Lightricks

LTX-2.3 is a multimodal video generation model that produces synchronized video and audio from text or images. It supports text-to-video and image-to-video workflows with native dialogue and ambient sound generation, emphasizing temporal stability, strong motion coherence, and production-ready output quality for professional creative pipelines.

LTX-2.3 Fast is a performance-optimized variant of LTX 2.3 designed for rapid video generation with synchronized audio. It supports text-to-video, image-to-video, and audio-conditioned workflows while prioritizing speed, responsiveness, and cost efficiency for draft, preview, and high-velocity creative production use cases.

LTX-2 is an open-source multimodal video foundation model that generates synchronized video and audio from text or image prompts. It produces high-quality motion sequences with native 4K resolution and smooth temporal coherence, making it suitable for creative video generation, production workflows, and audiovisual storytelling.

LTX-2 Retake regenerates targeted segments inside an existing clip. Define start time and duration. Replace video, audio or both with new prompts. Preserve surrounding motion and continuity. Ideal for selective revisions, dialog tweaks, and shot refinements without full regen.

LTX-2 Fast is the high speed tier of the LTX-2 video foundation model. It targets rapid cinematic iteration with strong motion quality and visual consistency. Generate short synced audio video clips from text or image prompts with low latency and efficient GPU use.

LTX-2 Pro is a cinematic video model by Lightricks. It supports text prompts and image inputs. It outputs high resolution clips with realistic motion and precise lighting. It targets professional workflows that need stable pacing, detailed subjects, and synchronized audio.