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
is there a video upscaling workflow?
How do I upscale an existing video I have using LTX? Do I plug it in "Add IC lora guide" node and then in the workflow after the first generation, use the Latent Upsampling? But can't I do it in the start. Please share a way. Maybe this is obvious so something is not already present but I genuinely want to know. Thank you.
You don't want to upscale using LTX...
You'd be better served by basic upscaling workflows with nodes like SeedVR2 or RTX Video Super Resolution or something like that. Or standalone applications specifically for this, Topaz Video. There are dozens of ways to upscale, but that's not a proper use-case for LTX.
The RTX Video Super Resolution is extremely fast. maybe try that
https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI
Its also a workflow there.
Unless you meant to add details etc. There is a workflow for LTX to "upscale" and add details to a low resolution video input, using a looping sampler.
But if its just regular upscale, the RTX or as mentioned SeedVR2 or FlashVSR are great ways... they all work in comfy.
Thank you to all!