Instructions to use RuneXX/LTX-2.3-2.5-Workflows with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX.io
How to use RuneXX/LTX-2.3-2.5-Workflows 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 RuneXX/LTX-2.3-2.5-Workflows --local-dir models/LTX-2.3-2.5-Workflows 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-2.3-2.5-Workflows/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2.3-2.5-Workflows/<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-2.3-2.5-Workflows/<checkpoint>.safetensors \ --distilled-lora models/LTX-2.3-2.5-Workflows/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2.3-2.5-Workflows/<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
Workflow : I2V & T2V - transfer body movements from reference video with IC-RealisDance lora
I2V & T2V - transfer body movements from reference video with IC-RealisDance lora
A nice alternative to the LTX Ic-Control lora many is probably familiar with.
And it uses a video input to drive the body movements, and a reference image to transfer the pose to.
Can often give more "natural" results, and less forcing the frame to change to adapt to the pose input.
LTX seems to work best with close up and not too fast motions, so might not do the most crazy tik-tok routines ;-)
(or you can try more steps, dev model, or even single pass if trying more "crazy" stuff)
In the workflow you can choose between LTX audio, custom audio input, or using the audio from the input video.
And the workflow has an easy toggle to choose between DW Pose and SD Pose.
For the lora, download the RealisDance here : https://huggingface.co/Kijai/LTX2-IC-LoRAs
Feel free to play around with it ;-)
https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main/Control-reference