I've noticed there is a lack of Undertale LORAs for SDXL, so I've trained one on Animagine XL v3.x, but can work on some other models (definitely not PonyXL, though). I used around 800 images in total that I could find, with some additions later on. Suffice to say, it can influence style quite a bit (mostly 3.0 models).
Characters:Asriel, Chara, Frisk, Muffet, Sans, Papyrus, Undyne, Gaster, Toriel, Mettaton, Grillby, Alphys, Flowey, Asgore, Napstablook. Some better, some worse but I don't recommend trying to generate either Asgore or Napstablook in the version 1.0 - they are overfitted. In the version 1.1 and onwards they work well enough, but be careful about it (but it is usually obvious). There could be some stylistic inconsistency, so it is better to specify.
Parameters: Trigger words are supposed to be like character_(undertale). Some chararacters can be accurate enough with trigger words alone, but for others it is better to add some more. The models have been trained on clip skip 2 (except for Base XL ones), and they work at a strength of 1.0 (or even lower, if need to), but it depends on what model you intend to use. The sampler that I use, unless specified, in the examples is dpmpp 3m sde gpu, with karass scheduler, from ComfyUI. My latest images have nodes to copy, but it's my personal workflow with a lot of unnecessary elements, so if someone were to use it, they would have to remove them.
Animagine 3.1: Starting with model 1.2, it surpasses the previous models in its flexibility and capabilities but stylistically they are quite different, so it is a matter of taste. Personally I like 1.2.5 model for its style, but it has lots of biases since I overfitted it a bit in the beginning, which makes it hard to generate some things.
Base XL: I've trained the second model, but this time on a base model, which is supposed to make it possible to use LoRA on any model, but not really (anime models seem to struggle a lot). So my examples are not only from Animagine v3 on this one. As of now, it isn't wholly accurate, but it really depends on the model. I trained this model as a substitute, if the other one doesn't work at all.
