THUDM / CogVideo

Text-to-video generation. The repo for ICLR2023 paper "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Let me use it

xowe1 opened this issue · comments

commented

Please

commented

We are currently working on a demo API and will post it in this repo as soon as it's available

Hi, first of all congratulations on the results and thanks for sharing this very cool work!

Regarding this line in the paper:

We present CogVideo, which is the largest and the first open-source pretrained transformer for text-to-video generation in the general domain

I think it’s inappropriate to claim to be “first to open source” before this has been accomplished.

The code, demo and model have been released. Have fun!