Instructions to use Lightricks/LTX-2.3-22b-IC-LoRA-Ingredients 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-IC-LoRA-Ingredients 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-2
How to use Lightricks/LTX-2.3-22b-IC-LoRA-Ingredients 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-2.3-22b-IC-LoRA-Ingredients --local-dir models/LTX-2.3-22b-IC-LoRA-Ingredients hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Video-to-video with the IC-LoRA (runs on the distilled base model) uv run python -m ltx_pipelines.ic_lora \ --distilled-checkpoint-path path/to/distilled_checkpoint.safetensors \ --spatial-upsampler-path path/to/spatial_upsampler.safetensors \ --gemma-root models/gemma-3-12b \ --lora models/LTX-2.3-22b-IC-LoRA-Ingredients/<weights>.safetensors 1.0 \ --video-conditioning reference.mp4 1.0 \ --prompt "your prompt here" \ --output-path output.mp4 - Notebooks
- Google Colab
- Kaggle
doesnt work with ltx 2.5
its not working correctly with the ltx 2.5 model
Yea I'm having issues with it too.
Yes. Confirmed, used official workflow from 2.5 and doesnt work
Thanks for flagging this - it works great with ltx-2.5.
Try bumping up the ingredients lora strength for 2.5. I find that it works best with 1.3, but really depends on your inputs (and result preferences).
Thanks for flagging this - it works great with ltx-2.5.
Try bumping up the ingredients lora strength for 2.5. I find that it works best with 1.3, but really depends on your inputs (and result preferences).
i have tried with 1.3 and the refernce prompt in the readme page . for first 3-4 it animates the refernce image itself , ill try bumping up the strenght to 2.5 and give it a try
please update this for wan2gp please please