Image-to-Video
LTX.io
GGUF
ltx-2
comfyui
comfy
ltx-video
ltx-2-3
ltx-2.5
ltxv
text-to-video
audio-to-video
video-to-video
Instructions to use RuneXX/LTX-2.3-2.5-Workflows with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX.io
How to use RuneXX/LTX-2.3-2.5-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-2.3-2.5-Workflows --local-dir models/LTX-2.3-2.5-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-2.3-2.5-Workflows/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2.3-2.5-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-2.3-2.5-Workflows/<checkpoint>.safetensors \ --distilled-lora models/LTX-2.3-2.5-Workflows/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2.3-2.5-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
FLF2V with different model
#184
by malfy - opened
Hey RuneXX your FLF2V workflow is awesome. I use a completely different I2V workflow to the LTX2.3-10Eros model for.. well the only reason to use that model, but I can't seem to adapt your FLF2V workflow to use it. Any interest in helping me figure it out, heh? π
nvm figured it out, sorry to bother
malfy changed discussion status to closed
Not bothering ;-) and late reply ... its a bit of hot summer days.. ;-)
Good that you figured it out. You can do it 2 ways :
- change to checkpoint loader (instead of diffusion model loader, that is made for split models). There is a checkpoint example workflow here you can look at, on how that works.
- get the transformer only version of eros, that works in any and all workflows here without any change needed
;- )
Or even a 3rd way, just use the extracted lora, instead of the full eros model.
And use the lora with regular LTX as models..
https://huggingface.co/maximsobolev275/LTX-10Eros-LoRA-r768/