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
- ostris pre-training "Primal VAE": 1-channel latents match modern 8x VAEs via patching — ostrisai · 2026-10-26
- Slopcore: AI-generated meme films turn low-fi slop aesthetics into a subculture — Yamapama · 2026-10-26
- TischEins, a large Midjourney SREF library, relaunches with new design after security outage — tisch_eins · 2026-10-26
- MOSS-Image-SFT 4-step distillation tops 16.5K downloads on Hugging Face — _akhaliq · 2026-10-26
- Claude Code can now edit videos: a 10-prompt workflow from raw footage to final cut — TawohAwa · 2026-10-26
- One-sentence 3D worlds turn cinematic with CineMap and TapNow — gizakdag · 2026-10-26