Instructions to use RuneXX/LTX-2.3-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-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-Workflows --local-dir models/LTX-2.3-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-Workflows/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2.3-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-Workflows/<checkpoint>.safetensors \ --distilled-lora models/LTX-2.3-Workflows/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2.3-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
LTX2.3-Mutiple-Subject-Reference (new IC lora model)
With this we can add multiple image references and make a video out of it. I did not test it yet because in his workflow he using not the transformer only model but the full distilled model with vae included and i have no space right now. Would be nice if u can add a new workflow for this great thing: https://huggingface.co/LiconStudio/LTX2.3-Mutiple-Subject-Reference
Looks very interesting for sure. Tried it, and works pretty well.
(and this is an early version lora, so it might even improve)
Will make a wf so its easy to try it out ;-)
(and the result in the video below is just a test run, probably not clear enough prompting since its a bit of leak between the characters.. only a first low res test run .. ;-)
Thank you so much <3. That would definitely be one of the best features in a long time. A major step toward cameos like in Sora 2—but not just that; it enables so much more if you can actually use multiple images as references. I love this community. Can't wait to try it with ur workflow.
Workflow added to try out https://huggingface.co/RuneXX/LTX-2.3-Workflows/discussions/167
Its an early test lora, so improvements might come. It's not a strong subject consistency .,.. yet. But a very promising lora for sure ;-)