LoRA trained on Bel'veth from League of LegendsRegular form: belveth, 1girl, monster girl, colored skin, third eye, glowingHuman form: belgirl, 1girl, third eye, colored skin, glowing, cloak, navelUlt/Monster form: belult, monster, no humans, extra eyes, sharp teethanime: YesMix - v1.6 (original), Zenith - v3, Yuzu - v1.12,5D: irRealitium, Aniverse - Aniverse V1.3, DarkSun, Dark Sushi 2.5D, ERA_09 - v1.0better hands LoRA: EnvyBetterHands LoCon - beta2negative embeddings: Fast Negative Embedding (+ FastNegativeV2) - v2Recommended settings:Make sure you are aware on the usage instructions of LORAVAE: 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 KarrasSteps: 20 to 35Clipskip: 2Upscaler : 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 0.55If you want to autocomplete the tags & trigger im using, I recommend using Booru style tag autocompletion for AUTOMATIC1111's Stable Diffusion web UIFor full body shots i recommend using: ComfyUI Impact Packor the a1111 alternative GitHub - Bing-su/adetailer
