School yard futsal pixel-art diorama
- Views
- 15.1K
- Likes
- 397
- Replies
- 37
- Saves
- 323
A pixel-art 3D futsal school-yard diorama was built in separate Opus and Sonnet runs, with Three.js and a simulated match engine.
Full prompt2,295 chars
Build a single-file pixel-art 3D diorama (three.js r160, orthographic camera at ~31°, rotatable in 90° steps, low-res render target with depth outlines and a quantized palette) of a futsal 5-a-side match on a small floating island: a school yard. Original content only, English UI.
Scene: a 40×20 m blue rubber futsal court inside a wire cage (cutaway on the sides nearest the camera), 3×2 m red-and-white goals, proper futsal markings (6 m arc areas, 6 m and 10 m spots, centre circle). Team benches and a timekeeper's table on one touchline, small bleachers on three sides with an instanced crowd of kids and parents. Behind the north end: a school facade ("School No. 12") with porch and door the teams walk out of, a wall clock with moving hands, a flag, and a 64×32 pixel scoreboard on the wall showing score, clock and team fouls. Around the court: playground, bike rack, shed, basketball hoop, snack kiosk, trees, ball boys, a photographer, stewards.
Match engine: 4 school clubs with distinct kits (none matching the court colour), 9-player squads (5 on court + 4 subs) in a 1-2-1 formation (GK, fixo, two alas, pivot). Two halves of 20 match minutes (real length selectable), no offside, kick-ins instead of throw-ins, keeper restarts by pass, corners and free kicks scaled to the small court. Ball physics with drag, analytic rolling and lob solving; short passing, shots from distance, rare crosses. Referee on one touchline, second official at the table. Coroutine-driven agents with A* navigation: walk-out from the school door, warm-up, kick-off, goal celebrations, half-time, full-time handshakes. Commentary feed, viewer actions (Shoot / Square it / Hit it long, click to mark the next pass), camera modes (TV follow, whole yard, close-up), day / dusk / night with four corner floodlights.
Switchable court surface (segmented control): rubber (blue), asphalt, artificial turf, wooden parquet. Each swaps the court texture AND the ball physics constants — rolling resistance, bounce restitution, skid — so asphalt is fast and bouncy, turf slows the ball and kills the bounce, parquet is the quickest and slickest.
Page: light editorial layout with a small mast, the canvas, and a control panel (match length, surface, time of day, views, commentary). Must work at phone width.Source: the creator's reply under the post. Kept in its original language, unedited.
Want more prompts like this one?
Get the 50 most-viewed Claude 5.5 video prompts on one page: the full original text, the creator and the post it came from. We'll only email you when there's a new prompt worth trying. Unsubscribe anytime.
Tools the creator mentioned
Original post: https://x.com/vib3coded/status/2116944633800368616
All works are open data at GitHub · awesome-opus-5.5-video.
Model attribution is as stated by the creator and was not independently reproduced. View counts are a snapshot from 2026-11-03. The work belongs to its creator; DM @GoSailGlobal on X for corrections or removal.
More comparisons
0:42AI self-portrait challenge: Sonnet 5.5 vs GPT-6 Astra
7.3M views
0:28Opus 5.5 vs GPT-6 Astra samurai game demo
1.1M views
0:13Gummy bear soft-body physics scene
631.5K views
0:30GPT-6 Astra vs Claude Opus 5.5 comparison
605K views
0:22Grok vs Opus grass-touching simulator cost test
554.9K views
0:44Opus 5.5 vs GPT-6 Sol Unreal game dev
544.2K views
Related articles
OpenAI Academy vs Anthropic: A Complete Comparison of Two Leading AI Companies' Free Learning Paths
Both of the top AI companies offer official free learning platforms — together that's 25+ courses and hundreds of hours of content, enough to take you from AI newcomer to resume-worthy engineer. This post maps out all 15 OpenAI Academy courses along a 10-week roadmap and provides a full side-by-side comparison with the Anthropic learning path.
My Current AI Tools List | 2025 Edition
The AI tools I shared at a corporate training session — if you can't be bothered sorting through options, just use the best ones.
The Complete Map of Free AI Learning: 10 Official Platforms, $0 Total Cost
Anthropic, OpenAI, Google, NVIDIA, Microsoft, AWS, Meta, IBM, DeepLearning.AI, Hugging Face — every official AI course from all 10 platforms is free. This is the master index: one comparison table + learning paths by role.
Three Things You Should Embrace in 2026
The future belongs to Agents — embrace the CLI; manage AI with a manager's mindset; stop fixating on execution-level details.