CottonNoob

Version 4 releasedBase model changed to IllumiYume XL v3.2(v-pred)It boasts a stable 1536*1536 resolution and character learning and prompt responsiveness that rivals or exceeds NoobAI-XL.Version 3 and 4 is v-pred Model.This is a merge model based on Noob e-pred.illustration-style pattern and focuses on skin tones.The merged content is as follows1.IllumiYume XL(Version 3 is V2.0 Version 4 is V3.2 )2.NoobaHoshiv1.0（Noob e-pred1.1 + Nova Orange XL v3 + Raehoshi illust XL v3）3.paruparu_illustrious_v44.My Lora(Trained by 360 images AI-generated)(v1 is 200 images AI-generated)Recommended settingsSampler: Euler aCFG: 5Steps: 24～30Quality tags:masterpiece, best qualityNegative prompt（ver1、ver2）:bad quality, worst quality, watermark※no problem without itNegative prompt（ver3）:bad quality,worst quality,worst detail,sketch,censor, simple background,transparent background, 3d, realistic, backlighting3d, realistic, backlighting is your choice.Negative prompt（ver4）:bad quality,worst quality,worst detail,sketch,censor, simple background,transparent background3d, realistic, backlighting is no longer necessary.