| --- |
| base_model: |
| - Lightricks/LTX-2.3 |
| 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-2.3 22B IC-LoRA Union Control |
|
|
| This is a unified control IC-LoRA trained on top of **LTX-2.3-22b**, 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://console.ltx.video/playground/) |
|
|
| ## 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-2.3-22b-ic-lora-union-control-ref0.5.safetensors` |
|
|
| ## License |
|
|
| See the **LTX-2-community-license** for full terms. |
|
|
| ## Model Details |
|
|
| - **Base Model:** LTX-2.3-22b 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** |
