---
tags:
- ltx-2
- ltx-video
- text-to-video
- audio-video
- image-to-video
- lora
- safetensors
pinned: true
language:
- en
license: other
pipeline_tag: image-to-video
library_name: diffusers
base_model:
- Lightricks/LTX-2
---

# LTX-2-19b-Squish-LoRA

This is a fine-tuned version of [`ltx-2-19b-dev.safetensors`](/root/LTX-2/packages/ltx-trainer/models/ltx-2-19b-dev.safetensors) trained on custom data.

<!-- ## Model Details -->

<!-- - **Base Model:** [`ltx-2-19b-dev.safetensors`](/root/LTX-2/packages/ltx-trainer/models/ltx-2-19b-dev.safetensors)
- **Training Type:** LoRA fine-tuning
- **Training Steps:** 2000
- **Learning Rate:** 0.0002
- **Batch Size:** 1 -->

<!-- ## Sample Outputs

| | | | |
|:---:|:---:|:---:|:---:|
| ![example1](./samples/sample_0.gif)<br><details style="max-width: 300px; margin: auto;"><summary>Prompt</summary>SQUISH two hands squeezing a squeezable object that is shaped like a woman's head.</details> |
 -->



 | Example 1 | Example 2 |
|---|---|
| <video src="https://huggingface.co/ovi054/LTX-2-19b-Squish-LoRA/resolve/main/samples/001.mp4" controls autoplay loop muted></video> | <video src="https://huggingface.co/ovi054/LTX-2-19b-Squish-LoRA/resolve/main/samples/002.mp4" controls autoplay loop muted></video> |

| Example 3 | Example 4 |
|---|---|
| <video src="https://huggingface.co/ovi054/LTX-2-19b-Squish-LoRA/resolve/main/samples/005.mp4" controls autoplay loop muted></video> | <video src="https://huggingface.co/ovi054/LTX-2-19b-Squish-LoRA/resolve/main/samples/004.mp4" controls autoplay loop muted></video> |

| Example 5 | Example 6 |
|---|---|
| <video src="https://huggingface.co/ovi054/LTX-2-19b-Squish-LoRA/resolve/main/samples/003.mp4" controls autoplay loop muted></video> | <video src="https://huggingface.co/ovi054/LTX-2-19b-Squish-LoRA/resolve/main/samples/006.mp4" controls autoplay loop muted></video> |


## Usage

This model is designed to be used with the LTX-2 (Lightricks Audio-Video) pipeline.

### 🔌 Using Trained LoRAs in ComfyUI

In order to use the trained LoRA in ComfyUI, follow these steps:

1. Copy your trained LoRA checkpoint (`.safetensors` file) to the `models/loras` folder in your ComfyUI installation.
2. In your ComfyUI workflow:
    - Add the "Load LoRA" node to choose your LoRA file
    - Connect it to the "Load Checkpoint" node to apply the LoRA to the base model

You can find reference Text-to-Video (T2V) and Image-to-Video (I2V) workflows in the
official [LTX-2 repository](https://github.com/Lightricks/LTX-2).

### Trigger Word

<!-- Example prompts used during validation: -->

- `squish it`



This model inherits the license of the base model ([`ltx-2-19b-dev.safetensors`](/root/LTX-2/packages/ltx-trainer/models/ltx-2-19b-dev.safetensors)).

## Acknowledgments

- Base model: [Lightricks](https://huggingface.co/Lightricks/LTX-2)
- Trainer: [LTX-2](https://github.com/Lightricks/LTX-2)