LingBot-World 2.0: open 1.3B world model runs real-time interactive generation on one consumer GPU
Scobleizer · x · 2026-09-10
ModelScope released LingBot-World 2.0, a 1.3B world model that runs continuous real-time interactive generation on a single consumer GPU, with the 14B causal pretrain backbone and bidirectional teacher open-sourced.
- Responds in real time to movement, camera control, combat, and text-driven events, with scenes continuously unfolding rather than ending as fixed clips.
- Causal pretraining and MoBA preserve textures, geometry, and scene consistency over long autoregressive rollouts.
- Consistency and distribution-matching distillation compress multi-step generation and train on its own rollouts to reduce drift, giving developers a post-training path.
Related event: Ant's LingBot Open-Sources LingBot-World 2.0 World Model(4 posts)→
More from Multimodal
- Creator makes 2D electro-pop anime music video with just a prompt using MiniMax H3 — Hailuo_AI · 2026-09-11
- Street View to driving footage: GPT Astra fetches images, MiniMax H3 turns them into dashcam video — Hailuo_AI · 2026-09-11
- Single-author ECCV 2026 paper makes rolling shutter correction practical — ducha_aiki · 2026-09-11
- AI digital human covers Japanese classic so realistically viewers can't tell — JourneymanChina · 2026-09-11
- ComfyUI Style Explorer Adds LoRA Preview Catalog and Sharing — neonsparksuk · 2026-09-11
- 4 favorite Midjourney V6.1 --sref style codes, ready to copy — michaelrabone · 2026-09-11