Instructions to use RuneXX/LTX-2-Workflows with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX.io
How to use RuneXX/LTX-2-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-Workflows --local-dir models/LTX-2-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-Workflows/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2-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-Workflows/<checkpoint>.safetensors \ --distilled-lora models/LTX-2-Workflows/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2-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
Im unable to use latent preview with the workflows.
4
#27 opened 3 months ago
by
pheonis
Still image instead of video
9
#26 opened 5 months ago
by
PopHorn1956
AttributeError: 'NoneType' object has no attribute 'endswith'
3
#25 opened 5 months ago
by
fzshyi
Has ltx-2-3 been released?
10
#24 opened 5 months ago
by
lanranjun
Issues After Switching to the New Model Loading Logic
2
#22 opened 5 months ago
by
yc199849
wow new workflow
8
#21 opened 5 months ago
by
lanranjun
hi, any idea why the change?
1
#20 opened 5 months ago
by
Lora-Daddy
SimpleCalculatorKJ SimpleCalculatorKJ.calculate() got an unexpected keyword argument 'variables.a'
9
#19 opened 6 months ago
by
alexloops
Workflow Request: LTX-2 V2V + I2V Hybrid with First-Frame Masked Character Swap
👍 2
3
#18 opened 6 months ago
by
okims
Discoloration at higher resolutions
6
#16 opened 6 months ago
by
w33bgen
audio and image to video
22
#15 opened 6 months ago
by
lanranjun
Question about First / Middle / Last Frame Workflow Based on LTX-2 Simple (1-pass K-Sampler)
❤️ 1
14
#14 opened 6 months ago
by
okims
masked guide frames?
👍 1
1
#13 opened 6 months ago
by
Soykaf
I2V - Talking Avatar workflow
1
#12 opened 6 months ago
by
AbsAnon
Middle frame freeze issue
3
#11 opened 6 months ago
by
Darux
Lipsync issues for vertical videos
3
#10 opened 6 months ago
by
pashka00
workflow v2v form 1 image?
18
#9 opened 6 months ago
by
hydraofm0
Please support VA2V video + audio, and lip-sync.
1
#6 opened 6 months ago
by
sunnyboxs
I2V custom audio + lora = auto lipsync
🚀 1
10
#5 opened 6 months ago
by
f0rkineye
Output files (T2V GGUF)
20
#4 opened 6 months ago
by
f0rkineye
LTX-2 - V2V (extend any video) Can it be changed?
17
#3 opened 7 months ago
by
Lora-Daddy
Checkerboard
11
#2 opened 7 months ago
by
trashkollector