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
Workflow "LTX-2.3_-_I2V_T2V_Dev_Custom_Audio" T2V question
Hi,
I have used the workflow "LTX-2.3_-_I2V_T2V_Dev_Custom_Audio" for I2V. Works great. Now I want to use it for T2V. I have switch on the node "Text To Video (no image ref)". I have uploaded a picture to "Load Image". If I start the workflow, it still performs I2V. Is there a switch I am missing? Do I have to bypass a node?
Thank you for your help.
RuneXX workflows do have a switch for either text or image, its right above the audio section towards the bottom of WF. From my experience, from other WF's, it still needs an image as a placeholder even though the WF will not use. Just use the example.png image that is in your \ComfyUI\ComfyUI\input, as your placeholder, hopefully you have it in there, if not just use anything you have handy.
Could be a slip, that this was not connected to the ImgInPlace bypass.
Will check
Thank you. Noted just know, that it is only in the "LTX-2.3_-I2V_T2V_Basic_ID-Lora_reference_audio" workflow. My bad, works in the "LTX-2.3-_I2V_T2V_Dev_Custom_Audio" workflow.
Will check LTX-2.3_-I2V_T2V_Basic_ID-Lora_reference_audio if maybe something is not connected there ;-)
Your solution does work. LTXVImgToVideoInplace bypass do the trick. Thank you!
Indeed, it was an oversight on that one. In the LTXImgToVideoInPlace (its twice in the workflow), just click the toggle "Bypass"
Uploaded an updated workflow though, so you could also download it again.
Your solution does work. LTXVImgToVideoInplace bypass do the trick. Thank you!
ah yes, you already figured out the manual toggles
The workflows are really great. Thank you for your help!



