JLNTV_IPD/CogVideo

mirror of https://github.com/THUDM/CogVideo.git synced 2025-04-05 19:41:59 +08:00

Go to file

wenyihong 26aee13496 add paper

2022-05-31 13:43:14 +08:00

change to png

2022-05-29 15:54:14 +08:00

add paper

2022-05-31 13:43:14 +08:00

README.md

Update README.md

2022-05-29 15:59:44 +08:00

README.md

CogVideo

This is the official repo for the paper: CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers.

https://user-images.githubusercontent.com/48993524/170857367-2033c514-3c9f-4297-876f-2468592a254b.mp4

Generated Samples

Video samples generated by CogVideo. The actual text inputs are in Chinese. Each sample is a 4-second clip of 32 frames, and here we sample 9 frames uniformly for display purposes.

CogVideo is able to generate relatively high-frame-rate videos. A 4-second clip of 32 frames is shown below.