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
- Meme: Developers hitting 'Allow' in Claude Code over and over — aishashok14 · 2026-10-02
- Scott Alexander answers cult accusations with a Pontius Pilate comeback — mjdramstead · 2026-10-02
- AI-made Robert's Rebellion fan trailer wows viewers, reigniting Game of Thrones regrets — dioscuri · 2026-10-02
- Machine god, booking flights: one-liner mocks what AI agents are used for — tekbog · 2026-10-02
- Opus 5.5 puts Minecraft into Slime Rancher and it actually works — Angaisb_ · 2026-10-02
- Joke post: 'Ben Affleck, Member of Technical Staff at Hugging Face' focusing on open video post-training — MaziyarPanahi · 2026-10-02