Instructions to use Lightricks/LTX-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lightricks/LTX-2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Inference
- Notebooks
- Google Colab
- Kaggle
Windows - torch_cpu.dll crash error
windows 10
python 3.13.7
torch 2.9.1+cu130
python -m ltx_pipelines.ti2vid_two_stages --checkpoint-path ... sample test, same torch_cpu.dll crash error
Comfy-UI is LTX-2 text to Video Test, Linux is Good but Windows is torch_cpu.dll crash error
Comfy-UI is git install or Comfy-UI installer , same torch_cpu.dll crash error
z-Image Turbo test is good, but LTX-2 is windows bed;
Please check that your NVIDIA drivers support CUDA 13.0.
If the crash persists during the final stage of generation, it is probably a VAE memory overflow.
I suggest you enable VAE Tiling in your script arguments and/or increase your Windows Pagefile size.
NVIDIA-SMI 591.74 Driver Version: 591.74 CUDA Version: 13.1
Compy-UI is same
Python -m ltx_pipelines.ti2vid_two_stages --checkpoint-path ... same
VRAM: 16G
RAM: 52G
Windows
LTX 2.3 is good windows comfy-ui make good, not crash