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

nvfp4 ?

#25

by lanranjun - opened Mar 12

Discussion

lanranjun

Mar 12

Have you ever used the LTX-2.3 NVFP4 version large model? How effective is it?
ltx-2.4 nvfp4 + gemma 12b fp4

RuneXX

Owner Mar 12

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 Apr 24

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment