---
title: LTX-2-19b-IC-LoRA-Detailer
canonical_url: "https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer"
md_url: "https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer.md"
repository: Lightricks/LTX-2-19b-IC-LoRA-Detailer
last_updated: 2026-03-30
license: other
base_model:
  - Lightricks/LTX-2
base_model_relation: finetune
parameters: 1.3B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 1855
stars: 2
tags:
  - ltx-video
  - video-to-video
---

# LTX-2-19b-IC-LoRA-Detailer

> LTX-2-19b-IC-LoRA-Detailer - Lightricks 在 ModelScope 开源的模型。LTX-2 19B IC-LoRA Detailer

Lightricks/LTX-2-19b-IC-LoRA-Detailer 是 ModelScope 魔搭社区上的 1.3B 参数机器学习模型，采用 other 许可，基于 Lightricks/LTX-2 构建。

- **Repository**: Lightricks/LTX-2-19b-IC-LoRA-Detailer
- **License**: other
- **Parameters**: 1.3B
- **Base model**: Lightricks/LTX-2
- **Tags**: ltx-video, video-to-video
- **Downloads**: 1855
- **Stars**: 2
- **Last updated**: 2026-03-30

Source: https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer

---

# LTX-2 19B IC-LoRA Detailer

This is a video detailer IC-LoRA trained on top of **LTX-2-19b**, designed to enhance fine details and textures in generated videos.

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

IC LoRA enables conditioning video generation on reference video frames at inference time, allowing fine-grained refinement on top of a text-to-video base model.  

## Model Files

`ltx-2-19b-ic-lora-detailer.safetensors`

## License

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

## Model Details

- **Base Model:** LTX-2-19b Video
- **Training Type:** IC LoRA
- **Purpose:** Video detail refinement
- **Paper:** [AVControl: Efficient Framework for Training Audio-Visual Controls](https://huggingface.co/papers/2603.24793)
- **Code:** [GitHub Repository](https://github.com/Lightricks/LTX-2)
- **Project Page:** [AVControl project page](https://matanby.github.io/AVControl/)

### 🔌 Using in ComfyUI
1. Copy the LoRA weights into `models/loras`.
2. Use the official IC-LoRA workflow from the LTX-2 ComfyUI repository.

## Acknowledgments

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