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
Same workflows for 2.5
Not sure why it wouldn't be possible to use your current workflows for the newer 2.5. I figured it just needs one or two things removed/disabled in order to function. I tried just going with a clip loader instead of your dual seeing as there is no text projection file currently for 2.5. I also disabled LTX2 NAG but still get an error when trying to generate. Any suggestions?
Not sure why it wouldn't be possible to use your current workflows for the newer 2.5. I figured it just needs one or two things removed/disabled in order to function. I tried just going with a clip loader instead of your dual seeing as there is no text projection file currently for 2.5. I also disabled LTX2 NAG but still get an error when trying to generate. Any suggestions?
yes, use comfy templates in the mean time....
Not sure why it wouldn't be possible to use your current workflows for the newer 2.5. I figured it just needs one or two things removed/disabled in order to function. I tried just going with a clip loader instead of your dual seeing as there is no text projection file currently for 2.5. I also disabled LTX2 NAG but still get an error when trying to generate. Any suggestions?
maybe just change the nodes,,,,,
Not sure why it wouldn't be possible to use your current workflows for the newer 2.5. I figured it just needs one or two things removed/disabled in order to function. I tried just going with a clip loader instead of your dual seeing as there is no text projection file currently for 2.5. I also disabled LTX2 NAG but still get an error when trying to generate. Any suggestions?
i did it, i just changed the nodes of the models, and it works well!!!
Sweet, thanks for posting the solution. Will be about an hour before I can try it. Hopefully all goes well for me too.
Odd, when I made my initial post I hadn't downloaded all the models yet for 2.5. I was just testing 2.3 without the text projector. That's when I got the error. I just assumed that 2.3 could work without it. I have the same settings but changed it all to 2.5 models and it now works. I guess 2.3 needs that projector by default.
