LTX-2/packages/ltx-trainer/templates/model_card.md

tags, pinned, language, license, pipeline_tag, library_name

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

{model_name}

This is a fine-tuned version of {base_model} trained on custom data.

Model Details

• Base Model: {base_model}
• Training Type: {training_type}
• Training Steps: {training_steps}
• Learning Rate: {learning_rate}
• Batch Size: {batch_size}

Sample Outputs

{sample_grid}

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.

Example Prompts

{validation_prompts}

This model inherits the license of the base model ({base_model}).

Acknowledgments

• Base model: Lightricks
• Trainer: LTX-2