LoRA trained on Miss Fortune from League of Legends
requested by: pretty much everyone
I tried to make her default skin as consistent as possible since the others focused more on the lore MF. However, you can still create the lore MF
I didn't include Captain MF in this LoRA because it would have overbled into everything else and made the captain hat and outfit mix with her default one. I really wanted to avoid that because my goal was to make default MF as consistent as possible without pruning, which would make it less flexible. However, I have the dataset ready for Captain MF, so it will also be uploaded today or tomorrow :)
default: miss fortune \(league of legends\), 1girl, pirate hat, bra, strap slip, bare shoulders, detached sleeves, wide sleeves, pants
lore mf: miss fortune \(league of legends\), 1girl, bare shoulders, off shoulder, cleavage, pants
anime: Kawaii Realistic Anime Mix - A0.2, YabaL_Mix - V5, Cetus-Mix
2,5D: Aniverse - Aniverse V1.1, Dark Sushi 2.5D, MeinaUnreal - V4.1, DarkSun - v4.0
realistic: Paragon V1.0, Kawaii Realistic European Mix - v0.3, OnlyAnime
negative embeddings: Fast Negative Embedding v2
Recommended settings:
Make sure you are aware on the usage instructions of LORA
VAE: vae-ft-mse-840000-ema-pruned (for realistic models & 2,5D), kl-f8-anime2, blessed2.vae (for anime models)
Sampler: DPM++ SDE Karras or DPM++ 2M Karras(euler a for img2img upscaling) from time to time im also using DPM++ 2M alt Karras
Steps: 20 to 35
Clipskip: 2
Upscaler : GitHub - pkuliyi2015/multidiffusion-upscaler-for-automatic1111 4x-UltraSharp(for 2,5D & realistic), 4xAnimesharp(for anime)
CFG Scale : 5 to 9 (mostly 7)
LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8 and 1)
Denoise strength upscaling: 0.3 to 0.55
If you want to autocomplete the tags & trigger im using, I recommend using Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UI
For full body shots i recommend using: ComfyUI Impact Pack
or the a1111 alternative GitHub - Bing-su/adetailer
Description
FAQ
Comments (9)
Gives me a very long error that starts with "failed to match keys" then i guess it kinda works anyways? Weird
Yep, this time I got the same error at the beginning. It still worked, but I think I need to reinstall Kohya (training GUI) after the Captain Fortune release so that this annoying message disappears. If the bug remains, it's an A1111 bug
@AhriMain its a bit confusing bcs i had that on jinx as well but jinx gave some very solid results nonetheless, this one seems a bit more iffy, ill try some of the models u use for the showcase eventually
@themangamer123 I don't think this changes the quality of it at all though. I pretty much scrolled through Civit yesterday and tested like 12 models, they all worked pretty solid
could you do tristana?
there is a good Tristana LoRA already
@AhriMain that model oversaturates the colors when you leave it at 1,you have to set it to 0.7 in order to get decent results,with other loras that has never happened to me,only with the tristana one that is available at the moment,I would appreciate a new lora on that since you are dedicated to lol characters.
you're the best ღ
Nice one, tried it on many models, gave really good results, thanks!
Could you do Spellthief Lux ? and maybe Taliyah ?
Thanks !
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.