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 : V2V - Create a new viewpoint angle from any video with CrossView Lora
V2V - Create a new viewpoint angle from any video with CrossView Lora
Crossview lora from @Cseti acts as a virtual second camera: give it a reference video and a short camera-angle prompt, and it re-renders the same scene from the requested new viewpoint keeping the subject and content, changing where the camera stands.
The lora is at version 0.9 and proof-of concept. Results may vary but feel free to experiment and try it out ;-)
The default in the workflow is set to Distilled model for fast generations.
For better results do change to Dev model, and set the steps in first pass higher (try 15 or so), and CFG to 1,5-3. (easy to change this in the workflow)
Optionally also toggle the "Single Pass" switch at bottom of workflow
Download the lora from here:
https://huggingface.co/Cseti/LTX2.3-22B_IC-LoRA-CrossView-Prompt
Workflow:
https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main/Video-2-Video
(also a workflow in the repo of the lora)
He released another version with custom nodes that lets you control the camera across the entire clip! https://huggingface.co/Cseti/LTX2.3-22B_IC-LoRA-CrossView-Warp
He released another version with custom nodes that lets you control the camera across the entire clip! https://huggingface.co/Cseti/LTX2.3-22B_IC-LoRA-CrossView-Warp
Think he is making a new node as well, to make things even easier. Will check it out asap ; -)