This is a motion track control IC-LoRA trained on top of
LTX-2.3-22b, enabling the user to guide the motion of objects or regions in a generated video using sparse point trajectories.
The user provides a reference video with colored spline overlays indicating desired motion paths, and the model generates a video that follows these trajectories.
Tracks can be extracted from existing videos using point tracking methods such as SpatialTrackerV2 or drawn manually.
For drawing manually we provide the trajectory drawing node in ComfyUI. See
example workflowIC LoRA enables conditioning video generation on reference video frames at inference time, allowing fine-grained video-to-video control on top of a text-to-video, base model.
It allows also the usage of an initial image for image-to-video, and generate audio-visual output.
IC LoRA uses a reference control signal, i.e. a video that is positionally aligned to the generated video and contains the reference for context.
To allow for added efficiency, the reference video can be smaller, so it consumes less tokens.
The reference downscale factor determines the expected downscaling of the reference video compared to the generated resolution.
To signify the expected reference size, the checkpoint name will have a 'ref' denominator followed by the scale relative to the output resolution.
The model was trained using a proprietary dataset.
1@article{hacohen2025ltx2,
2 title={LTX-2: Efficient Joint Audio-Visual Foundation Model},
3 author={HaCohen, Yoav and Brazowski, Benny and Chiprut, Nisan and Bitterman, Yaki and Kvochko, Andrew and Berkowitz, Avishai and Shalem, Daniel and Lifschitz, Daphna and Moshe, Dudu and Porat, Eitan and others},
4 journal={arXiv preprint arXiv:2601.03233},
5 year={2025}
6}
7@misc{LTXVideoTrainer2025,
8 title={LTX-Video Community Trainer},
9 author={Matan Ben Yosef and Naomi Ken Korem and Tavi Halperin},
10 year={2025},
11 publisher={GitHub},
12}
