Trigger: @urusanhanddrawn

I'm not a good artist by any stretch of the imagination, but I went ahead and trained on my own hand drawn sketches. The results were genuinely interesting and a little bit useful too.

It does a good job conforming to my style, it's really fascinating seeing the AI output something like what I'd draw. Also, despite the results often being aesthetically unpleasing it's very different from the norm, so it's good to see it's flexible enough to handle this kind of hyper-minimalist style. I also kinda like it, but maybe that's just me.

Now you might be asking yourself, why would I want a LoRA that makes my resulting generations worse?

I go into it in a lot more detail in the Pony model page (btw, it didn't work well on Illustrious so I never released that one) but basically it's good for sketching as an input for more serious work and as a diagnostic tool to see what LoRAs learned during training. Also if you like the style, that's great too.

A comment on that page also pointed out that the crude sketch quality makes it fly under people's AI-detecting radar, so you can use it to prompt with AI to communicate visual information to people who would otherwise react negatively.