diff --git a/README.md b/README.md index 3c0088f..441f0b7 100644 --- a/README.md +++ b/README.md @@ -1,2 +1,19 @@ # CogVideo -Text-to-video generation. + +This is the official repo for the paper: CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers. + + + +## 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. + +![Overview](assets/intro-image.pdf) + +![More samples](assets/appendix-moresamples.pdf) + + + +**CogVideo is able to generate relatively high-frame-rate videos. ** A 4-second clip of 32 frames is shown below. + +![Overview](assets/appendix-sample-highframerate.pdf) \ No newline at end of file diff --git a/assets/CogVideo_samples.mp4 b/assets/CogVideo_samples.mp4 new file mode 100644 index 0000000..045fd4f Binary files /dev/null and b/assets/CogVideo_samples.mp4 differ diff --git a/assets/appendix-moresamples.pdf b/assets/appendix-moresamples.pdf new file mode 100644 index 0000000..f750942 Binary files /dev/null and b/assets/appendix-moresamples.pdf differ diff --git a/assets/appendix-sample-highframerate.pdf b/assets/appendix-sample-highframerate.pdf new file mode 100644 index 0000000..90c4260 Binary files /dev/null and b/assets/appendix-sample-highframerate.pdf differ diff --git a/assets/intro-image.pdf b/assets/intro-image.pdf new file mode 100644 index 0000000..0dc44fd Binary files /dev/null and b/assets/intro-image.pdf differ