AITuber without Live2D: Opus builds 3D stage, Minimax h3 and TTS fill the rest
Hailuo_AI · x · 2026-10-02
Japanese developer @ivy432hz prototyped an AITuber setup that skips Live2D/3D character models entirely: Claude Opus generates a 3D stage and camera work, with pre-generated image/video assets produced per episode. The stack: gpt-image-2 for the character portrait and limbs, Minimax h3 for video, and Irodori-TTS for voice. Their demo came out a bit "try-hard," but the no-Live2D AITuber route looks viable.
More from Fun
- Core Memory profiles Ari Kuschnir, the creator behind viral AI parody videos — kyliebytes · 2026-11-19
- AI-generated Scottish-accent parody video hailed as the funniest AI video yet — DimitriDeJonghe · 2026-11-19
- The academia LLM paradox: everyone writes with AI, nobody wants to read or be judged by it — wandedob · 2026-11-19
- Tibo's spicy take on why Astra 6.2 is getting such bad reviews — eigenrobot · 2026-11-19
- Designer spins up an agent to build state-airline brand gallery mid-flight delay — beh_zod · 2026-11-19
- LeCun refuses doomer faction letter, enjoys doomers infighting — ylecun · 2026-11-19