Open
Description
Lots of model use their custom fine tuned VAE to get color and texture right, for example (https://huggingface.co/Linaqruf/anything-v3.0/blob/main/Anything-V3.0.vae.pt).
Is there a way to use these fine tuned VAE on apple's ml-stable-diffusion?
Can torch2coreml script do this job? I've used other's pre-converted coreml model and most of them looks like they are missing proper VAE.