Support small-sd and tiny-sd

A while ago there was a [release from segmind](https://blog.segmind.com/introducing-sd-small-and-sd-tiny-stable-diffusion-models/) of two new stable diffusion models which are way smaller and faster to run.

I think this would be a great addition to the examples to get people started with image generation on lower power devices.

I looked into how to add them to the example but got stuck on not knowing what the config should look like. Any tips on what would need to be done to make this happen? is it something that'd be easy for somebody else to tackle?

Huggingface repos:

https://huggingface.co/segmind/tiny-sd

https://huggingface.co/segmind/small-sd

Start by reviewing the existing image-generation examples and their configuration, then compare the linked segmind/tiny-sd and segmind/small-sd Hugging Face repositories. Done means the examples support both models and provide a clear way to run them on lower-power devices.

Written by the indexing model from the issue text.