Instructions to use RuneXX/LTX-2.3-Workflows with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RuneXX/LTX-2.3-Workflows with LTX-2:

# Install the LTX-2 pipelines
git clone https://github.com/Lightricks/LTX-2.git
cd LTX-2
uv sync --extra natten

# Download weights from this repo
# Substitute filenames from this repo's "Files and versions" if they differ
hf download RuneXX/LTX-2.3-Workflows \
    diffusion_models/<distilled-transformer>.safetensors \
    text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    vae/<video-vae>.safetensors \
    vae/<audio-vae>.safetensors \
    latent_upscale_models/<spatial-upsampler>.safetensors \
    latent_upscale_models/<temporal-upsampler>.safetensors \
    --local-dir models/LTX-2.3-Workflows
# DFR requires the detailing IC-LoRA (separate repo; strength is fixed at 0.5)
hf download Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler --local-dir models/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler

# Distilled LTX-2.5 pipeline (fast)
uv run python -m ltx_pipelines.distilled \
    --transformer-path models/LTX-2.3-Workflows/diffusion_models/<distilled-transformer>.safetensors \
    --text-encoder-path models/LTX-2.3-Workflows/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    --video-vae-path models/LTX-2.3-Workflows/vae/<video-vae>.safetensors \
    --audio-vae-path models/LTX-2.3-Workflows/vae/<audio-vae>.safetensors \
    --spatial-upsampler-path models/LTX-2.3-Workflows/latent_upscale_models/<spatial-upsampler>.safetensors \
    --num-frames 121 \
    --prompt "A beautiful sunset over the ocean" \
    --output-path output.mp4
# For image-to-video, add: --image path/to/image.jpg 0 0.8

# DFR pipeline (higher detail fidelity; optional temporal 2x/4x)
uv run python -m ltx_pipelines.dfr_pipeline \
    --transformer-path models/LTX-2.3-Workflows/diffusion_models/<distilled-transformer>.safetensors \
    --text-encoder-path models/LTX-2.3-Workflows/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    --video-vae-path models/LTX-2.3-Workflows/vae/<video-vae>.safetensors \
    --audio-vae-path models/LTX-2.3-Workflows/vae/<audio-vae>.safetensors \
    --spatial-upsampler-path models/LTX-2.3-Workflows/latent_upscale_models/<spatial-upsampler>.safetensors \
    --temporal-upsampler-path models/LTX-2.3-Workflows/latent_upscale_models/<temporal-upsampler>.safetensors \
    --detailing-lora models/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler/ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors \
    --spatial-upscalings 1 \
    --temporal-upscalings 1 \
    --height 1088 \
    --width 1920 \
    --num-frames 121 \
    --prompt "A beautiful sunset over the ocean" \
    --output-path output.mp4
# For 4K: --spatial-upscalings 2 --width 3840 --height 2176
# For image-to-video, add: --image path/to/image.jpg 0 0.8

Notebooks
Google Colab
Kaggle

How to use from the

Use from the

LTX-2 library

# Install the LTX-2 pipelines
git clone https://github.com/Lightricks/LTX-2.git
cd LTX-2
uv sync --extra natten

# Download weights from this repo
# Substitute filenames from this repo's "Files and versions" if they differ
hf download RuneXX/LTX-2.3-Workflows \
    diffusion_models/<distilled-transformer>.safetensors \
    text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    vae/<video-vae>.safetensors \
    vae/<audio-vae>.safetensors \
    latent_upscale_models/<spatial-upsampler>.safetensors \
    latent_upscale_models/<temporal-upsampler>.safetensors \
    --local-dir models/LTX-2.3-Workflows
# DFR requires the detailing IC-LoRA (separate repo; strength is fixed at 0.5)
hf download Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler --local-dir models/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler

# Distilled LTX-2.5 pipeline (fast)
uv run python -m ltx_pipelines.distilled \
    --transformer-path models/LTX-2.3-Workflows/diffusion_models/<distilled-transformer>.safetensors \
    --text-encoder-path models/LTX-2.3-Workflows/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    --video-vae-path models/LTX-2.3-Workflows/vae/<video-vae>.safetensors \
    --audio-vae-path models/LTX-2.3-Workflows/vae/<audio-vae>.safetensors \
    --spatial-upsampler-path models/LTX-2.3-Workflows/latent_upscale_models/<spatial-upsampler>.safetensors \
    --num-frames 121 \
    --prompt "A beautiful sunset over the ocean" \
    --output-path output.mp4
# For image-to-video, add: --image path/to/image.jpg 0 0.8

# DFR pipeline (higher detail fidelity; optional temporal 2x/4x)
uv run python -m ltx_pipelines.dfr_pipeline \
    --transformer-path models/LTX-2.3-Workflows/diffusion_models/<distilled-transformer>.safetensors \
    --text-encoder-path models/LTX-2.3-Workflows/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors \
    --video-vae-path models/LTX-2.3-Workflows/vae/<video-vae>.safetensors \
    --audio-vae-path models/LTX-2.3-Workflows/vae/<audio-vae>.safetensors \
    --spatial-upsampler-path models/LTX-2.3-Workflows/latent_upscale_models/<spatial-upsampler>.safetensors \
    --temporal-upsampler-path models/LTX-2.3-Workflows/latent_upscale_models/<temporal-upsampler>.safetensors \
    --detailing-lora models/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler/ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors \
    --spatial-upscalings 1 \
    --temporal-upscalings 1 \
    --height 1088 \
    --width 1920 \
    --num-frames 121 \
    --prompt "A beautiful sunset over the ocean" \
    --output-path output.mp4
# For 4K: --spatial-upscalings 2 --width 3840 --height 2176
# For image-to-video, add: --image path/to/image.jpg 0 0.8

LTX-2.5

LTX-2.5: All models can be downloaded here: https://huggingface.co/Lightricks/LTX-2.5
LTX-2-5 is already "split files" from the official source, and they work out of the box with the workflows here.

LTX-2.5 also works with most LTX-2.3 loras and is quite backwards compatible. Dedicated LTX-2.5 workflows are coming asap ;-) (but feel free to use LTX-2.3 workflows with the LTX-2.5 models. Most all should work)

LTX-2.3

LTX-2.3: The workflows are based on the extracted models from https://huggingface.co/Kijai/LTX2.3_comfy The extracted models might run easier on your computer (as separate files). (but you can easily swap out the model loader for the ComfyUI default model loader if you want to load the checkpoint with "all in one" vae built-in etc)

LTX-2.3 Main Model Downloads (split models):

Main split models used in these workflows (LTX-2.3 dev & distilled safetensor, embeddings, audio & video vae & tiny vae): https://huggingface.co/Kijai/LTX2.3_comfy

Gemma - either safetensor or GGUF:

Gemma 3 12B it safetensor: https://huggingface.co/Comfy-Org/ltx-2/tree/main/split_files/text_encoders
Gemma 3 12B it GGUF: https://huggingface.co/unsloth/gemma-3-12b-it-GGUF/

Upscale Model

ltx-2.3-spatial-upscaler (only need the 2x file) - : https://huggingface.co/Lightricks/LTX-2.3/tree/main

LTX-2.3 GGUF models (for GGUF workflows) - one of the source below:

Quantstack: https://huggingface.co/QuantStack/LTX-2.3-GGUF
Unsloth : https://huggingface.co/unsloth/LTX-2.3-GGUF
Vantage : https://huggingface.co/vantagewithai/LTX-2.3-GGUF

Tiny Vae by madebyollin (for sampler previews): (Optional/Recommended. Without this vae you still get previews with latentrgb from KJnodes, at a lower res)

If you are unsure where to put the files see here

Needed nodes:

https://github.com/kijai/ComfyUI-KJNodes (NB! Must be up to date for LTX-2 support)
https://github.com/city96/ComfyUI-GGUF (NB! Must be up to date for LTX-2 support)
ComfyUI itself must be updated to very latest

LTX-2.3

Lighttricks LTX-2.3 main repro: https://huggingface.co/Lightricks/LTX-2.3
Lightricks LTX-2.3 Collection (loras etc): https://huggingface.co/collections/Lightricks/ltx-23

More workflows :

ComfyUI Official Workflows : https://blog.comfy.org/p/ltx-23-day-0-supporte-in-comfyui

LTX-2 Video Official Workflows : https://github.com/Lightricks/ComfyUI-LTXVideo/tree/master/example_workflows/2.3

For ComfyUI's new "app mode" some to try here: https://huggingface.co/WanApp

Downloads last month: -