---
title: LTX-2.3-22b-IC-LoRA-LipDub
canonical_url: "https://www.modelscope.cn/models/Lightricks/LTX-2.3-22b-IC-LoRA-LipDub"
md_url: "https://www.modelscope.cn/models/Lightricks/LTX-2.3-22b-IC-LoRA-LipDub.md"
repository: Lightricks/LTX-2.3-22b-IC-LoRA-LipDub
last_updated: 2026-10-22
license: other
pipeline_tag: any-to-any
tasks:
  - any-to-any
base_model:
  - Lightricks/LTX-2.3
base_model_relation: finetune
parameters: 1.2B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 1563
stars: 4
tags:
  - ltx-video
  - video-to-video
  - dubbing
  - ic-lora
  - dub-it
---

# LTX-2.3-22b-IC-LoRA-LipDub

> LTX-2.3-22b-IC-LoRA-LipDub - Lightricks 在 ModelScope 开源的模型。LTX-2.3 22B IC-LoRA Dub-It

Lightricks/LTX-2.3-22b-IC-LoRA-LipDub 是 ModelScope 魔搭社区上的 1.2B 参数any-to-any模型，采用 other 许可，基于 Lightricks/LTX-2.3 构建。

- **Repository**: Lightricks/LTX-2.3-22b-IC-LoRA-LipDub
- **License**: other
- **Tasks**: any-to-any
- **Parameters**: 1.2B
- **Base model**: Lightricks/LTX-2.3
- **Tags**: ltx-video, video-to-video, dubbing, ic-lora, dub-it
- **Downloads**: 1563
- **Stars**: 4
- **Last updated**: 2026-10-22

Source: https://www.modelscope.cn/models/Lightricks/LTX-2.3-22b-IC-LoRA-LipDub

---

# LTX-2.3 22B IC-LoRA Dub-It

This is an IC-LoRA trained on top of **LTX-2.3-22b**, enabling lip dubbing on top of the LTX model.

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

*   **Project Page:** [JustDubIt project page](https://justdubit.github.io/)
*   **Paper:** [JustDubIt paper](https://arxiv.org/abs/2601.22143)
*   **Code:** [GitHub Repository](https://github.com/Lightricks/LTX-2)
*   **Inference Pipeline:** [`packages/ltx-pipelines/src/ltx_pipelines/lipdub.py`](https://github.com/Lightricks/LTX-2/blob/main/packages/ltx-pipelines/src/ltx_pipelines/lipdub.py)

## Model Files

`ltx-2.3-22b-ic-lora-lipdub-0.9.safetensors`

## License

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

## Model Details

*   **Base Model:** LTX-2.3
*   **Training Type:** IC-LoRA
*   **Control Type:** Video & Audio
*   **Reference Downscale Factor:** 1 (reference resolution is the same as output resolution)

### 🔌 Using in ComfyUI

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

## Dataset

The model was trained using a lip-dubbing dataset.

## Citation

```bibtex
@article{chen2026just,
  title={JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion},
  author={Chen, Anthony and Korem, Naomi Ken and Zeevi, Gal and Halperin, Tavi and Yosef, Matan Ben and Jelercic, Urska and Bibi, Ofir and Patashnik, Or and Cohen-Or, Daniel},
  journal={arXiv preprint arXiv:2601.22143},
  year={2026}
}
```

## Acknowledgments

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