Sure! Sir!

In the months to come i would be working on the problem of text to video. After literature review i got the idea that it might be compute extensive, like a cluster of GPUs required to train the models. So I asked that if it could be done with a mediocre GPU such as a 3080. I haven't really thought about the models i would use or general architecture of the model. Just wanted an answer, because i dont wish to take up this topic then get stuck due to compute issues.