Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
LTX-2.3 Models
Model downloads for LTX-2.3. Each checkpoint below is a single file bundling the transformer, the video and audio VAEs, and the text projection; the Gemma text encoder is downloaded separately (listed below).
Every pipeline in this repository runs on these checkpoints. If you want LTX-2.5 instead, start from the Quick Start -- its weights are split per component and are not interchangeable with the files here. The LoRAs at the end of this page were trained on LTX-2.3, so pair them with an LTX-2.3 checkpoint.
Download the models you need from the LTX-2.3 HuggingFace repository:
LTX-2.3 Model Checkpoint (choose and download one of the following)
Spatial Upscaler - Required for the two-stage pipeline implementations in this repository
ltx-2.3-spatial-upscaler-x2-1.1.safetensors- Downloadltx-2.3-spatial-upscaler-x1.5-1.0.safetensors- Download
Temporal Upscaler - Supported by the model and will be required for future pipeline implementations
Distilled LoRA - Required for the two-stage pipeline implementations in this repository (except DistilledPipeline, ICLoraPipeline, and DubItPipeline)
Gemma Text Encoder (download all assets from the repository)
LoRAs
LTX-2.3-22b-IC-LoRA-Union-Control- DownloadLTX-2.3-22b-IC-LoRA-Motion-Track-Control- DownloadLTX-2-19b-IC-LoRA-Detailer- DownloadLTX-2-19b-IC-LoRA-Pose-Control- DownloadLTX-2-19b-LoRA-Camera-Control-Dolly-In- DownloadLTX-2-19b-LoRA-Camera-Control-Dolly-Left- DownloadLTX-2-19b-LoRA-Camera-Control-Dolly-Out- DownloadLTX-2-19b-LoRA-Camera-Control-Dolly-Right- DownloadLTX-2-19b-LoRA-Camera-Control-Jib-Down- DownloadLTX-2-19b-LoRA-Camera-Control-Jib-Up- DownloadLTX-2-19b-LoRA-Camera-Control-Static- DownloadLTX-2.3-22b-IC-LoRA-HDR- HDR IC-LoRA and pre-computed text embeddings forHDRICLoraPipelineLTX-2.3-22b-IC-LoRA-DubIt- Download