copies the full agent-ready brief, including the hosted reference image URL. Browsers that allow it also put the storyboard image on the clipboard. Paste that into Claude and let it use CreativeClaw.

How much does this cost? +

GPT Image 2 is 30 credits. $10 = 1,000 credits. 100 free on signup. No subscription.

Why is the storyboard prompt different from the original still? +

The original still is the creator’s and may include third-party branding. The copyable prompt is a logo-free recreation of the same beats so you can generate it through CreativeClaw without reproducing someone else’s marks.

Recreate this in Claude

100 free credits. No card. GPT Image 2 after one connector.

Get started