Image-to-Video
LTX.io
GGUF
ltx-2
comfyui
comfy
ltx-video
ltx-2-3
ltxv
text-to-video
audio-to-video
video-to-video
Instructions to use RuneXX/LTX-2.3-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-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-Workflows --local-dir models/LTX-2.3-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-Workflows/<distilled-checkpoint>.safetensors \ --spatial-upsampler-path models/LTX-2.3-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-Workflows/<checkpoint>.safetensors \ --distilled-lora models/LTX-2.3-Workflows/<distilled-lora>.safetensors 0.8 \ --spatial-upsampler-path models/LTX-2.3-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
Workflow: V2V - Extend Any Video towards Last Frame reference image
#137
by RuneXX - opened
V2V - Extend Any Video towards Last Frame reference image
By request, a variant of extend any video, where you can input a last frame image to guide the extend towards.
The workflow comes with 2 types of end target:
- Guider: End frame image as guide, but with freedom for the model to give a natural result (might not always end exactly on end frame)
- Frame Injection: Inject last frame as image in the video, forcing the model to end on the exact image
(but since the image is made in other models, sometimes a little flicker at end (that you can edit out)
With both single pass and 2-pass option.
Single pass will always be the most faithful to the input image, 2-pass is faster, and can add more details and enhance your input image.
Up to you ;-)
Can try it out here:
https://huggingface.co/RuneXX/LTX-2.3-Workflows/tree/main/Video-2-Video