README.md

metadata

license: cc-by-4.0
datasets:
  - nkp37/OpenVid-1M
language:
  - en
tags:
  - text-to-video
  - Video Generative Model Training
  - Text-to-Video Diffusion Model Training
  - prompts

Summary

Here we provide pre-trained model weights on our OpenVid-1M in model_weights.

Project: https://nju-pcalab.github.io/projects/openvid

Paper: https://huggingface.co/papers/2407.02371

Code: https://github.com/NJU-PCALab/OpenVid

Dataset: https://github.com/NJU-PCALab/OpenVid

Directory

model_weights
   └─ MVDiT-16×512×512.pt
   └─ STDiT-16×512×512.pt
   └─ STDiT-16×1024×1024.pt

Download

You can download model weights by wget, for instance:

wget https://huggingface.co/datasets/nkp37/OpenVid-1M/resolve/main/model_weights/MVDiT-16×512×512.pt
wget https://huggingface.co/datasets/nkp37/OpenVid-1M/resolve/main/model_weights/STDiT-16×1024×1024.pt
wget https://huggingface.co/datasets/nkp37/OpenVid-1M/resolve/main/model_weights/STDiT-16×512×512.pt

If you want to generate videos use our pre-trained model weights, please refer to here.