About this model
LTX Video 2.5 Pro is the quality-oriented text-to-video tier of the LTX-2.5 generation from Lightricks, released in 2026. Lightricks' model documentation describes LTX-2.5 as an open foundation model for cinematic creation, built on a 22-billion-parameter asymmetric dual-stream diffusion transformer that produces synchronized audio alongside picture rather than silent footage.
Against its same-family predecessors LTX Video 2.3 Full Quality and LTX Video 2.3 Fast, Lightricks' LTX-2.5 page frames the new generation around several added capabilities: multi-shot scenes generated in a single pass rather than stitched from separate clips, editing of real recorded footage, cinema-grade EXR export for downstream color and compositing work, and rendering compute allocated according to scene complexity.
Within the 2.5 line, the Pro and Fast labels follow Lightricks' own API tiering: the Fast tier is intended for iteration, storyboards and previews, while the Pro tier is aimed at final renders. Users who want cheaper drafts of the same prompt can switch to LTX Video 2.5 Fast; those starting from an existing still image should use LTX Video 2.5 Pro in its image-to-video form, or LTX Video 2.5 Fast for quick image-driven tests.
Lightricks, founded in 2013 and known for its video and image editing apps including Facetune, publishes the LTX models as an open foundation family while also offering hosted generation through its own API, which suits teams that want to prototype on a managed endpoint before self-hosting.
This About section is AI-generated from public sources (Claude Opus 5), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.
Data sources: Venice API · HuggingFace · Wikipedia — enrichment updated 5d ago