Floating island 3D web app
- Views
- 20.3K
- Likes
- 201
- Replies
- 26
- Saves
- 205
The creator built a single-file Three.js 3D web app featuring a floating island and interactive day, weather, growth, and explosion states. Opus wrote the code while Fable reviewed the plan and result.
Full prompt1,645 chars
Build a single-file interactive 3D web app: “Floating Island” — a stylized low-poly island floating in the sky.
Tech: one file, index.html. Use three.js r170 only, loaded with this exact importmap:
{“imports”:{“three”:”https://unpkg.com/three@0.170.0/build/three.module.js”,”three/addons/”:”https://unpkg.com/three@0.170.0/examples/jsm/”}}
No other libraries, no external assets: every model, texture and sound is generated in code.
The island:
Low-poly floating island with grass top, layered rock underside and hanging roots
A waterfall that pours off the edge and dissolves into mist below
A small cottage with a smoking chimney, a spinning windmill, trees that sway in the wind
Clouds drifting past at different depths, birds circling
Controls (bottom bar, clearly labeled buttons):
“Day / Night”: smooth 3-second transition; at night windows glow, stars appear, fireflies come out
“Weather”: cycles Clear → Rain → Snow, with particles and matching sky color
“Grow”: plants a new tree at a random spot with a growing animation
“Explode”: the island splits into floating layers with labels, press again to reassemble
Keyboard shortcuts: D, W, G, E for the same four buttons.
Mouse: drag to orbit, scroll to zoom, gentle auto-rotate when idle.
Quality bar: soft shadows, fog, tone mapping, smooth 60fps, polished UI with a title card in the top-left. It should look like a finished indie game menu screen, not a demo.
Finish in one go. Do not ask me questions. When done, tell me the file is ready.
setup: fresh folder → /model opus → /advisor fable → paste. Fable on high effort, Opus on medium (its default). costs straight from /usage.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/0xShoopy/status/2122695064304435566
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 2026-11-19. 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
0:17Interactive gummy orange slice comparison
1.2M views
0:13Gummy bear soft-body physics scene
632.6K views
0:13Glitter sticker effect comparison
480.8K views
0:18Jelly candy simulation comparison
448.7K views
0:18Watermelon rubber band test: Opus 5.5 vs GPT-6 Astra
421.5K views
Related articles
Anthropic Claude Certified Architect Complete Roadmap: 8 Free Courses + $99 Exam
Anthropic launched the Claude Certified Architect certification on March 12, 2026, with 13 self-paced courses — all completely free, no registration required, no paywalls. The exam itself costs just $99. This post walks through a 12-week roadmap covering the 8 key courses in Weeks 1–9, with direct links to each.
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.
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.
I Ran Six Experiments on TypeSafe Jev: What It Can and Can't Do
Six experiments, five open-source repos, 210,000 judgments: zero-shot Jev is worth a few hundred labels, but its best role is as a feature, not as a model.