If I want to train an unconditional ldm on my custom dataset(without any condition), is it the following steps?

[hellohahaw]

          If I want to train an unconditional ldm on my custom dataset(without any condition), is it the following steps?

1. Train a VQGAN on custom dataset to get a well-trained autoencoder.
2. Train a ldm with the pre-trained autoencoder.

Many pre-trained autoencoders (VQ and KL) have been provided. But I'm not sure if they can be used on custom dataset and skip the first stage and go straight to the second stage.

Originally posted by @Suimingzhe in https://github.com/CompVis/latent-diffusion/issues/211#issuecomment-1435469431

[iris0329]

same question