Instructions to use Lightricks/LTX-2.3-22b-IC-LoRA-Relight 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-Relight 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-Relight 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-Relight --local-dir models/LTX-2.3-22b-IC-LoRA-Relight 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-Relight/<weights>.safetensors 1.0 \ --video-conditioning reference.mp4 1.0 \ --prompt "your prompt here" \ --output-path output.mp4 - Notebooks
- Google Colab
- Kaggle
Feedback
#2
by 129loopback - opened
This is a great lora when it comes to lighting. 10/10 for changing the lighting.
Unfortunately, this also changes subject and background. Face of characters get changed. Also its adding some random outside background into most scenes.
If possible add inside video into training data for next version.
Thank you so much for this Lora.
@129loopback can you share a sample render where you're seeing subject changes?
@rluxemburg Please see the link for output videos, source videos and workflow.
Mirror: https://gofile.io/d/qZE4l5