metadata

tags:
  - ltx-video
  - text-to-video
  - image-to-video
pinned: true
language:
  - en

LTX-Video Model Card

This model card focuses on the model associated with the LTX-Video model, codebase available here.

Model Details

Developed by: Lightricks
Model type: Diffusion-based text-to-video and image-to-video generation model
Language(s): English
Model Description: LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content.

Usage

Setup

The codebase was tested with Python 3.10.5, CUDA version 12.2, and supports PyTorch >= 2.1.2.

Installation

git clone https://github.com/LightricksResearch/LTX-Video.git
cd ltx_video-core

# create env
python -m venv env
source env/bin/activate
python -m pip install -e .\[inference-script\]

Then, download the model from Hugging Face

from huggingface_hub import snapshot_download

model_path = 'PATH'   # The local directory to save downloaded checkpoint
snapshot_download("Lightricks/LTX-Video", local_dir=model_path, local_dir_use_symlinks=False, repo_type='model')

Inference

Inference Code

To use our model, please follow the inference code in inference.py at https://github.com/LightricksResearch/LTX-Video/blob/main/inference.py:

For text-to-video generation:

python inference.py --ckpt_dir 'PATH' --prompt "PROMPT" --height HEIGHT --width WIDTH

For image-to-video generation:

python inference.py --ckpt_dir 'PATH' --prompt "PROMPT" --input_image_path IMAGE_PATH --height HEIGHT --width WIDTH