how to train playground?
#12
by Faissalhamdi - opened
I am trying to fine-tune playground v2.5 and looking for a way to do so, I would appreciate your input
There's some information here: https://github.com/huggingface/diffusers/pull/7126
"We were also inspired by Hoogeboom et al [13] to skew the noise schedule towards an overall noisier one when training on high-resolution images."
How is this sentence implemented in diffusers？