![Tsumugi Shirogane ( Danganronpa ) [SD 1.5]版本V1 (ID: 799958)](https://image.1111down.com/xG1nkqKTMzGDvpLrqFT7WA/4fc6ca3c-533b-495d-b236-6f6b0a89cd8d/width=450/27958146.jpeg)
Tsumugi Shirogane - The Ultimate Cosplayer from Danganronpa V3. This lora should let you create images with Tsumugi in a few different art styles and clothing options. It's plain to see that Tsumugi needs to be able to cosplay!
IMPORTANT: This stable diffusion 1.5 lora is trained on a conversion of my original flux Tsumugi Shirogane 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. It's probably going to be a bit unpredictable. For models, I've had the best results for this lora with lustermix 2D, Mistoon_Anime 3.0 and aing diffusion. Likewise, I typically used adetailer for the faces. Next, Danganronpa GUI elements are probably going to appear every now and then. It doesn't seem to happen 'too' often though. And you might be able to catch them with negative prompts. The anime style options in particular can be more unpredictable than in either the SDXL or Flux version of this lora. If you want to try pushing the anime look further than I'd recomend using TheArnoldPickaxe's "Danganronpa 3: The End of Hope's Peak High School: Despair Arc" style lora alongside this while also using this lora's built-in danganronpa 3 style. Sometimes doubling up like that helps, other times it just makes a mess. You should find one or more examples of the practice in this lora's gallery section. That said, caveats aside, I think this experiment was a success. The majority of the images I've uploaded with this lora were made through random wildcard generations for the tags which I think is a nice testament to its flexability. Finally, the tagging is a little messy. The price payed for automated conversion.
I trained on a few specific image types 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. But these are the major options.
Danganronpa the Animation: Use the tags 'Danganronpa The Animation, screencap from the anime Danganronpa The Animation, anime' in the prompt to emulate the art style from the anime series Danganronpa the animation.
Danganronpa 3 (anime): Use "Danganronpa 3 screencap style, 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: 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: 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: "Tsumugi Shirogane character, Tsumugi Shirogane, school uniform, 1girl, solo, white blouse, orange bow, teal-black blazer, silver buttons, teal-blue hair, center parted hair, straight hair, teal-green eyes, round glasses, white glasses, teal-black pleated skirt with teal stripe hem, dark navy knee-length socks, teal-gray loafers"
Swimsuit: "Tsumugi Shirogane, 1girl, solo, swimsuit, orange bikini, white lace trim, thin straps, light orange bow, teal flowing hair, round glasses"
Prelude uniform: "1girl, solo, Tsumugi Shirogane, danganronpa v3, Danganronpa 3 screencap style, teal green eyes, ((((white long sleeved sailor uniform)))), ((((white seifuku)))), navy blue collar, navy blue tie, white trim on sleeves and cuffs, teal blue hair, center parted hair, long hair"
Locations: I didn't try to train on any specific locations, but some of them appeared enough in the training data that you might be able to improve your results by specifying areas and tags from danganronpa V3 or danganronpa S. In particular with 'jabberwock island' and 'danganronpa v3'.
Note: Tsumugi's hair is annoyingly inconsistent through various portrayals. Not as bad as Chiaki's hair, but still. Flux can get a little confused about her hair color because spike chunsoft gets a little confused about her hair color too.
Training material: The majority of the training data came from Danganronpa V3 and Danganronpa S with as much official supplementary material added in as possible. The game-related data includes all sprites and a handful of in-game screenshots. LLM captioned, then hand edited. I then added style training from Danganronpa the Animation and Danganronpa 3. With the latter I had some concern that it might contaminate the training but testing with and without didn't show any differences. So I kept it in to allow for easier style changes without needing additional loras. However, because Tsumugi wasn't actually in that material she doesn't benefit as much as, say, Chiaki would.
描述:
训练词语:
名称: Tsumugi_Shirogane_emSD15.safetensors
大小 (KB): 18663
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success