<p>x.com/horayo328518</p><h3 id="moss">moss</h3><p>Activation <span style="color:rgb(130, 201, 30)">by laoshi</span></p><p>either fizgig is an ass trainer or the model has a tendency to consistently increase loss at 1mp. any lr tuners try to dump it all the way to e-6 so the adapter never learns, and even resuming training at 1mp after 0.25mp initial epochs produced worse results. Thus, this draft lora is trained on 512x512.</p><p><span style="color:rgb(58, 58, 61)">everyone are doing the new hype model<br />i wanna be trendy too...</span></p><h3 id="anima">anima</h3><p>I realized civitai has free storage. Now picking good epoch is your problem.</p><p>Activation tag <span style="color:rgb(255, 189, 212)">@laoshi wo hao e</span></p>

Files with SHA256: 948f938a5fd6d60e8ad686d06473cb4eb3bfee5ab13cdc290f7b31f42eb2adcb