LTX 2.3 is a 22-billion-parameter open-source AI video model built by Lightricks on Diffusion Transformer architecture. It supports text-to-video, image-to-video, audio-to-video generation with native portrait output (1080x1920), rebuilt VAE for sharper quality, and 4x-expanded text connector. Features include: cinematic video generation from text prompts, image-to-video transformation with smooth camera motion, audio-to-video synchronization with lip-sync, multi-modal generation pipeline, face & character preservation across frames, and up to 4K resolution output. Runs 18x faster than WAN 2.2 on H100 GPUs. Free credits available, commercial use allowed, no watermarks. Ideal for filmmakers, marketers, content creators making Reels/Shorts/TikTok videos.