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
I have a simple question regarding the workflow "LTX-2.3_-_FML2V_First_Middle_Last_Frame_guider".
First of all, I am always grateful for the truly useful and effective workflow you have created. My question is, would adding intermediate frames significantly reduce the workflow's efficiency? I find this workflow very useful, but one thing I find lacking is that I think it would be even better if there were a few more intermediate guide frames.
Yes can definitively be creative with even more frames.
I guess it comes a bit down to "lazy" and just prompt, and not input too many images, but definitively can.
Might add a workflow variant with more frames... reminds be a bit of Wan days ;-( wan video above, even if that was extremely short video above, due to being wan, its dead accurate animation)
(the guider nodes already in the FLMF workflow can easily be changed to have more image inputs. and the index value is the frame number you want it to be at)
Its a little more work to create the input images, but the reward might be worth it, since you can direct it more ;-)