LTX-2.5

22B open-weight diffusion video model turning text, image or video input into synchronized video and audio in one model. Native multishot generation holds character, environment and voice across cuts; a 10-second image-to-video clip takes 6.8 seconds on two NVIDIA GB200 chips.

выпуск 11.08.2026, веса на Hugging Face под LTX-2.x Community License; текстовый энкодер — Gemma 4 12B. Производителя Lightricks в справочнике нет вообще

Understands

text, images, video

Produces

video, speech, sound effects

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.