---
title: LTX-Video-ICLoRA-pose-13b-0.9.7
canonical_url: "https://www.modelscope.cn/models/Lightricks/LTX-Video-ICLoRA-pose-13b-0.9.7"
md_url: "https://www.modelscope.cn/models/Lightricks/LTX-Video-ICLoRA-pose-13b-0.9.7.md"
repository: Lightricks/LTX-Video-ICLoRA-pose-13b-0.9.7
last_updated: 2025-07-09
license: other
pipeline_tag: text-to-video-synthesis
tasks:
  - text-to-video-synthesis
base_model:
  - Lightricks/LTX-Video-0.9.7-dev
base_model_relation: finetune
parameters: 151.0M
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 366
stars: 0
tags:
  - ltx-video
  - image-to-video
  - text-to-video
---

# LTX-Video-ICLoRA-pose-13b-0.9.7

> LTX-Video-ICLoRA-pose-13b-0.9.7 - Lightricks 在 ModelScope 开源的模型。LTX Video ICLoRA Pose 13B 0.9.7

Lightricks/LTX-Video-ICLoRA-pose-13b-0.9.7 是 ModelScope 魔搭社区上的 151.0M 参数text-to-video-synthesis模型，采用 other 许可，基于 Lightricks/LTX-Video-0.9.7-dev 构建。

- **Repository**: Lightricks/LTX-Video-ICLoRA-pose-13b-0.9.7
- **License**: other
- **Tasks**: text-to-video-synthesis
- **Parameters**: 151.0M
- **Base model**: Lightricks/LTX-Video-0.9.7-dev
- **Tags**: ltx-video, image-to-video, text-to-video
- **Downloads**: 366
- **Stars**: 0
- **Last updated**: 2025-07-09

Source: https://www.modelscope.cn/models/Lightricks/LTX-Video-ICLoRA-pose-13b-0.9.7

---

# LTX Video ICLoRA Pose 13B 0.9.7

This is a pose control model on top of [`LTXV_13B_097_DEV`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-13b-0.9.7-dev.safetensors) trained on custom data.

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

IC LoRA is a method that enables adding video context into the video generation process. This approach allows for video-to-video control on top of the text-to-video model, providing more precise control over the generated content by conditioning the model on reference video frames during inference.

comfy compatible model: [ltxv-097-ic-lora-pose-control-comfyui.safetensors](https://huggingface.co/Lightricks/LTX-Video-ICLoRA-pose-13b-0.9.7/blob/main/ltxv-097-ic-lora-pose-control-comfyui.safetensors)


diffusers compatible model:[ltxv-097-ic-lora-pose-control-diffusers.safetensors](https://huggingface.co/Lightricks/LTX-Video-ICLoRA-pose-13b-0.9.7/blob/main/ltxv-097-ic-lora-pose-control-diffusers.safetensors)

## License

For licensing information, please refer to the [LTXV Open Weights License](LTX-Video-Open-Weights-License-0.X.txt).
## Model Details

- **Base Model:** [`LTXV_13B_097_DEV`](https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-13b-0.9.7-dev.safetensors)
- **Training Type:** IC LoRA training
- **Learning Rate:** 0.0002
- **Rank:** 24

## Sample Outputs


| | | |
|:---:|:---:|:---:|
| ![example1](./samples/sample_0.gif) | ![example2](./samples/sample_1.gif) | ![example3](./samples/sample_2.gif) |

| | |
|:---:|:---:|
| ![example4](./samples/sample_3.gif) | ![example5](./samples/sample_4.gif) |

## Usage

This model is designed to be used with the LTXV (Lightricks Text-to-Video) pipeline.

### 🔌 Using Trained LoRAs in ComfyUI
In order to use the trained lora in comfy:
1. Copy the comfyui trained LoRA weights to the `models/loras` folder in your ComfyUI installation.
2. Use ic_lora/ic-lora.json from [official LTXV ComfyUI repository](https://github.com/Lightricks/ComfyUI-LTXVideo)






## Acknowledgments

- Base model by [Lightricks](https://huggingface.co/Lightricks)
- Training infrastructure: [LTX-Video-Trainer](https://github.com/Lightricks/ltx-video-trainer)