Gemini 3.7 Flash Generates 16.5K-Voxel Japanese Pagoda Garden in Three.js from One Prompt
CodeByPoonam · x · 2026-08-14
A developer gave Gemini 3.7 Flash a detailed prompt to recreate a voxel-style Japanese pagoda garden in Three.js: 16.5K voxels, cherry blossoms, pond, torii gate, particles, lighting, camera controls, and interactive UI. The model generated the complete single-file HTML + JavaScript.
More from Multimodal
- FrankenSim builds a physics-based virtual orchestra, piano and drum demos live — doodlestein · 2026-10-16
- vLLM officially supports Muse Spark Open: multimodal, 1M context, agentic — vllm_project · 2026-10-16
- InfoVis: 9B unified model tops open-source slide generation and editing, trained on 13M records — Jiahao Wang · 2026-10-16
- RepForcing: feature-space supervision improves few-step autoregressive video distillation — zju · 2026-10-16
- SCOPE: semantic span-aware GRPO objective improves T2I prompt rewriting — university-of-rochester · 2026-10-16
- Orbia benchmark asks: do generated videos form a consistent 3D world? — tencent · 2026-10-16