Instructions to use Lightricks/LTX-2.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lightricks/LTX-2.3 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-2.3", 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") - LTX-2
How to use Lightricks/LTX-2.3 with LTX-2:
# Install the LTX-2 pipelines git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync --frozen
# Download the weights from this repo, plus the Gemma text encoder hf download Lightricks/LTX-2.3 --local-dir models/LTX-2.3 hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Fast pipeline (distilled model, no distilled LoRA needed) uv run python -m ltx_pipelines.distilled \ --distilled-checkpoint-path models/LTX-2.3/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2.3/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8# HQ pipeline (two-stage, higher quality) uv run python -m ltx_pipelines.ti2vid_two_stages_hq \ --checkpoint-path models/LTX-2.3/<checkpoint>.safetensors \ --distilled-lora models/LTX-2.3/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2.3/<spatial-upsampler>.safetensors \ --gemma-root models/gemma-3-12b \ --prompt "A beautiful sunset over the ocean" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Notebooks
- Google Colab
- Kaggle
Clarification on LTX-2.3 Licensing for Non-Commercial Academic Research in University–Industry Collaboration
Hello LTX Team,
I am a graduate student at a university, currently conducting an academic research project in collaboration with an industry partner. Our research uses LTX-2.3 solely for academic experimentation and the preparation of a joint research paper intended for publication.
We have reviewed the LTX-2 Community License Agreement and your previous clarification regarding non-commercial academic research conducted by universities (#66). Thank you for providing that guidance.
However, our situation is slightly different because the research involves collaboration between a university and a company whose annual revenue exceeds USD 10 million.
To clarify our intended use:
- LTX-2.3 is used exclusively for academic research, experimentation, and publication of a joint scientific paper.
- The research does not involve commercial product development, production deployment, or commercial services.
- LTX-2.3 is not used to train or fine-tune models for commercial purposes.
- No direct or indirect revenue is generated from the use of LTX-2.3.
Could you please confirm whether this type of non-commercial university–industry collaborative research is covered by the free license grant under Section 2.2, even when the collaborating company's annual revenue exceeds USD 10 million? Or would a paid Commercial Use Agreement still be required due to the company's involvement?
A written clarification would be greatly appreciated, as it would help us ensure compliance with the license terms before proceeding with our academic publication.
Thank you for your time and assistance.
Best regards,
A Graduate Student