search

fdbtrs / IDiff-Face

Official repository of the paper: IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-conditioned Diffusion Models (ICCV 2023)
64 stars 1 forks source link

How to split the LDM model to Encoder & Decoder #13

Open panigrahidileep opened 5 months ago

panigrahidileep commented 5 months ago

Hello,

In the read-me mentioned splitting the LDM into Encoder & Decoder, could you please help us with how to split the models.

Download links for the pre-trained autoencoder weights that originally come from the fhq256 LDM from Rombach et al. and strictly follow their licence. Their VQModelInterface submodule has been manually extracted and split into its encoder and decoder models since the encoder is only used during training and the decoder is only needed for sampling: