Skip to content

[GitHub Trending] Lightricks/LTX-2

7.8 relevance
Score Breakdown
technical depth
8
novelty
7
actionability
8
community
7
strategic
8
personal
9

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

Open-source generative AI model with inference and LoRA training, directly relevant to AI/ML interests.

AI/ML github.com
Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model. - Lightricks/LTX-2
Summary

Lightricks open-sourced LTX-2, a 22B-parameter DiT-based audio-video foundation model that synchronizes audio and video with high fidelity. It supports multiple performance modes, production-ready outputs, and API access, with pipelines for text-to-video, audio-to-video, lip dubbing, and more. Optimization includes FP8 quantization and FlashAttention 4 for efficient inference on Hopper and Blackwell GPUs.

Author

Lightricks