| | --- |
| | base_model: |
| | - Lightricks/LTX-2 |
| | datasets: |
| | - Lightricks/Canny-Control-Dataset |
| | language: |
| | - en |
| | license: other |
| | license_name: ltx-2-community-license |
| | license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE |
| | pipeline_tag: any-to-any |
| | tags: |
| | - ltx-video |
| | - image-to-video |
| | - text-to-video |
| | pinned: true |
| | --- |
| | |
| | # LTX-2 19B IC-LoRA Union Control |
| |
|
| | This is a unified control IC-LoRA trained on top of **LTX-2-19b**, enabling multiple control signals to be used for video generation from text and reference frames. |
| | It was trained with downscaled reference latents by a factor of 2. |
| |
|
| | 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 initial image for image-to-video, and generate audio-visual output. |
| |
|
| | ## What is Reference Downscale Factor? |
| |
|
| | 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. |
| |
|
| | ## Model Files |
| |
|
| | `ltx-2-19b-ic-lora-union-control-ref0.5.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:** Union conditioning - Canny + Depth + Pose |
| | - **Reference Downscale Factor:** 2 (reference resolution is 0.5x the output resolution) |
| |
|
| | ### 🔌 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/). |
| | 3. Make sure to use the nodes supporting Reference Downscale Factor: LTXICLoRALoaderModelOnly to load the lora and extract the downscale factor, and LTXAddVideoICLoRAGuide to add the small latent as a guide. |
| |
|
| |
|
| | ## Dataset |
| |
|
| | The model was trained using the [Lightricks/Canny-Control-Dataset](https://huggingface.co/datasets/Lightricks/Canny-Control-Dataset/) amongst others. |
| |
|
| | ## 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} |
| | } |
| | @misc{LTXVideoTrainer2025, |
| | title={LTX-Video Community Trainer}, |
| | author={Matan Ben Yosef and Naomi Ken Korem and Tavi Halperin}, |
| | year={2025}, |
| | publisher={GitHub}, |
| | } |
| | ``` |
| |
|
| | ## Acknowledgments |
| |
|
| | - Base model by **Lightricks** |
| | - Training infrastructure: **LTX-2 Community Trainer** |
