DreamSound
DreamSound copied to clipboard
prior preservation loss in Dreambooth
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 in dreambooth_audioldm.py, it works, but in dreambooth_audioldm2.py there are some bugs.
Hi, The results we include in the paper are obtained using AudioLDM with prior preservation loss. Thank you for noticing the bug in the code for AudioLDM2 I will take a look at it. Thodoris
There are also bugs when using classifier guidance.