I named my simple algorithm that generate new merging recipe near current and let user choose which is better to "learn" the best weight merging ratios with a exaggerated name "RMHF - Reinforcement Merging on Human Feedback".<a target="_blank" rel="ugc" href="https://github.com/TkskKurumi/DiffusersFastAPI/blob/main/rmhf_v2.py">https://github.com/TkskKurumi/DiffusersFastAPI/blob/main/rmhf_v2.py</a>

RMHF

This is a merged model of following models. Huge thanks for the creators for these amazing models.<ul><li><a target="_blank" rel="ugc" href="https://civitai.com/models/18427?modelVersionId=95199">Fantexi - V0.9 Beta</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/101518">RMHF - 2.5D-V3</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/101518/rmhf">RMHF - AnimeV3</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/7240">MeinaMix - V11</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/28169/cuteyukimixadorable-style">CuteYukiMix - NeoChapter</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/100505?modelVersionId=107578">Kakigori - V1</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/77751/nextgenmix">NextGen Mix - R2.8</a></li><li><a target="_blank" rel="ugc" href="https://civitai.com/models/44605?modelVersionId=112251">NullStyle - V2</a></li></ul>

Files with SHA256: 428a35ae0d637c1917c48c50c78e7a6576b3f28d077744408a8511d20220d3c4