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
Is LTX-2 compatible with Mac M4/Metal?
Hi everyone,
I'm trying to run the LTX-2.0 Text to Video workflow in ComfyUI but I keep getting a "Reconnecting" status (see screenshot). The workflow never starts processing.
My Setup:
Mac: MacBook Pro with Apple M4 Max
Chip: 16 cores (12 performance + 4 efficiency)
GPU: 40-core Apple M4 Max GPU with Metal 4 support
RAM: 48 GB unified memory
OS: macOS Sequoia
Workflow Settings:
Frame count: 121
Width: 1280
Height: 720
Noise seed: 10
Checkpoint: ltx-2-19b-dev-fp8.safetensors
What I've tried:
Running the default sample workflow that comes with LTX-2 (no custom modifications)
Using the default prompt and settings provided
Feed the error from your terminal output into ChatGPT or Claude. They'll give you a good sense of what's going on, usually.
fp8 models don't work on metal...change the model to b16 or a gguf
