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.io
How to use Lightricks/LTX-2.3 with LTX.io:
# 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 about small internal previs / R&D usage
Hello,
I am trying to better understand the expected licensing model for a small internal-only evaluation setup using LTX-2.3.
The intended usage would be:
- 4β5 internal users
- Closed local environment
- Internal previs / ideation workflows
- No external distribution
- No customer-facing service
- No LoRA or fine-tuning
- Reference-only outputs (not final production assets)
This would mainly be for internal creative exploration and camera / motion previs.
Would this type of usage generally be considered enterprise/commercial usage for a larger company, or is there a smaller-scale evaluation option typically available?
At this stage I am only trying to understand the expected licensing approach before discussing internally.
Thank you.
Hi @centerV -- please check https://ltx.io/model/license and reach out to the licensing team through the form there!
Thank you for the clarification!
I understand that the licensing team would need to handle the specifics.
Before reaching out formally, I just wanted to better understand whether there is typically an evaluation / internal R&D path for very small closed-team previs usage (around 4β5 users, internal-only, reference outputs).
This would help us determine whether it makes sense to discuss internally first.
Thanks again!
It depends.
@centerV a small clarification, in a company above our limit ARR, using LTX requires a license, even if for internal use, assuming it is a production tool in use for business purposes.
Given a limited usage pattern, i.e. A previz tool for a small team, we have smaller scale licenses.
If it's evaluation of LTX itself to see if it can even be used for this previz tool, that doesn't require a license.