coreml stable-diffusion text-to-image

Core ML Converted Model:

Note: This model does not have the unet split into chunks.

Healy's Anime Blend V1.7:

Source(s): CivitAI

This is a blend of some anime models mixed with "realistic" stuff to get a look i've been trying to accomplish for awhile. Im pretty happy with what it outputs, but judge that for yourself. I can't for the life of me remember what I put into this model.

I take no credit whatsoever, I just smashed rocks together like a caveman and the outcome somehow worked.

It can create NSFW stuff to I think, but i've noticed the outcomes remain pretty tolerable with "cleavage" in the negative prompts.