README.md

---
tags:
  - ltx-2
  - ltx-video
  - text-to-video
  - audio-video
pinned: true
language:
  - en
license: other
pipeline_tag: text-to-video
library_name: diffusers
---

# ltx2-compile-keytest

Trained with the [LTX LoRA Trainer](https://huggingface.co/spaces/ltx-community/ltx2-lora-trainer) — powered by [LTX-2](https://github.com/Lightricks/LTX-2).

This is a **IC-LoRA (in-context control)** fine-tuned from [`ltx-2.3-22b-dev.safetensors`](https://huggingface.co/Lightricks/LTX-2.3) on custom data.

## Model Details

- **Base Model:** [`ltx-2.3-22b-dev.safetensors`](https://huggingface.co/Lightricks/LTX-2.3)
- **LoRA type:** IC-LoRA (in-context control)
- **Training Type:** LoRA fine-tuning
- **Training Steps:** 300
- **Learning Rate:** 0.0002
- **Batch Size:** 1

## Sample Outputs

| | | | |
|:---:|:---:|:---:|:---:|


## Usage

### 🧨 Diffusers

> LTX-2.3 support is currently on the diffusers `main` branch:
> `pip install git+https://github.com/huggingface/diffusers.git`

```python
import torch
from diffusers import LTX2InContextPipeline
from diffusers.pipelines.ltx2.export_utils import encode_video
from diffusers.pipelines.ltx2.utils import DEFAULT_NEGATIVE_PROMPT

pipe = LTX2InContextPipeline.from_pretrained(
    "diffusers/LTX-2.3-Diffusers", torch_dtype=torch.bfloat16
)
pipe.enable_model_cpu_offload()

# Load this LoRA
pipe.load_lora_weights("ltx-community/ltx2-compile-keytest", weight_name="lora_weights_step_00300.safetensors", adapter_name="lora")
pipe.set_adapters("lora", 1.0)

video, audio = pipe(
    prompt="<your prompt>",
    negative_prompt=DEFAULT_NEGATIVE_PROMPT,
    # IC-LoRA is reference-conditioned — pass your control video via reference_conditions:
    # reference_conditions=[...],  # see the LTX-2 diffusers docs for the condition object
    width=768, height=512, num_frames=49, frame_rate=25.0,
    num_inference_steps=30, guidance_scale=4.0,
    output_type="np", return_dict=False,
)
encode_video(video[0], fps=25.0, output_path="output.mp4")
```

For the full reference implementation and ComfyUI workflows, see the [official LTX-2 repository](https://github.com/Lightricks/LTX-2).

### 🔌 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).

### Example Prompts




This model inherits the license of the base model ([`ltx-2.3-22b-dev.safetensors`](https://huggingface.co/Lightricks/LTX-2.3)).

## Acknowledgments

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