Text2Video-Zero is azero sampleText-to-Video Generator, by leveraging existing text-to-image synthesis methods, proposes a low-cost method (without any training or optimization) to make it applicable to the video domain.

Experiments show that our method performs reasonably well despite not being trained on additional video data.

set up

1. Clone the repository and enter the directory:

git clone https://github.com/Picsart-AI-Research/Text2Video-Zero.git
cd Text2Video-Zero/

2. Use Python 3.9 installation requirements

virtualenv --system-site-packages -p python3.9 venv
source venv/bin/activate
pip install -r requirements.txt

Reasoning API

To run inference, create an instance of Modelkind

import torch
from model import Model

model = Model(device = "cuda", dtype = torch.float16)