Instructions to use Lightricks/LTX-2.3-22b-LoRA-Foley-V2A with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Lightricks/LTX-2.3-22b-LoRA-Foley-V2A with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- LTX.io
How to use Lightricks/LTX-2.3-22b-LoRA-Foley-V2A 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-2.3-22b-LoRA-Foley-V2A --local-dir models/LTX-2.3-22b-LoRA-Foley-V2A hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Text/image-to-video with the LoRA on the HQ two-stage base pipeline uv run python -m ltx_pipelines.ti2vid_two_stages_hq \ --checkpoint-path path/to/checkpoint.safetensors \ --distilled-lora path/to/distilled_lora.safetensors 0.8 \ --spatial-upsampler-path path/to/spatial_upsampler.safetensors \ --gemma-root models/gemma-3-12b \ --lora models/LTX-2.3-22b-LoRA-Foley-V2A/<weights>.safetensors 1.0 \ --prompt "your prompt here" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Notebooks
- Google Colab
- Kaggle
Demo for this model on Spaces
Hey @Lightricks 🤗, it's me again, Poli from Hugging Face
You keep shipping 🚢 — congrats on Lightricks/LTX-2.3-22b-LoRA-Foley-V2A! Once again, me + my agent built an interactive demo app of it on Hugging Face Spaces, running on a free ZeroGPU infrastructure.
Here's a link to the demo: https://huggingface.co/spaces/hugging-apps/ltx-foley-v2a
And you know the spiel, but it would be great to transfer it to your organization/user on Hugging Face. Just let me know which username/org to transfer over, we hope it can give your work more visibility, discoverability and allows folks to try it out.
In the future, feel free to already ship models with demos included. You can use this one as a blueprint to build by yourself or with the help of an agent — you can load the huggingface-spaces skill on Claude Code, Codex, Pi, etc.
(If you have any questions or just want to chat more about this, you can find me on Twitter, LinkedIn or apolinario @ huggingface.co)
Cheers,
Poli