LTX Video 2.3 Full Quality

• 🎬 Open-source text-to-video model from Lightricks, full-quality tier.
• 🆕 LTX-2.3 update: improved audio, visual quality, and prompt adherence.
• 🎵 Generates synchronized video and audio from a single network.
• 📏 Supports extended clips and high-resolution output.
• 🔧 Updated VAE for finer detail over LTX-2.
• 🔒 Open weights released on Hugging Face under Apache 2.0.
• ⚡ Quantized and distilled variants plus upscalers for efficiency.
• 🌐 Diffusers integration and local execution supported.

Lightricks

Lightricks is a creative technology company founded in January 2013, widely recognized for its popular selfie-editing app Facetune. Originally focused on mobile video and image editing tools, the company has expanded significantly into generative AI,…

LTX Video 2.3 Full Quality is the high-fidelity, text-to-video tier of Lightricks' LTX-2.3 release, a diffusion-transformer foundation model that generates synchronized video and audio from a single network. It targets stable, detailed output for production-grade workflows, contrasting with the speed-focused LTX Video 2.3 Fast flow built for rapid iteration. An image-to-video counterpart in the same Full Quality tier, LTX Video 2.3 Full Quality, shares the same engine.

Compared with its same-family predecessor, LTX Video 2.0 19B, Lightricks documents LTX-2.3 as an update with improved audio and visual quality and enhanced prompt adherence. The release adds an updated VAE for finer detail and supports extended clip lengths at high resolution.

The model retains LTX-2's core design philosophy: open weights, practical local execution, and one model handling both video and synchronized native audio. The release also provides quantized and distilled variants for faster inference, alongside spatial and temporal upscalers that let creators render at manageable resolution then scale up.

Weights are freely available on Hugging Face under the Apache 2.0 license, with reference workflows documented on the model card. It integrates with the Diffusers library, fitting the family's emphasis on iterative, exploratory video creation.