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