These are lora trained with about 49-130 images from the Disgaea series. (Disgaea 5/6/7/RPG) My goal was to capture the flat, 2d style the games are known for. It's not a perfect re-creation due to the influence of the model and the variety of images I used, but I am happy with the results nonetheless. Please note, this is not a character lora. My goal wasn't to recreate the characters from the game, it was only to capture the artstyle.
To get the results you see in the images above, these are the settings I used.
V5 The base for this lora is Anima 1.0.
V4 The base for this lora is Noob 1.0 V-Pred. I haven't tested it with anything else and I don't believe it will work very well on anything else.
V3 The base for this lora is Zootlustrious V2. I haven't tested it with anything else and I don't believe it will work very well on anything else.
V2 was trained with 49 images on 2D Fish. I haven't tested it with anything else and I don't believe it will work very well on anything else.
V1 was trained on Autism Pony. I haven't tested it with anything else.
SDXL Exclaimer: In most of the examples I intentionally used tags like pointy ears, and devil eyes to give the images that "Disgaea" feel. They are not features inherit to the lora itself, but they were a part of the training data. All of the images I used for training were sfw, so the nsfw images aren't as strong as I'd like.
Description
This version was trained on Anima 1.0, using 50 images at a resolution of 1792. Meaning, you should be able to gen up to 1792x1792.
I had to redo all the data for this lora since the old data was too poor for Anima. I decided to use images from Disgaea RPG since the data available is pretty high quality. Most of the images I chose were full body shots on white backgrounds so expect the backgrounds to reflect the simplicity of the style. Lastly, I had to remake this lora multiple times since I kept getting sporadic detail like debris and sparkle effects when I prompt for white background. Anima picks so many small details, so I had to tag each image aggressively and edit out all the fluff.