<h1 id="noobai-xl-lora-mike-no-hito-ov2wye1ms">NoobAI XL LoRA Mike No Hito</h1>This is a LoRA for the <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294?modelVersionId=1116447">v1.1 version of the NoobAI XL model</a>.The dataset <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/v2ray/mike-no-hito">v2ray/mike-no-hito</a> used to train this LoRA is scraped using <a target="_blank" rel="ugc" href="https://github.com/LagPixelLOL/mitgw">LagPixelLOL/mitgw</a>, containing a total of 172 images.Big thanks to the artist for the very cute catgirls :3, you can find the artist on X (Twitter) with ID <a target="_blank" rel="ugc" href="https://x.com/doremifaso64">@doremifaso64</a>.To use this LoRA, you can use the trigger word <code>mike no hito</code>. The artist is a furry artist so this will have a chance to make a character into a furry unprompted, if you encounter this, simply add <code>furry</code> to the negative prompt.This LoRA is trained using <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">kohya-ss/sd-scripts</a>, with rank 32, alpha 16, learning rate 1e-4, for 512 epochs with a total of 9728 steps, using an A100-80GB, took approximately 14 hours.If you have any questions, suggestions, or just want to talk to me, you can add me on Discord with ID <a target="_blank" rel="ugc" href="https://discord.gg/r4Wj97nZ">@v2ray</a>.<h2 id="changelog-xawmh6fju">Changelog</h2><ul><li>v2.2: This version is trained with rank 32, for 512 epochs (384 more epochs compared to v2.1), I didn't expect it to work but it actually works pretty well. If you think it's bad you can always use an older version.</li><li>v2.1: This version is trained with 3x3 Conv2d layers targeted, for 128 epochs (64 more epochs compared to v2.0).</li><li>v2.0: This version added a lot more training data, which are hand picked, cleaned, and deduped by me, mostly by hand. It has improved non-furry ability thanks to generalization, and overall better quality.</li></ul>

NoobAI XL LoRA Mike No Hito

This version is trained with rank 32, for 512 epochs (384 more epochs compared to v2.1), I didn't expect it to work but it actually works pretty well. If you think it's bad you can always use an older version.

Files with SHA256: fccf9d6664767ccad33c19cc063f5ba5701dea92e5cde58a51aa6deb290c8f4d