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

Workflow : Extend Any Video

#28

by RuneXX - opened Mar 13

Discussion

RuneXX

Owner Mar 13

•

edited Mar 13

V2V - Extend Any Video

A great way to make your LTX-2.3 videos longer (and longer...)
Generate a video, then extend it (and steer it with prompt to make your story).

For example input a 10 second LTX video, run the workflow to make it 20 seconds.
You can do this process again, and again.. should you want clips to be even longer.

It only uses last part of the input video, so it should be quite light on the pc, to extend in incremental steps.

Not limited to LTX video as input, it can be any video... like The Joker above ;-)
Uses LTX "ReTake" sort of feature with KJNodes LTX AudioVideo masking, to keep motion, looks, and voice consistent for extended part

https://huggingface.co/RuneXX/LTX-2.3-Workflows/

DarkSty1eG0dz

Mar 25

Hi really nice workflow, if i want to choose to extend the beginning or the end of the video how can i do?

RuneXX

Owner Mar 25

Hi really nice workflow, if i want to choose to extend the beginning or the end of the video how can i do?

Was playing around with that.. Extend beginning, end... or middle ("retake/reshoot")
Will try see if i can make it work well ;-)

Perfs

Apr 3

how to lock the face and not drift it as the extended part collapse the face of the joker here..

RuneXX

Owner Apr 3

how to lock the face and not drift it as the extended part collapse the face of the joker here..

Its unfortunately at bit of face drift with LTX. Maybe some future lora will help with that

DarkSty1eG0dz

Apr 17

Hi really nice workflow, if i want to choose to extend the beginning or the end of the video how can i do?

Was playing around with that.. Extend beginning, end... or middle ("retake/reshoot")
Will try see if i can make it work well ;-)

Sorry but this retake/reshoot replaces parts of the original video dont extend the beginning or the middle of the video... :-(

RuneXX

Owner Apr 17

Sorry but this retake/reshoot replaces parts of the original video dont extend the beginning or the middle of the video... :-(

Yes exactly. Retake is to reshoot part of the video, within the video.

The workflow could likely be combined with extending also. But for now if you want to extend a video, use the extend video workflow ;-)
https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main/Video-2-Video

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