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
long video bad
LTX-2.3_-I2V_T2V_Long_Video_Custom_Audio.json
and
LTX-2.3-_I2V_T2V_Long_Video_Custom_Audio_Loop.json
I noticed that there is a blurring and flickering issue in the video starting from the second paragraph
yes, i noticed that could happen. It a challenge with any video model. Will take a look, was going to clean up a bit, so will see if there is room for improvements
yes, i noticed that could happen. It a challenge with any video model. Will take a look, was going to clean up a bit, so will see if there is room for improvements
what nodes do i have to delete to not use custom audio? setting to "false" is not generating anything, the nodes are marked in red
what nodes do i have to delete to not use custom audio? setting to "false" is not generating anything, the nodes are marked in red
The workflow was heavily focused on singer type of long shots. I might have forgotten that bypass. Will check.
In process of updating those long video workflows, and will be much lighter, simpler and work quite a lot better (as far as consistency, color etc)
(already uploaded a single pass variant today that is improved, but this one also dont have bypass custom audio. Will add ;-))
I noticed that there is a blurring and flickering issue in the video starting from the second paragraph
Try the new singlepass workflow. Should be working better ;-)
(will update the regular 2-pass long video ones asap too)
Can see example from single pass at bottom of thread here https://huggingface.co/RuneXX/LTX-2.3-Workflows/discussions/27
Is it recommended to use single sampling for video extension
Is it recommended to use single sampling for video extension
Depends on who you ask I guess. Both work fine ;-)
But will updated the 2-pass sampling as well, for long videos