Instructions to use RuneXX/LTX-2-Workflows with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX.io
How to use RuneXX/LTX-2-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-Workflows --local-dir models/LTX-2-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-Workflows/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2-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-Workflows/<checkpoint>.safetensors \ --distilled-lora models/LTX-2-Workflows/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2-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
hi, any idea why the change?
#20
by Lora-Daddy - opened
is there supposed to be a difference in the new node setup? not 100% sure why its changed
yes, although it seems like ComfyUI reverted the changes, for a limited time... so the "old" workflows might still work for a bit longer
https://github.com/Comfy-Org/ComfyUI/commit/84aba95e03c6498f9e73df100cbcde9d14128ea9
But yes either already or soon, the logic in ComfyUI has/will be changed.
And for that the workflows needs a new model loader logic. ( I am updating mine)
the changes are not drastical, basically just a new way of loading the model with a different node.
You can see what the changes are here: https://huggingface.co/Kijai/LTXV2_comfy
As to WHY the change, no idea ;-)
