<h2 id="news">🎊NEWS🎊</h2>I made a v6.0 ZIT.zit - Maybe there aren't enough learning stepsanima - I think I set the training parameters wrong! (*ﾉω・*)ﾃﾍboogu - booooooooooogu! turbo lora is HF repo<h2 id="todo">🎏TODO🎏</h2>Create a new dataset for V6.1<s>Adjusting the bias in the v6.0 dataset and the training parameters.</s><s>Creating the ZIT Version.</s>All glory to Boogu!<h2 id="about-sample-image">🐷About sample image🐷</h2>standardized the sample images for V5.4.<ul><li>Same prompt.</li><li>Same resolution. (3:4, 1.5M pixels)</li><li>No upscaling.</li><li>Different seeds.</li><li>Using distilled LORA.</li></ul><h2 id="version-history">🎴Version History🎴</h2>V6.0 New concept|2D|ー🐈ーーーーーーーーー|2.5D|ーーーーーーーーーー|3D|V5.4 jitome return!!|2D|ーーーーーーー🐈ーーー|2.5D|ーーーーーーーーーー|3D|V5.0 boogu test|2D|ーー🐈ーーーーーーーー|2.5D|ーーーーーーーーーー|3D|v4.1 ill int8 only! 🍦I'll make bf16 later too (if I remember...).|2D|ーーー🐈ーーーーーーー|2.5D|ーーーーーーーーーー|3D|v4.0 jitome love|2D|ーーー🐈ーーーーーーー|2.5D|ーーーーーーーーーー|3D|V3.0 change base model|2D|ーーーーー🐈ーーーーー|2.5D|ーーーーーーーーーー|3D|V2.0|2D|ーー🐈ーーーーーーーー|2.5D|ーーーーーーーーーー|3D|thanks <a target="_blank" rel="ugc" href="https://civarchive.com/user/maxfeifei8">maxfeifei8</a>’s <a target="_blank" rel="ugc" href="https://civarchive.com/models/1318945/one-obsession">one obsession</a>V1.0|2D|ーーーー🐈ーーーーーー|2.5D|ーーーーーーーーーー|3D|<hr />P.S.Since I'm training on a potato PC, the lack of training data is really noticeable!Training boogu… 10 hours per 1,000 steps with an RTX 3060 and 12 GB of VRAM…あとがきじゃがいもPCで学習してるので学習データ不足が目立ちますね！許してちょんまげ！booguの学習…RTX3060 VRAM12Gで1000STEPあたり10時間…

nununu mix

Merge the LORA model trained on images generated by nununu mix v4.1 illfp8 is int84step model

Files with SHA256: f724c5201f395c287082c55fa48579cc4e99c9a98876d68bd6fb7c8e1fd097c1