Home
The community provides you with featured content
Inspiration
Share your amazing creations
AI Apps
Free and high quality AI apps
AI Characters
Immersive AI character interaction
AI Audio
Unlock all kinds of novel AI audio
No relevant data found yet
Download the SeaArt App
Please scan this QR code with your camera to download the SeaArt app on your phone.
Notifications
LoRA trained on Riven from League of Legends
requested by @1797437344610
models used
anime: YabaL_Mix V3
2,5D: PastelDiffusedMix - V2.1, CamelliaMIx_2.5D - V2, DarkSun
realistic: Paragon V1.0
tags: riven \(league of legends\), 1girl,
optional tags: folded ponytail, short dress, corset, single pauldron, white hair, black eyeshadow, bare shoulders, facial mark
negative embeddings: bad-hands-5, 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)
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)
Denoise strength upscaling: 0.4 to 0.7
for full body shots i recommend using: ComfyUI Impact Pack
or the a1111 alternative GitHub - Bing-su/adetailer