---
base_model:
- Lightricks/LTX-2
datasets:
- Lightricks/Canny-Control-Dataset
language:
- en
license: other
license_name: ltx-2-community-license
license_link: https://www.github.com/Lightricks/LTX-2/LICENSE
pipeline_tag: any-to-any
tags:
- ltx-video
- image-to-video
- text-to-video
pinned: true
---

# LTX-2 19B IC-LoRA Canny Control

This is a Canny control IC-LoRA trained on top of **LTX-2-19b**, enabling structure-preserving video generation from text and reference frames.

It is based on the [LTX-2](https://huggingface.co/papers/2601.03233) foundation model.

- **Paper:** [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://huggingface.co/papers/2601.03233)
- **Code:** [GitHub Repository](https://github.com/Lightricks/LTX-2)
- **Project Page:** [LTX-2 Playground](https://app.ltx.studio/ltx-2-playground/i2v)

## What is In-Context LoRA (IC LoRA)?

IC 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 intial image for image-to-video, and generate audio-visual output.

## Model Files

`ltx-2-19b-ic-lora-canny-control.safetensors`

## License

See the **LTX-2-community-license** for full terms.

## Model Details

- **Base Model:** LTX-2-19b Video
- **Training Type:** IC LoRA
- **Control Type:** Canny edge conditioning

### 🔌 Using in ComfyUI
1. Copy the LoRA weights into `models/loras`.
2. Use the official IC-LoRA workflow from the [LTX-2 ComfyUI repository](https://github.com/Lightricks/ComfyUI-LTXVideo/).

## Dataset

The model was trained using the [Lightricks/Canny-Control-Dataset](https://huggingface.co/datasets/Lightricks/Canny-Control-Dataset/).

## Citation

```bibtex
@article{hacohen2025ltx2,
  title={LTX-2: Efficient Joint Audio-Visual Foundation Model},
  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},
  journal={arXiv preprint arXiv:2601.03233},
  year={2025}
}
```

## Acknowledgments

- Base model by **Lightricks**
- Training infrastructure: **LTX-2 Community Trainer**