游戏AI研究所-Game AI Research Institute
Recommended Usage: Pair with the large model of the "Game Icon Institute"
This LORA must be activated using the trigger phrase "Game Icon Institute"; otherwise, it will not function.
Recommended LORA Weight: 0.4 to 0.75
LORA-XL Version:
We recommend using "Kohaku-XL Epsilon REV2"
LORA-SD1.5 Version:
We recommend using "Game icon Institute_modev30"
This game icon model is a beta version. We welcome you to join our group discussion and provide us with your suggestions. The development of this model is a mass-produced version from Icon Academy. We invite everyone to learn and exchange ideas together.
DISCORD: https://discord.gg/njBMYJ7mRF
QQ Group: 855795962
Description
((( gray background, simple background))),masterpiece,best quality,great quality,good quality,gmic_\(katongzhuzi\), A mushroom, solo,<lora:gmic icon_2Dicon-000014:0.75>,
Negative prompt: worst quality,low quality,normal quality,old,early,lowres,bad anatomy,blurry,cropped,text,jpeg artifacts,signature,watermark,username,artist name,trademark,title,multiple view,reference sheet,long body,multiple breasts,disfigured,ugly,text font ui,monochrome,chibi,nsfw,lowres,bad anatomy,bad hands,text,error,missing fingers,extra digit,fewer digits,cropped,worst quality,low quality,normal quality,jpeg artifacts,signature,watermark,username,blurry,artist name,
Steps: 20, Sampler: DPM++ 2M, Schedule type: Karras, CFG scale: 7, Seed: 4149997306, Size: 512x512, Model hash: 81cc2b4db3, Model: Game Icon InstituteXLbac2, VAE hash: e9ed949371, VAE: sdxl_vae.safetensors, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 2, Hires steps: 20, Hires upscaler: Latent, Lora hashes: "gmic icon_2Dicon-000014: 0c36118e99f4", Version: v1.10.1