LTX-2.5 Open-Source World Model: 10s 4K Video in 6.8s from a Single Image
dr_cintas · x · 2026-08-13
Lightricks introduces LTX-2.5, an open-source world model that predicts the next moment rather than the next word.
Key Features:
- Ultra-fast: Generates 10-second videos from a single image in just 6.8 seconds.
- High Quality: Uses a new compression model for sharper textures and better faces, with native 4K and synced audio support.
- Local Execution: Runs locally on consumer GPUs.
- 100% Open Source: Weights and code are fully available, with distilled and pre-trained models released on Hugging Face.
Related event: Lightricks Releases Open-Source Video Model LTX-2.5(23 posts)→
More from Models
- Reuters Exclusive: Google AI Reshuffle Driven by Internal Conflicts and Gemini Delays — firstadopter · 2026-08-13
- Liquid AI Launches LFM2.5-VL-3B: A 2GB On-Device Vision Model with Massive Grounding Gains — Fun-Meaning-6474 · 2026-08-13
- Beyond US and China: 24 Countries Build Foundational Models on Low Budgets — TobyWalsh · 2026-08-13
- GPT-5-pro Successfully Proves Open Math Problem from Optimization Paper — analisereal · 2026-08-13
- Hands-on with Grok 4.6 for Coding: Fast, Cheap, and 'Good Enough' for Daily Tasks — draginol · 2026-08-13
- Deepgram Launches Flux TTS: Built for Real-Time Voice Agents — Scobleizer · 2026-08-13