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 Open-Sources LTX-2.5 Video Model with Native Multishot(24 posts)→
More from Models
- GLM 5.3 Flash scores 39 on Artificial Analysis index, beating larger Mistral and Muse models — airesearch12 · 2026-10-16
- Open-source ASR built on a Qwen3-4B decoder posts 3.54 average WER across 5 languages — rohanpaul_ai · 2026-10-16
- Google's "Paid Pro" paywall in Antigravity angers Pixel buyers and bundle subscribers — Chance-Okra-5920 · 2026-10-16
- GLM 5.3 Flash is now free in OpenCode coding tool — DanielLockyer · 2026-10-16
- GPT-6 Sol runs a potion shop flawlessly but its reasoning mistakes stock for its own stats — liminal_bardo · 2026-10-16
- Codex convert says Claude app is 2-3x better optimized with a far smoother UI — ItchyResearcher5671 · 2026-10-16