Open-Sourcing 14B World Model and 1.3B Version
thetripathi58 · x · 2026-07-10
The post introduces an open-source multimodal world/video generation model, releasing the model weights, inference code, and related agentic-harness code. The main model is 14B, and the paper also introduces a lightweight 1.3B version designed for deployment on a single consumer-grade GPU.
The author also points out a key limitation: the model lacks true long-term memory. When leaving a scene and returning, it will generate a new "plausible-looking" space rather than accurately recalling the previous state.
Related event: Ant-backed Team Open-Sources LingBot-World 2.0 Real-time World Model(26 posts)→
More from Multimodal
- Midjourney creator showcases --sref style reference outputs: gothic character art — OVolosin82152 · 2026-10-27
- AI artist BluesOfBirds drops glitch-laden piece "In the Storm" — LudovicCreator · 2026-10-27
- Community-trained MOSS Sharpness Slider LoRA: 72 photos, 500 steps, +/-1 focus control — aoleg77 · 2026-10-27
- MOSS Image Edit vs Fibo-2.0-edit: 5-grid comparison of instruction-based image editing — Illustrious_Row_9971 · 2026-10-27
- Cinematic title sequence built with ComfyUI: LTX-2.5 + MiniMax H3 image-to-video — magratheya_64 · 2026-10-27
- Fish Audio ships open-weight Drama 3 TTS; creator shows turning old posts into narrated videos — alex_verem · 2026-10-27