Sign In

Satsuki Iranami ( Danganronpa Another ) [Illustrious]

11
69
1
Verified:
SafeTensor
Type
LoRA
Stats
69
0
Reviews
Published
Nov 7, 2024
Base Model
Illustrious
Training
Steps: 1,568
Epochs: 30
Usage Tips
Clip Skip: 1
Hash
AutoV2
B7DE22CEED
default creator card background decoration
Second Birthday Badge
emerjk
Created on Civitai

Satsuki Iranami - The Ultimate Clown from the fan game Danganronpa Another. This lora should let you create images with Satsuki Iranami in a few different art styles and clothing options. This is a port of my flux lora for Satsuki to Illustrious. But I think that for the most part it carried everything over quite well.

Unique features

The main point I try to stress in my Danganronpa loras is authenticity to the source material. It's fairly easy to get the basics of a character's style or clothing down. Characterization is a lot harder. Models have their own concepts of what a scared, or happy, or sad, or angry expression or stance would be. But a character in something like Dananronpa has a lot of careful attention put into ensuring their designs make all of those states unique. I go through every sprite, every CG, every official image I can find to caption and include them in the dataset in hope of best representing that. Whether it works out is another question, but it's what I'm aiming for and why these might be a little odd.

Prompt style

I trained using natural language for the captions rather than tags. So natural language prompts will give you the best results. Tags will generally still work. However, natural language usually works best, followed by natural language with some additional tags,and finally just tags.

Specific prompts

I trained on a few specific image styles which you can replicate, to varying levels of success. I tried to include a range of the prompt options in the images so you can easily compare and contrast. Unfortunately the "sprite style" and in-game styles are a little weak here since she's an anime-only character. Still, they'll push the style in those directions even if not as much as in some of my other Danganronpa loras. But these are the major options.

Danganronpa the Animation: Use 'This is an anime screencap from Danganronpa The Animation' in the prompt to emulate the art style from the anime series Danganronpa the animation.

Danganronpa 3 (anime): Use "This is an anime screencap from Danganronpa 3."

Sprites from Danganronpa: Mention 'danganronpa sprite style' in the prompt to try emulating the art style of Danganronpa. For example, 'this image is in the danganronpa sprite style'. Despite the name, I trained on full screenshots, with and without the GUI, with this description along with character sprite rips. So in theory it should be able to 'danganronpafy' a full image.

Sprites from Danganronpa Another: In theory this is similar but distinct from the prior Danganronpa sprite style. It's the updated sprites used in Danganronpa Another. To use this style, include this within your prompt "The image is in Danganronpa another sprite style."

Clothing

You can try different clothing options with prompts like the following:

Standard clown outfit: "Satsuki Iranami is wearing a two-toned jester-like outfit split vertically down the middle with blue on the left side and pink on the right, and a matching jester's cap with white polka dots and a yellow band. Her costume features a white ruffled collar, yellow buttons down the front and curled shoes. Satsuki has short blue hair and striking yellow eyes. She wears a red clown nose."

Swimsuit: "Satsuki Iranami is wearing a blue and pink bikini top with a yellow trim. The bikini bottom matches the design of the top. The left side of the bikini top and bottom are blue and the right sides are pink. Her short blue hair covers her ears and she has bright yellow eyes."

Formal dress: "Satsuki Iranami wearing her dress from Danganronpa Another. She has short blue hair that is tied in a ponytail and yellow eyes. She is wearing a light blue dress with puffy short sleeves and a low neckline. The bottom of the dress features a layered design with ruffled tiers."

Additional tags

A lot of Illustrious models have additional danbooru training. If you're using one, you might be able to add some more elements from danganronpa by adding this tag to your prompt " danganronpa_(series)".

Locations

I didn't try to train on any specific locations, but some of them appeared enough that you might be able to improve your results by specifying areas in Hope's Peak like "Hope's Peak's pool". Even just mentioning Hope's Peak might be enough to help push the lighting in an image in the right direction if you're generating something set in the school.

The game

If you haven't played it, I really can't recommend Danganronpa Another strongly enough. The translation can be a bit odd, the rpg maker graphics might be jarring at first, but overall it's just a really fun story that captures the heart of the franchise. The English translation is available at Danganronpa Another 1.