GPT-6 Astra semi-autonomously recreates Nagoya Station with one-prompt city generation
gabrielchua · x · 2026-09-12
Creator @studioveco used GPT-6 Astra to build a 3D scene of Nagoya Station almost hands-off. After detailing the station, a single prompt — "generate the surroundings" — produced the entire surrounding city in one shot, combined with Japan's PLATEAU 3D city data. The creator notes this near-autonomous workflow is a major boost for 3D production (video shown at 2x speed).
More from Multimodal
- Teaching image generation models to understand hex color codes, an ECCV 2026 paper — ducha_aiki · 2026-09-12
- Consistent multi-view 3D generation: using a multi-angle reference matrix — LCD-9 · 2026-09-12
- JD Cloud debuts Lingjing AIGC platform with infinite canvas; student made award-winning short film in 4 days — 量子位 · 2026-09-12
- Blender MCP with Astra delivers impressively smooth AI-driven animation — Dimillian · 2026-09-12
- Step-by-step Nano Banana workflow: split colorization into three passes to cut errors — aziz4ai · 2026-09-12
- Pwnisher winner tests full GPT Astra x Blender x Dreamina 3D animation pipeline — aziz4ai · 2026-09-12