DreamSound
DreamSound copied to clipboard
zelaki
Code for Investigating Personalization Methods in Text to Music Generation
Hello, Thanks for this great repo, been having a lot of fun with it. I'm wondering if it's possible to implement the newer ``audioldm_48khz`` checkpoint for finetuning? It seems it...
Dear authors, You claimed in the paper that "using a single NVIDIA RTX-3090 GPU with a training batch size of 4, employing learning rates of 4 × 10−6 for DB",...
Dear author, I have a few question on the dataset: 1. I wonder if there YouTube id for Obama and Trump. 2.the YouTube id of agni_parthene is no longer valid....
Just want to know that, are the result in the paper using prior preservation loss in Dreambooth? I saw your code have prior preservation loss, but when I run it...
I want to test this with my own audio, to test how it works.
