This is a lora for Miaya Gekkogahara, the former Ultimate Therapist, Branch Office 7 Director of the Future Foundation, and creator of Usami/Monomi.

IMPORTANT: This stable diffusion 1.5 lora is trained on a conversion my original Miaya Gekkogahara flux training data. In short, this SD 1.5 lora suffers a bit from being designed for a very, very, different framework. I wrote a system to automatically convert the flux training data to as close to the 1.5 format as possible. But I only did a small amount of manual editing afterward. Still, the testing seems to be giving acceptable results. That said, there are issues.

Problems

Monomi should, in theory, be able to appear on Miaya's computer monitor. In practice it doesn't really work. Even getting a rabbit is a roll of the dice. And getting the rabbit to fit Monomi's design is even more rare.

Her front display on the wheelchair should come up with the keywords 'silver laptop' or just 'laptop' but she instead seems to just get....well....a silver laptop. I left it in the instructions because that's the way it should be working. But if you're getting the laptop, try removing the keyword..That sometimes makes the actual display appear.

Style tags

I trained on a few specific image types which you can replicate, to varying levels of success. This tends to work quite well in flux, OK with SDXL, and generally fairly poorly in SD 1.5. I tried to include a range of the prompt options in the images so you can easily compare and contrast. But these are the major options.

Danganronpa the Animation: Use the tags 'Danganronpa The Animation, screencap from the anime Danganronpa The Animation, anime, dr1anime' in the prompt to emulate the art style from the anime series Danganronpa the animation. The good part of these tags is that they can sometimes push away from the pixilation issue.

Danganronpa 3 (anime): Use "Danganronpa 3 screencap style, danganronpa 3, anime"

Sprites from Danganronpa: Use the tags 'danganronpa sprite style, Danganronpa V3 sprite style' or 'danganronpa sprite style, Danganronpa S sprite style' in the prompt to try emulating the art style of Danganronpa. 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.

Danganronpa V3 GUI (nearly broken): You can give it a try with these tags: 'Danganronpa V3 sprite style, Danganronpa V3 GUI status bar, black text, Danganronpa V3 GUI title bar yellow, screencap from anime Danganronpa V3'

Danganronpa S GUI (nearly broken): You can give it a try with this. "danganronpa s, danganronpa sprite style, danganronpa S sprite style, danganronpa s gui style dialog box, Danganronpa S GUI status bar, black text, Danganronpa S GUI title bar"

Clothing

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

Standard outfit in wheelchair: Miaya Gekkogahara, 1girl, white dress shirt, long red scarf, blue eyes, pale brown jacket, blue-gray hair, headphones, wheelchair, black vest, silver laptop, Danganronpa

Standard outfit standing 1girl, Miaya Gekkogahara, standing, full body, blue-gray hair, light gray headband, blue eyes, long eyelashes, pale brown jacket, black vest, white dress shirt, black skirt, black socks, white slippers, dark red scarf

Negative prompts

If GUI elements are showing up you can often get rid of them with these tags as negatrive prompts: (((danganronpa S GUI style speech bubble))), (((name bubble))), (((speech bubble))), blue speech bubble, text box:danganronpa S GUI style, GUI style, speech bubble, danganronpa S GUI style

General tips

The best results I've had with this lora come from using the LusterMix2D model, add detail lora, and goodhands lora. I've linked to them in the resources. Additionally, I'd advise using some form of upscaling like automatic1111's hires fix.

描述:

训练词语: