









LTX-2 is a state-of-the-art, production-ready AI foundation model developed by Lightricks for generating synchronized audiovisual content. It is the first fully open-source, open-weights AI model that supports native 4K resolution (2160p) video generation at up to 50 FPS, along with synchronized audio generation (including dialogue, ambient sounds, and music). Powered by a 19B parameter Diffusion Transformer (DiT) architecture, LTX-2 supports text-to-video and image-to-video generation, creating clips up to 20 seconds long. It is optimized for NVIDIA GPUs, offering 3x faster performance on RTX 50 Series.
LTX-2 can be used by accessing the interactive demo directly in the browser, or by deploying the fully open-source model locally using the provided weights, training code, and inference pipeline available on GitHub and Hugging Face. Users can transform text prompts or static images into dynamic video content, utilizing features like multi-keyframe conditioning for advanced control. Deployment is also possible via cloud APIs like Fal, Replicate, and RunDiffusion.
More Contact, visit the contact us page(https://www.lightricks.com/contact)
LTX-2 by Lightricks Company name: Lightricks .
LTX-2 by Lightricks Company address: .
More about LTX-2 by Lightricks, Please visit the about us page(https://www.lightricks.com).
LTX-2 by Lightricks Twitter Link: https://twitter.com/lightricks
LTX-2 by Lightricks Github Link: https://github.com/Lightricks/LTX-Video




23.13%
Social Listening