Currently, there is a lot of guesswork in getting models to work. Users have to fend for themselves in many cases to determine which text encoders, VAE, etc are supported or included, and sometimes even the quantization level is obscured until you get the log output from a working run.

The feature I would like to see here is something like --model-info, which will print every available metadata of what a model is, has, and needs to work.