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
Hello, RUNE - i notice a new WF of CONTROL LORA - can i do a tango dance with this?
my friends love my LIPSYNCHS, but they want a change, they want me to put a woman we know dancing tango.... can this be done with any of these WF of control DW or SD pose? using a reference video and image?
Yes. If I understood you correctly
It will take an input image. And make it move to the body movements of an input video
So in this case the input image could be the woman, and the input video could be the tango dance.
with one caveat. Its a one character workflow. For multiple characters it becomes more complicated, and will add something for that as soon as some of the new stuff Kijai has made is added into ComfyUI (Sam3 and/or multi character skeleton pose)
Or actually two caveats, LTX is not the best on fast movements (might be better if using DEV mode though). But tango dance might be slow enough ;-)
And it will help a lot if your friends photo is somewhat similar to that of the first frame of the input video (framing, pose).
I am making version of the workflow where Flux Klein will reposition the input image to match the first frame, will add that soon. It should work even better ;-)