It’s not obvious that fine-tuning can remove all latent compulsions from these models. Consider that the creators know that fine-tuning exists and have vastly more resources to explore the feasibility of removing deep bias using this method.
Go check out the Unstable Diffusion Discord.
The vast majority of images there are SD1.5, even the ones made today.
Which goes far more towards the idea that safety isn’t a desirable feature to a lot of AI users.
I suppose you could train a model from scratch if you have enough money to blow…