LTX
Open foundation models for video, audio, and world simulation
Visit ltx.io ↗What is LTX?
LTX is an open-weight diffusion transformer platform for generating synchronized video and audio. Built by a frontier AI lab, it powers production workflows across film post-production, robotics, gaming, autonomous driving, and medical applications. The models feature diffusion fidelity rendering, which allocates compute dynamically to complex scenes and renders directly in pixel space for high-quality output.
The platform provides open-access models, API access, and research resources. LTX-2, the latest version, integrates audio and video generation in a single model with multiple performance modes and production-ready outputs. Teams can download open weights, adapt models for specific pipelines, and access research papers across robotics, creative applications, gaming, and autonomous systems.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered LTX automatically. Evidence: GitHub Lightricks/LTX-2; repo has .claude. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation

Clone viral videos with AI agents, generate 100 variants in one command


Desktop app for DeepSeek Harness with built-in model provider support

AI agent controls your iPhone through a $7 ESP32 board, no jailbreak needed

Run frontier LLMs locally on your PC with optimized MoE serving


Local-first memory storage and retrieval system for AI workflows