Image-to-Video
LTX.io
GGUF
ltx-2
comfyui
comfy
ltx-video
ltx-2-3
ltx-2.3
ltxv
text-to-video
audio-to-video
video-to-video
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
nvfp4 ?
#25
by lanranjun - opened
Have you ever used the LTX-2.3 NVFP4 version large model? How effective is it?
ltx-2.4 nvfp4 + gemma 12b fp4
Havent used the NVFP4 myself, since my GPU is a bit too old to benefit from that.
But if you have RTX 4xxx or 5xxx it can run well with a much smaller file size.
And Kijai made some input_scaled modes as well that also are for newer graphic cards (Blackwell, RTX 4xxx, 5xxx etc), that can run a lot faster.
https://huggingface.co/Kijai/LTX2.3_comfy/tree/main/diffusion_models
They all do the same thing, so its more about size, and speed.
And if you have the GPU for it worth trying out, specially the input_scaled i saw had some good feedback
RuneXX changed discussion status to closed