VideoGPT: Video Generation using VQ-VAE and Transformers
Paper • 2104.10157 • Published • 4
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("hpcai-tech/vqvae", trust_remote_code=True, dtype="auto")This repository is a clone of the VideoGPT in order to convert the VQ-VAE model to the Hugging Face format for easier model loading.
Paper: VideoGPT: Video Generation using VQ-VAE and Transformers
We follow the MIT license distributed by the VideoGPT project.
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="hpcai-tech/vqvae", trust_remote_code=True)