Deltarune LORAs for SDXL (Animagine, Illustrious, Pony) and SD 1.5
SDXL:
Trained on Animagine and Pony models
Covers 20 Deltarune characters with variations: Kris, Noelle, Susie (light/dark world versions), Jevil, Ralsei (Ch.1/2), Berdly (light/dark), Spade King, Lancer, Cyber Queen, Rouxls, Spamton (+Neo), Swatchling, Tasque Manager, Rudolph, Ant Tenna, Roaring Knight, Dess, Carol, Shadowguy, Pluey
Prompting Tips:
Place trigger words at beginning of prompt (except Pony model)
Pony model trained with shuffling, so you can use trigger words in different places with higher success
Additional details help (e.g., Kris's sweater type)
Caution with "masterpiece, best quality" in Animagine models, can cause gender bend and NSFW
Legacy Models:
Characters may struggle to interact unless similar
Can influence output style minimally
Rework Information:
See "about this version" section for specifics, same goes for other models
Pony Model:
Slightly undertrained, but sufficient for most characters
SD1.5 Model:
Lower quality than SDXL, requires more detailed prompting
Limited comparison data with other 1.5 models
Description
Alternative version to SDXL one, 1.5 obviously has its own limitations in comparison
FAQ
Comments (3)
The weight range for CivitAI generation is currently locked 1.0 for this model. You might not know this, but that means that, when using the on-site generator, that makes it so the weight cannot be changed from 1.0.
Having a wider range is useful for flexibility as you might imagine, so a -2.00 to +2.00 would be more useful.
Oh, I see - so that's what those min and max meant, I'll change it in models
@munchkin CivitAI has done a really bad job at informing users about it, it's become a big issue with uploaded LoRA where the range is set to -100.00 which, y'know, kinda makes them completely unusable for the site generator. Having an expanded range, like -10 to +10 is useful for certain sliders, but the -2.00 to +2.00 is generally very helpful, so thanks for changing it.