mini-sora / minisora

MiniSora: A community aims to explore the implementation path and future development direction of Sora.
https://github.com/mini-sora/minisora
Apache License 2.0
1.16k stars 148 forks source link

A new video-text dataset which may help #362

Open mutonix opened 5 months ago

mutonix commented 5 months ago

Vript is a fine-grained video-text dataset with 12K annotated high-resolution videos (~400k clips), where each clip has a detailed caption of ~145 words.

chg0901 commented 5 months ago

Could you please propose a pr in the dataset section?

TruthSearcher commented 4 months ago

Vript is a fine-grained video-text dataset with 12K annotated high-resolution videos (~400k clips), where each clip has a detailed caption of ~145 words.

isn't that a non-commercial dataset?

mutonix commented 4 months ago

It is non-commercial and academic only.

chg0901 commented 1 month ago

Could you please propose a pr in the dataset section?

@mutonix