chavinlo / TempoFunk

(pseudo) Make-a-Video with stable diffusion

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About pretrained model and dataset

chouchonkit opened this issue · comments

Hi, I am try to train your code by myself but I am not sure what dataset and pretrained model should I use.
I try use some river video and text (I am not sure my text dataset is right or not) as dataset, and CompVis/stable-diffusion-v1-4 used to pretrained model.
But it didn't work out, could you tell me what dataset and pretrained model are you using? Thanks.