LTX Models by Lightricks
Last refreshed 2026-06-29. Next refresh: weekly.
About
LTX is Lightricks' family of open-weight video generation models. LTX-2 is a DiT-based audio-video foundation model that generates synchronized video and audio in a single model, with a focus on practical, local use. It handles text-to-video and image-to-video, and ships as a 19B full model, a distilled 8-step version, and spatial and temporal upscalers. LTX-2.3 is a significant update with better audio and visual quality and closer prompt adherence, released as a 22B model with distilled versions. The models run locally through Lightricks' LTX-2 codebase, ComfyUI, or Diffusers, and can be tried in LTX Studio.
Decision facts
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| LTX-2.3 | Use when provider availability and model metadata match the workload. | 2024-12 | — | Current |
| LTX-2.3 Fast | Use when provider availability and model metadata match the workload. | 2024-12 | — | Current |
Release Timeline
1 release groupSpecifications(2 models)
| Model | Released |
|---|---|
| LTX-2.3 | 2024-12 |
| LTX-2.3 Fast | 2024-12 |