<h1 id="heading-10">SD_1.5</h1>v1.0 - trained a little on some imagesv2.0 - trained more on more imagesBest settings: Model: meinamix (should work fine with any anime model)weight: 0.7-0.8CFG: 5-7 Resolution: 512x768 (optional) Hires.Fix: scale 1.5-2.0, steps 14, denoising: 0.36Clip skip 2Use Adetailer: face_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8n.pt</a>, to get better face (sometimes it's better without it)<h1 id="heading-11">Pony</h1>Trained on Pony model, so for best result use only Pony modelsBest settings: Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/288584?modelVersionId=324524">AutismMix_confetti</a>weight: 0.7-0.8Resolution: 896x1152 Use Adetailer: face_<a target="_blank" rel="ugc" href="http://yolov8n.pt">yolov8s.pt</a>, ADetailer steps:40 (at least, to get good face) Actually, It doesn't require trigger words, but words that was used in training: score_9, girl,smile,open eyes,close eyes,open mouth,close mouth,white background,winter clothes, summer clothes

Files with SHA256: da1c7622ba6e314fadc15963aa483c3811281686bf976eca34eca57c98ef4938