A legacy, silent video model, now worth a look only for hobbyists who want something light to experiment with.
Kenning's take
What it does
LTXV, also called LTX-Video, was the first open-source video model in Lightricks' LTX family, built for fast text-to-video and image-to-video generation without sound. A 13 billion parameter version announced in May 2025 added multiscale rendering for higher quality at speed. Lightricks now calls it a legacy model; it is still downloadable and available in LTX Studio, while LTX-2.5 is the current model.
- Text-to-video and image-to-video
- Fast, near real-time generation
- 13B version with multiscale rendering
- LoRA and IC-LoRA support
- Runs on high-end and consumer GPUs
Who it suits. Developers and hobbyists experimenting with a lighter open video model.
Key facts
- Category
- AI models
- Part of
- LTX Studio
- Made by
- Lightricks
- Launched
- 2024
- How to get it
- open source on GitHub and Hugging Face; available in LTX Studio
- Works on
- self-hosted, LTX Studio
- In the UK
- Yes
- Free plan
- open-source weights and code
FAQ
Is LTXV still supported?
Lightricks calls it a legacy open-source model. It remains downloadable and in LTX Studio, and LTX-2.5 is the current model.
Does LTXV make sound?
No. LTXV is video only; synchronised audio arrived with LTX-2.
Is LTXV free?
Yes, it is open source on GitHub and Hugging Face.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
LTX-2.5
Lightricks' latest open-weight video model, with multi-shot scenes, sound, 4K output and HDR
LTX-2.3
Lightricks' 2026 open video model with sound, sharper detail and native vertical video, runnable on home GPUs
LTX-2
Lightricks' 2025 open-source video model that first added synchronised sound and 4K output
ACE-Step 1.5
Open-source music generation model that writes full songs with lyrics and runs on ordinary consumer GPUs.