LoRA trained on Jinx from League of Legends
There are 4 arcane Jinx models, but there isn't a default Jinx model, lol. So there you go xD
Base: jinx \(league of legends\), 1girl, twin braids, single elbow glove, short shorts, bikini top only, necklace, belt, bullet, fingerless gloves
models used
anime: Kawaii Realistic Anime Mix - A0.2, YabaL_Mix - V5, MeinaAlter - V3
2,5D: Aniverse - Aniverse V1.0, PastelDiffusedMix - V2.2, MeinaUnreal - V4.1
realistic: Paragon V1.0
negative embeddings: bad_prompt, negative_hand, ng_deepnegative_v1_75t, bad-artist, EasyNegative
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 (5)
I never actually noticed every other jinx lora was the arcane outfit, including the biggest one
Ye, same. I wanted to test some LoRAs with Jinx in it, and that's when I realized that there is no default Jinx
@AhriMain from the generations i made this lora is pretty solid actually
@themangamer123 Thanks! Yeah, it should be she probably has the largest dataset for a single outfit out of every character I've done a LoRA of
Is there a possibility of releasing a new version that focuses more on the tattoo, which is a strong characteristic of hers? :3
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.