Support me: <a target="_blank" rel="ugc" href="https://ko-fi.com/elevatedone">https://ko-fi.com/elevatedone</a> ☕Please post suggestions for future models here: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/5921/suggestion-list">https://civarchive.com/articles/5921/suggestion-list</a>The early access can be removed (for everyone) by donating to my Ko-Fi (Say the model name in the message field).<hr />As I couldn't let go of many SD 1.5 model's artstyles, I decided to retrain them for PonyXL.This is the fourth iteration of retraining styles, but the first trained checkpoint.Information:<ul><li>The model is based on <a target="_blank" rel="ugc" href="https://civarchive.com/models/12262/night-sky-yozora-style-model">Night Sky YOZORA</a> by @YozoRaAru</li><li>Base model for training used was <a target="_blank" rel="ugc" href="https://civarchive.com/models/317902/t-ponynai3">T-ponynai3 v5.5</a> by @Tonade</li><li>The model was trained at 1536x1536 (V1) and 1024x1024 V2</li><li>The model was trained with around 250 pictures and around 3000 steps after batch size of 8 I believe (V1), and around 500 pictures and around 2500 steps after a batch of 12 (V2)</li><li>V2 is here.</li></ul><hr />If you want to check the other retrains of mine, here you go:<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/481305/lora-flat2danimerge-pony">flat2DAnimerge</a> (<a target="_blank" rel="ugc" href="https://civarchive.com/models/35960?modelVersionId=266360">Original</a> by @bigbeanboiler)</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/495396/lora-animeliner-pony">Animeliner</a> (LoRA) (<a target="_blank" rel="ugc" href="https://tensor.art/models/607774770718784729">Original</a> by @Goofy_Ai)</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/533768/lora-sd15lorium-pony">SD15Lorium </a>(LoRA trained on data from 34 checkpoints, with triggers for all of them. It's kinda bad since it was trained with rank of 16 I believe)</li></ul>

Files with SHA256: d0b1e722ba2448b0ddc0c941cfc59eb2a9bead506343947aa921d6c0b45c8d0c